Token | the |
Token ID | 262 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
shampoo | +0.025 |
L | +0.024 |
common | +0.023 |
Qu | +0.022 |
fault | +0.022 |
Neg logit contributions | |
pole | -0.029 |
emaker | -0.028 |
umbo | -0.028 |
warrior | -0.028 |
ickets | -0.027 |
Token | pigeon |
Token ID | 46387 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
warrior | +0.026 |
owl | +0.024 |
King | +0.023 |
eagle | +0.023 |
angel | +0.023 |
Neg logit contributions | |
ours | -0.045 |
vinegar | -0.044 |
fault | -0.043 |
bruises | -0.042 |
common | -0.042 |
Token | all |
Token ID | 477 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
shampoo | +0.009 |
fault | +0.009 |
L | +0.009 |
common | +0.009 |
vinegar | +0.009 |
Neg logit contributions | |
pole | -0.008 |
emaker | -0.008 |
warrior | -0.008 |
ickets | -0.008 |
ados | -0.008 |
Token | those |
Token ID | 883 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
pole | +0.062 |
emaker | +0.059 |
warrior | +0.056 |
ickets | +0.056 |
stone | +0.054 |
Neg logit contributions | |
fault | -0.080 |
shampoo | -0.079 |
vinegar | -0.079 |
bruises | -0.077 |
aj | -0.075 |
Token | weeks |
Token ID | 2745 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
fault | +0.106 |
vinegar | +0.103 |
shampoo | +0.102 |
common | +0.100 |
L | +0.097 |
Neg logit contributions | |
pole | -0.078 |
warrior | -0.075 |
emaker | -0.072 |
stone | -0.072 |
ickets | -0.070 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
fault | +0.076 |
vinegar | +0.074 |
shampoo | +0.074 |
common | +0.072 |
bruises | +0.071 |
Neg logit contributions | |
pole | -0.059 |
emaker | -0.055 |
stone | -0.053 |
ickets | -0.053 |
warrior | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
vinegar | +0.252 |
shampoo | +0.247 |
common | +0.243 |
bruises | +0.242 |
fault | +0.239 |
Neg logit contributions | |
pole | -0.180 |
emaker | -0.162 |
ados | -0.158 |
person | -0.154 |
warrior | -0.154 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
shampoo | +0.006 |
L | +0.006 |
fault | +0.005 |
Qu | +0.005 |
common | +0.005 |
Neg logit contributions | |
pole | -0.011 |
emaker | -0.011 |
warrior | -0.011 |
ados | -0.010 |
ickets | -0.010 |
Token | Mike |
Token ID | 16073 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
fault | +0.014 |
shampoo | +0.014 |
vinegar | +0.013 |
bruises | +0.013 |
common | +0.013 |
Neg logit contributions | |
pole | -0.016 |
ickets | -0.015 |
emaker | -0.015 |
warrior | -0.015 |
oon | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
fault | +0.031 |
shampoo | +0.031 |
bruises | +0.031 |
vinegar | +0.031 |
common | +0.030 |
Neg logit contributions | |
pole | -0.017 |
emaker | -0.016 |
warrior | -0.015 |
ickets | -0.014 |
umb | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
shampoo | +0.021 |
fault | +0.020 |
L | +0.020 |
common | +0.020 |
vinegar | +0.019 |
Neg logit contributions | |
pole | -0.023 |
emaker | -0.022 |
warrior | -0.022 |
ickets | -0.022 |
ados | -0.021 |
Token | velvet |
Token ID | 47750 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
pole | +0.048 |
warrior | +0.047 |
King | +0.046 |
stone | +0.045 |
eagle | +0.045 |
Neg logit contributions | |
ours | -0.057 |
L | -0.055 |
vinegar | -0.055 |
aj | -0.054 |
shampoo | -0.054 |
Token | box |
Token ID | 3091 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
shampoo | +0.008 |
fault | +0.008 |
vinegar | +0.008 |
common | +0.008 |
L | +0.008 |
Neg logit contributions | |
pole | -0.006 |
emaker | -0.006 |
warrior | -0.006 |
ickets | -0.006 |
ados | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
pole | +0.063 |
emaker | +0.058 |
warrior | +0.058 |
stone | +0.057 |
ickets | +0.056 |
Neg logit contributions | |
shampoo | -0.066 |
fault | -0.064 |
vinegar | -0.063 |
common | -0.062 |
bruises | -0.061 |
Token | those |
Token ID | 883 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
pole | +0.058 |
emaker | +0.052 |
warrior | +0.051 |
ickets | +0.048 |
stone | +0.047 |
Neg logit contributions | |
shampoo | -0.135 |
fault | -0.133 |
vinegar | -0.131 |
bruises | -0.130 |
L | -0.128 |
Token | years |
Token ID | 812 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
fault | +0.087 |
shampoo | +0.085 |
vinegar | +0.084 |
common | +0.080 |
ours | +0.080 |
Neg logit contributions | |
pole | -0.064 |
warrior | -0.059 |
stone | -0.058 |
King | -0.056 |
emaker | -0.055 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
bruises | +0.143 |
shampoo | +0.142 |
vinegar | +0.138 |
fault | +0.136 |
mustard | +0.129 |
Neg logit contributions | |
pole | -0.106 |
stone | -0.103 |
warrior | -0.098 |
person | -0.096 |
King | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
shampoo | +0.242 |
vinegar | +0.235 |
bruises | +0.230 |
common | +0.229 |
fault | +0.229 |
Neg logit contributions | |
pole | -0.182 |
ados | -0.165 |
emaker | -0.160 |
person | -0.160 |
stone | -0.160 |
Token | They |
Token ID | 1119 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
pole | +0.002 |
ickets | +0.002 |
amber | +0.002 |
umbo | +0.002 |
warrior | +0.002 |
Neg logit contributions | |
bruises | -0.002 |
ruined | -0.002 |
shampoo | -0.002 |
vinegar | -0.002 |
fault | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
pole | +0.013 |
emaker | +0.013 |
warrior | +0.013 |
ickets | +0.012 |
ados | +0.012 |
Neg logit contributions | |
shampoo | -0.009 |
fault | -0.009 |
vinegar | -0.009 |
common | -0.009 |
L | -0.009 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
pole | +0.010 |
emaker | +0.010 |
warrior | +0.010 |
ickets | +0.009 |
ados | +0.009 |
Neg logit contributions | |
shampoo | -0.011 |
fault | -0.010 |
vinegar | -0.010 |
common | -0.010 |
L | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
warrior | +0.014 |
King | +0.014 |
Peter | +0.014 |
stone | +0.013 |
ados | +0.013 |
Neg logit contributions | |
vinegar | -0.019 |
bruises | -0.019 |
aj | -0.019 |
common | -0.019 |
fault | -0.018 |
Token | ancestors |
Token ID | 18668 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
shampoo | +0.082 |
vinegar | +0.081 |
fault | +0.081 |
common | +0.079 |
L | +0.078 |
Neg logit contributions | |
pole | -0.065 |
warrior | -0.064 |
emaker | -0.062 |
ickets | -0.060 |
stone | -0.059 |
Token | who |
Token ID | 508 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
shampoo | +0.047 |
fault | +0.046 |
vinegar | +0.045 |
common | +0.045 |
bruises | +0.044 |
Neg logit contributions | |
pole | -0.042 |
warrior | -0.040 |
emaker | -0.040 |
ickets | -0.039 |
ados | -0.038 |
Token | sang |
Token ID | 25889 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
fault | +0.062 |
shampoo | +0.061 |
vinegar | +0.060 |
bruises | +0.058 |
L | +0.057 |
Neg logit contributions | |
pole | -0.088 |
warrior | -0.087 |
emaker | -0.085 |
ickets | -0.084 |
stone | -0.082 |
Token | it |
Token ID | 340 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
shampoo | +0.013 |
fault | +0.013 |
vinegar | +0.013 |
bruises | +0.012 |
common | +0.012 |
Neg logit contributions | |
pole | -0.014 |
warrior | -0.014 |
emaker | -0.013 |
ickets | -0.013 |
ados | -0.013 |
Token | long |
Token ID | 890 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
shampoo | +0.037 |
fault | +0.037 |
common | +0.037 |
L | +0.035 |
cheaper | +0.032 |
Neg logit contributions | |
emaker | -0.050 |
ados | -0.046 |
umbo | -0.046 |
warrior | -0.046 |
person | -0.045 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
vinegar | +0.094 |
shampoo | +0.092 |
bruises | +0.092 |
fault | +0.089 |
ours | +0.087 |
Neg logit contributions | |
pole | -0.068 |
warrior | -0.063 |
emaker | -0.061 |
ickets | -0.060 |
stone | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -7.74e-03 |
Pos logit contributions | |
shampoo | +0.230 |
vinegar | +0.226 |
fault | +0.220 |
bruises | +0.219 |
common | +0.218 |
Neg logit contributions | |
pole | -0.197 |
emaker | -0.177 |
warrior | -0.175 |
ados | -0.175 |
ickets | -0.172 |
Token | Would |
Token ID | 10928 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
pole | +0.012 |
emaker | +0.011 |
warrior | +0.011 |
ados | +0.011 |
stone | +0.011 |
Neg logit contributions | |
shampoo | -0.011 |
L | -0.011 |
fault | -0.011 |
vinegar | -0.010 |
common | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
shampoo | +0.033 |
L | +0.031 |
vinegar | +0.031 |
fault | +0.031 |
common | +0.031 |
Neg logit contributions | |
pole | -0.030 |
emaker | -0.029 |
warrior | -0.029 |
ickets | -0.028 |
ados | -0.027 |
Token | like |
Token ID | 588 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
pole | +0.022 |
warrior | +0.022 |
ickets | +0.021 |
emaker | +0.021 |
stone | +0.020 |
Neg logit contributions | |
vinegar | -0.015 |
fault | -0.015 |
bruises | -0.015 |
shampoo | -0.015 |
L | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.014 |
ickets | +0.014 |
emaker | +0.013 |
stone | +0.013 |
Neg logit contributions | |
fault | -0.015 |
vinegar | -0.015 |
shampoo | -0.015 |
bruises | -0.015 |
common | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
fault | +0.020 |
shampoo | +0.020 |
vinegar | +0.019 |
common | +0.019 |
bruises | +0.018 |
Neg logit contributions | |
pole | -0.021 |
emaker | -0.020 |
warrior | -0.020 |
ados | -0.020 |
ickets | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -8.70e-04 |
Pos logit contributions | |
fault | +0.018 |
aj | +0.018 |
ses | +0.017 |
vinegar | +0.017 |
bruises | +0.017 |
Neg logit contributions | |
ados | -0.011 |
Charlie | -0.011 |
pole | -0.011 |
King | -0.010 |
mushroom | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
pole | +0.001 |
warrior | +0.001 |
emaker | +0.001 |
ados | +0.001 |
stone | +0.001 |
Neg logit contributions | |
shampoo | -0.001 |
fault | -0.001 |
vinegar | -0.001 |
common | -0.001 |
L | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
shampoo | +0.071 |
fault | +0.069 |
L | +0.068 |
vinegar | +0.067 |
common | +0.067 |
Neg logit contributions | |
pole | -0.039 |
warrior | -0.038 |
emaker | -0.038 |
ickets | -0.037 |
ados | -0.036 |
Token | 's |
Token ID | 338 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
shampoo | +0.030 |
fault | +0.030 |
vinegar | +0.029 |
common | +0.029 |
L | +0.029 |
Neg logit contributions | |
pole | -0.015 |
emaker | -0.014 |
warrior | -0.014 |
ickets | -0.013 |
ados | -0.013 |
Token | brand |
Token ID | 4508 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
shampoo | +0.047 |
fault | +0.046 |
vinegar | +0.046 |
common | +0.045 |
L | +0.044 |
Neg logit contributions | |
pole | -0.046 |
warrior | -0.044 |
ados | -0.042 |
emaker | -0.042 |
stone | -0.042 |
Token | new |
Token ID | 649 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
shampoo | +0.143 |
fault | +0.140 |
vinegar | +0.134 |
common | +0.132 |
bruises | +0.130 |
Neg logit contributions | |
pole | -0.267 |
emaker | -0.258 |
warrior | -0.257 |
ickets | -0.252 |
ados | -0.250 |
Token | table |
Token ID | 3084 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
shampoo | +0.109 |
fault | +0.108 |
vinegar | +0.106 |
L | +0.103 |
bruises | +0.103 |
Neg logit contributions | |
pole | -0.125 |
warrior | -0.120 |
emaker | -0.117 |
ados | -0.115 |
stone | -0.115 |
Token | ! |
Token ID | 0 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
shampoo | +0.038 |
fault | +0.037 |
vinegar | +0.037 |
common | +0.036 |
bruises | +0.036 |
Neg logit contributions | |
pole | -0.032 |
emaker | -0.029 |
warrior | -0.029 |
stone | -0.028 |
ados | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
shampoo | +0.003 |
fault | +0.003 |
L | +0.002 |
vinegar | +0.002 |
common | +0.002 |
Neg logit contributions | |
pole | -0.002 |
emaker | -0.002 |
warrior | -0.002 |
stone | -0.002 |
ickets | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
shampoo | +0.011 |
fault | +0.011 |
vinegar | +0.011 |
common | +0.011 |
L | +0.010 |
Neg logit contributions | |
pole | -0.018 |
emaker | -0.017 |
warrior | -0.017 |
ickets | -0.017 |
ados | -0.016 |
Token | showed |
Token ID | 3751 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
fault | +0.006 |
shampoo | +0.006 |
vinegar | +0.006 |
common | +0.006 |
bruises | +0.006 |
Neg logit contributions | |
pole | -0.007 |
warrior | -0.006 |
emaker | -0.006 |
stone | -0.006 |
ickets | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
emaker | +0.009 |
pole | +0.009 |
ados | +0.008 |
warrior | +0.008 |
ickets | +0.008 |
Neg logit contributions | |
fault | -0.012 |
common | -0.011 |
shampoo | -0.011 |
vinegar | -0.011 |
bruises | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
shampoo | +0.009 |
common | +0.009 |
fault | +0.009 |
vinegar | +0.009 |
bruises | +0.009 |
Neg logit contributions | |
pole | -0.012 |
emaker | -0.011 |
ados | -0.011 |
warrior | -0.011 |
stone | -0.011 |
Token | other |
Token ID | 584 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
mushroom | +0.022 |
image | +0.022 |
King | +0.021 |
ados | +0.021 |
stone | +0.021 |
Neg logit contributions | |
ours | -0.033 |
Qu | -0.033 |
vinegar | -0.033 |
shampoo | -0.032 |
Aw | -0.032 |
Token | bath |
Token ID | 7837 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
vinegar | +0.066 |
ours | +0.066 |
common | +0.066 |
shampoo | +0.065 |
fault | +0.065 |
Neg logit contributions | |
warrior | -0.060 |
pole | -0.059 |
emaker | -0.058 |
ados | -0.058 |
ickets | -0.056 |
Token | ro |
Token ID | 305 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
common | +0.147 |
bruises | +0.144 |
fault | +0.142 |
vinegar | +0.140 |
cheaper | +0.139 |
Neg logit contributions | |
est | -0.074 |
around | -0.074 |
ickets | -0.072 |
oon | -0.071 |
emaker | -0.069 |
Token | bes |
Token ID | 12636 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
fault | +0.222 |
shampoo | +0.221 |
vinegar | +0.220 |
L | +0.217 |
ours | +0.214 |
Neg logit contributions | |
pole | -0.177 |
oon | -0.166 |
emaker | -0.164 |
ados | -0.164 |
warrior | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
shampoo | +0.061 |
common | +0.061 |
fault | +0.060 |
vinegar | +0.060 |
L | +0.059 |
Neg logit contributions | |
pole | -0.048 |
emaker | -0.043 |
stone | -0.042 |
warrior | -0.042 |
ados | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
fault | +0.011 |
common | +0.011 |
bruises | +0.011 |
shampoo | +0.011 |
vinegar | +0.010 |
Neg logit contributions | |
pole | -0.008 |
ados | -0.007 |
ickets | -0.007 |
warrior | -0.007 |
emaker | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
pole | +0.022 |
lf | +0.021 |
warrior | +0.020 |
stone | +0.019 |
around | +0.019 |
Neg logit contributions | |
fault | -0.031 |
common | -0.026 |
vinegar | -0.026 |
injuries | -0.026 |
bruises | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +9.10e-04 |
Pos logit contributions | |
ours | +0.037 |
ses | +0.035 |
etchup | +0.034 |
arose | +0.033 |
common | +0.033 |
Neg logit contributions | |
Charlie | -0.016 |
around | -0.016 |
pole | -0.015 |
dragons | -0.015 |
all | -0.015 |
Token | man |
Token ID | 582 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
fault | +0.053 |
common | +0.051 |
ours | +0.050 |
ucker | +0.048 |
L | +0.047 |
Neg logit contributions | |
warrior | -0.031 |
King | -0.029 |
pole | -0.028 |
knight | -0.027 |
eagle | -0.027 |
Token | drove |
Token ID | 10357 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
fault | +0.007 |
shampoo | +0.006 |
common | +0.006 |
vinegar | +0.006 |
bruises | +0.006 |
Neg logit contributions | |
pole | -0.010 |
warrior | -0.010 |
emaker | -0.010 |
stone | -0.010 |
ickets | -0.009 |
Token | off |
Token ID | 572 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
shampoo | +0.039 |
fault | +0.038 |
vinegar | +0.037 |
common | +0.037 |
L | +0.036 |
Neg logit contributions | |
pole | -0.029 |
emaker | -0.028 |
warrior | -0.028 |
ickets | -0.027 |
ados | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
pole | +0.045 |
emaker | +0.043 |
warrior | +0.043 |
ickets | +0.042 |
ados | +0.041 |
Neg logit contributions | |
shampoo | -0.044 |
fault | -0.043 |
vinegar | -0.042 |
L | -0.042 |
common | -0.042 |
Token | his |
Token ID | 465 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
fault | +0.006 |
aj | +0.006 |
shampoo | +0.006 |
ours | +0.006 |
vinegar | +0.006 |
Neg logit contributions | |
warrior | -0.004 |
Charlie | -0.004 |
King | -0.004 |
emaker | -0.004 |
pole | -0.004 |
Token | brand |
Token ID | 4508 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
fault | +0.069 |
shampoo | +0.068 |
vinegar | +0.067 |
L | +0.066 |
common | +0.064 |
Neg logit contributions | |
warrior | -0.048 |
pole | -0.047 |
King | -0.044 |
kingdom | -0.043 |
ados | -0.042 |
Token | new |
Token ID | 649 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
shampoo | +0.168 |
fault | +0.168 |
bruises | +0.165 |
vinegar | +0.163 |
common | +0.160 |
Neg logit contributions | |
pole | -0.230 |
ados | -0.216 |
stone | -0.213 |
emaker | -0.212 |
warrior | -0.211 |
Token | car |
Token ID | 1097 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
vinegar | +0.160 |
fault | +0.157 |
L | +0.156 |
shampoo | +0.155 |
ours | +0.152 |
Neg logit contributions | |
pole | -0.103 |
warrior | -0.099 |
est | -0.090 |
ados | -0.088 |
King | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
shampoo | +0.170 |
fault | +0.168 |
vinegar | +0.164 |
common | +0.163 |
L | +0.160 |
Neg logit contributions | |
pole | -0.136 |
emaker | -0.128 |
warrior | -0.128 |
ickets | -0.122 |
ados | -0.121 |
Token | and |
Token ID | 290 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
fault | +0.014 |
shampoo | +0.013 |
common | +0.013 |
vinegar | +0.013 |
bruises | +0.012 |
Neg logit contributions | |
pole | -0.012 |
warrior | -0.011 |
emaker | -0.011 |
stone | -0.011 |
ados | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
pole | +0.012 |
warrior | +0.012 |
emaker | +0.012 |
stone | +0.011 |
King | +0.011 |
Neg logit contributions | |
fault | -0.014 |
common | -0.013 |
shampoo | -0.013 |
vinegar | -0.013 |
ours | -0.013 |
Token | children |
Token ID | 1751 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
pole | +0.017 |
warrior | +0.017 |
stone | +0.016 |
King | +0.016 |
eagle | +0.015 |
Neg logit contributions | |
fault | -0.016 |
vinegar | -0.015 |
shampoo | -0.015 |
common | -0.014 |
bruises | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
shampoo | +0.070 |
common | +0.070 |
fault | +0.070 |
vinegar | +0.070 |
bruises | +0.067 |
Neg logit contributions | |
pole | -0.071 |
warrior | -0.063 |
ickets | -0.063 |
emaker | -0.062 |
King | -0.061 |
Token | on |
Token ID | 319 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
pole | +0.026 |
down | +0.026 |
ados | +0.026 |
around | +0.025 |
est | +0.023 |
Neg logit contributions | |
fault | -0.036 |
common | -0.033 |
aj | -0.033 |
bruises | -0.032 |
rou | -0.032 |
Token | their |
Token ID | 511 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ados | +0.026 |
Charlie | +0.025 |
pole | +0.025 |
King | +0.024 |
around | +0.024 |
Neg logit contributions | |
fault | -0.023 |
ses | -0.022 |
aj | -0.021 |
ours | -0.021 |
bruises | -0.021 |
Token | bath |
Token ID | 7837 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
fault | +0.032 |
arose | +0.031 |
ours | +0.030 |
ucker | +0.030 |
L | +0.029 |
Neg logit contributions | |
warrior | -0.028 |
King | -0.027 |
pole | -0.027 |
ados | -0.027 |
eagle | -0.026 |
Token | ro |
Token ID | 305 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
bruises | +0.164 |
vinegar | +0.162 |
fault | +0.159 |
common | +0.157 |
ruined | +0.153 |
Neg logit contributions | |
pole | -0.091 |
oon | -0.091 |
est | -0.090 |
ickets | -0.089 |
around | -0.087 |
Token | bes |
Token ID | 12636 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
vinegar | +0.224 |
fault | +0.220 |
bruises | +0.219 |
shampoo | +0.217 |
ours | +0.212 |
Neg logit contributions | |
pole | -0.177 |
oon | -0.166 |
emaker | -0.159 |
warrior | -0.159 |
ados | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
shampoo | +0.063 |
fault | +0.063 |
vinegar | +0.062 |
common | +0.061 |
bruises | +0.061 |
Neg logit contributions | |
pole | -0.052 |
warrior | -0.048 |
emaker | -0.048 |
ickets | -0.047 |
stone | -0.046 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
fault | +0.027 |
common | +0.024 |
vinegar | +0.022 |
rou | +0.022 |
ses | +0.021 |
Neg logit contributions | |
forth | -0.021 |
down | -0.021 |
warrior | -0.021 |
pole | -0.021 |
King | -0.020 |
Token | around |
Token ID | 1088 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
pole | +0.002 |
down | +0.002 |
warrior | +0.002 |
around | +0.002 |
emaker | +0.002 |
Neg logit contributions | |
fault | -0.006 |
vinegar | -0.006 |
bruises | -0.006 |
shampoo | -0.006 |
common | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
around | +0.030 |
down | +0.028 |
warrior | +0.026 |
through | +0.025 |
outside | +0.025 |
Neg logit contributions | |
fault | -0.052 |
bruises | -0.050 |
vinegar | -0.050 |
aj | -0.050 |
ours | -0.049 |
Token | his |
Token ID | 465 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
fault | +0.015 |
shampoo | +0.015 |
bruises | +0.014 |
vinegar | +0.014 |
common | +0.014 |
Neg logit contributions | |
pole | -0.015 |
warrior | -0.015 |
emaker | -0.015 |
ickets | -0.014 |
ados | -0.014 |
Token | favorite |
Token ID | 4004 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
shampoo | +0.013 |
vinegar | +0.013 |
fault | +0.013 |
bruises | +0.013 |
L | +0.013 |
Neg logit contributions | |
warrior | -0.012 |
pole | -0.011 |
King | -0.011 |
ados | -0.010 |
stone | -0.010 |
Token | shows |
Token ID | 2523 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
shampoo | +0.040 |
fault | +0.040 |
vinegar | +0.039 |
common | +0.038 |
L | +0.038 |
Neg logit contributions | |
pole | -0.035 |
emaker | -0.033 |
warrior | -0.033 |
ickets | -0.032 |
ados | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
pole | +0.033 |
warrior | +0.030 |
emaker | +0.030 |
ickets | +0.030 |
ados | +0.029 |
Neg logit contributions | |
shampoo | -0.038 |
fault | -0.038 |
vinegar | -0.038 |
common | -0.037 |
bruises | -0.037 |
Token | their |
Token ID | 511 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
warrior | +0.017 |
pole | +0.016 |
Charlie | +0.016 |
King | +0.016 |
lf | +0.016 |
Neg logit contributions | |
fault | -0.022 |
vinegar | -0.021 |
bruises | -0.021 |
shampoo | -0.021 |
ours | -0.020 |
Token | brand |
Token ID | 4508 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
shampoo | +0.024 |
vinegar | +0.024 |
fault | +0.024 |
L | +0.024 |
bruises | +0.023 |
Neg logit contributions | |
pole | -0.023 |
warrior | -0.023 |
ados | -0.021 |
King | -0.021 |
stone | -0.021 |
Token | new |
Token ID | 649 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
fault | +0.150 |
shampoo | +0.149 |
bruises | +0.145 |
vinegar | +0.143 |
common | +0.139 |
Neg logit contributions | |
pole | -0.252 |
warrior | -0.238 |
emaker | -0.238 |
ickets | -0.236 |
ados | -0.234 |
Token | television |
Token ID | 5581 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
shampoo | +0.128 |
fault | +0.125 |
common | +0.121 |
vinegar | +0.121 |
L | +0.119 |
Neg logit contributions | |
pole | -0.119 |
emaker | -0.115 |
warrior | -0.113 |
ickets | -0.111 |
ados | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
shampoo | +0.047 |
fault | +0.047 |
vinegar | +0.045 |
common | +0.045 |
L | +0.044 |
Neg logit contributions | |
pole | -0.048 |
emaker | -0.046 |
warrior | -0.046 |
ickets | -0.044 |
ados | -0.044 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
pole | +0.004 |
ickets | +0.003 |
umbo | +0.003 |
warrior | +0.003 |
Charlie | +0.003 |
Neg logit contributions | |
shampoo | -0.004 |
fault | -0.004 |
vinegar | -0.004 |
common | -0.004 |
bruises | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
fault | +0.005 |
shampoo | +0.005 |
vinegar | +0.005 |
bruises | +0.005 |
common | +0.004 |
Neg logit contributions | |
pole | -0.005 |
emaker | -0.005 |
ickets | -0.005 |
warrior | -0.005 |
oon | -0.005 |
Token | â |
Token ID | 22940 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
fault | +0.036 |
shampoo | +0.035 |
common | +0.034 |
vinegar | +0.034 |
bruises | +0.034 |
Neg logit contributions | |
pole | -0.042 |
warrior | -0.041 |
emaker | -0.040 |
ickets | -0.040 |
stone | -0.039 |
Token | € |
Token ID | 26391 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
shampoo | +0.053 |
fault | +0.053 |
vinegar | +0.051 |
common | +0.051 |
L | +0.050 |
Neg logit contributions | |
pole | -0.037 |
emaker | -0.035 |
warrior | -0.034 |
ickets | -0.033 |
ados | -0.032 |
Token | ™ |
Token ID | 8151 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
shampoo | +0.059 |
vinegar | +0.058 |
fault | +0.057 |
common | +0.055 |
bruises | +0.055 |
Neg logit contributions | |
pole | -0.054 |
warrior | -0.052 |
ickets | -0.052 |
emaker | -0.052 |
ados | -0.050 |
Token | s |
Token ID | 82 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
shampoo | +0.098 |
bruises | +0.097 |
vinegar | +0.096 |
fault | +0.095 |
common | +0.094 |
Neg logit contributions | |
pole | -0.074 |
ickets | -0.072 |
emaker | -0.069 |
umb | -0.066 |
umbo | -0.066 |
Token | Spring |
Token ID | 8225 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
vinegar | +0.033 |
bruises | +0.033 |
common | +0.033 |
fault | +0.032 |
shampoo | +0.032 |
Neg logit contributions | |
pole | -0.036 |
est | -0.033 |
ickets | -0.033 |
around | -0.032 |
down | -0.031 |
Token | time |
Token ID | 2435 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
bruises | +0.093 |
fault | +0.091 |
vinegar | +0.090 |
shampoo | +0.086 |
common | +0.084 |
Neg logit contributions | |
pole | -0.095 |
warrior | -0.093 |
ickets | -0.089 |
est | -0.089 |
emaker | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
bruises | +0.219 |
fault | +0.217 |
vinegar | +0.214 |
shampoo | +0.204 |
ours | +0.204 |
Neg logit contributions | |
pole | -0.172 |
warrior | -0.162 |
est | -0.157 |
ickets | -0.157 |
King | -0.152 |
Token | This |
Token ID | 770 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
fault | +0.003 |
common | +0.003 |
vinegar | +0.003 |
ruined | +0.003 |
shampoo | +0.003 |
Neg logit contributions | |
pole | -0.002 |
ickets | -0.002 |
warrior | -0.002 |
emaker | -0.002 |
umbo | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
bruises | +0.054 |
fault | +0.053 |
vinegar | +0.053 |
ses | +0.050 |
injuries | +0.049 |
Neg logit contributions | |
warrior | -0.059 |
pole | -0.057 |
est | -0.056 |
ickets | -0.055 |
oon | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ses | +0.038 |
bruises | +0.037 |
fault | +0.036 |
aj | +0.035 |
vinegar | +0.035 |
Neg logit contributions | |
around | -0.025 |
pole | -0.024 |
Charlie | -0.024 |
King | -0.023 |
forward | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
warrior | +0.038 |
pole | +0.037 |
King | +0.036 |
eagle | +0.036 |
angel | +0.033 |
Neg logit contributions | |
ours | -0.055 |
fault | -0.054 |
vinegar | -0.053 |
bruises | -0.053 |
common | -0.052 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
warrior | +0.002 |
pole | +0.002 |
emaker | +0.001 |
stone | +0.001 |
eagle | +0.001 |
Neg logit contributions | |
shampoo | -0.003 |
fault | -0.003 |
vinegar | -0.003 |
common | -0.003 |
aj | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
shampoo | +0.017 |
fault | +0.016 |
vinegar | +0.016 |
common | +0.016 |
bruises | +0.016 |
Neg logit contributions | |
pole | -0.015 |
emaker | -0.014 |
warrior | -0.014 |
stone | -0.013 |
ickets | -0.013 |
Token | You |
Token ID | 921 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
pole | +0.012 |
emaker | +0.012 |
warrior | +0.012 |
ickets | +0.011 |
ados | +0.011 |
Neg logit contributions | |
shampoo | -0.017 |
fault | -0.016 |
vinegar | -0.016 |
common | -0.016 |
L | -0.016 |
Token | admit |
Token ID | 9159 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
shampoo | +0.019 |
fault | +0.019 |
vinegar | +0.018 |
common | +0.018 |
L | +0.018 |
Neg logit contributions | |
pole | -0.041 |
emaker | -0.040 |
warrior | -0.039 |
ickets | -0.039 |
ados | -0.038 |
Token | your |
Token ID | 534 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
shampoo | +0.032 |
fault | +0.031 |
vinegar | +0.030 |
L | +0.030 |
common | +0.030 |
Neg logit contributions | |
pole | -0.037 |
emaker | -0.035 |
warrior | -0.035 |
ickets | -0.034 |
ados | -0.033 |
Token | fault |
Token ID | 8046 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
vinegar | +0.109 |
shampoo | +0.106 |
ours | +0.104 |
L | +0.104 |
Qu | +0.103 |
Neg logit contributions | |
warrior | -0.085 |
eagle | -0.085 |
owl | -0.084 |
angel | -0.082 |
pole | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +6.36e-03 |
Pos logit contributions | |
shampoo | +0.193 |
fault | +0.188 |
vinegar | +0.186 |
common | +0.185 |
bruises | +0.180 |
Neg logit contributions | |
pole | -0.200 |
emaker | -0.191 |
warrior | -0.189 |
ickets | -0.184 |
ados | -0.182 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
fault | +0.010 |
vinegar | +0.010 |
shampoo | +0.010 |
aj | +0.010 |
common | +0.010 |
Neg logit contributions | |
warrior | -0.008 |
pole | -0.008 |
ados | -0.008 |
owl | -0.008 |
stone | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
pole | +0.019 |
warrior | +0.018 |
ados | +0.018 |
emaker | +0.018 |
ickets | +0.017 |
Neg logit contributions | |
fault | -0.030 |
shampoo | -0.030 |
vinegar | -0.029 |
common | -0.028 |
bruises | -0.028 |
Token | mercy |
Token ID | 17703 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
owl | +0.007 |
warrior | +0.006 |
Charlie | +0.006 |
ados | +0.006 |
eagle | +0.006 |
Neg logit contributions | |
fault | -0.013 |
ours | -0.013 |
aj | -0.012 |
outed | -0.012 |
ucker | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
vinegar | +0.018 |
shampoo | +0.018 |
bleach | +0.017 |
bruises | +0.017 |
ses | +0.017 |
Neg logit contributions | |
pole | -0.008 |
warrior | -0.007 |
emaker | -0.007 |
est | -0.007 |
other | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
pole | +0.093 |
warrior | +0.090 |
emaker | +0.089 |
ickets | +0.087 |
stone | +0.085 |
Neg logit contributions | |
fault | -0.064 |
shampoo | -0.064 |
common | -0.061 |
vinegar | -0.061 |
bruises | -0.058 |
Token | so |
Token ID | 523 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
pole | +0.014 |
emaker | +0.014 |
warrior | +0.013 |
ickets | +0.013 |
ados | +0.013 |
Neg logit contributions | |
shampoo | -0.016 |
fault | -0.016 |
vinegar | -0.015 |
common | -0.015 |
L | -0.015 |
Token | proud |
Token ID | 6613 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.014 |
emaker | +0.014 |
ickets | +0.013 |
stone | +0.013 |
Neg logit contributions | |
shampoo | -0.017 |
fault | -0.017 |
vinegar | -0.017 |
common | -0.016 |
L | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
pole | +0.042 |
warrior | +0.040 |
emaker | +0.039 |
ickets | +0.039 |
stone | +0.038 |
Neg logit contributions | |
fault | -0.097 |
shampoo | -0.096 |
common | -0.095 |
vinegar | -0.094 |
bruises | -0.093 |
Token | their |
Token ID | 511 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
aj | +0.032 |
shampoo | +0.029 |
fault | +0.028 |
cheaper | +0.028 |
vinegar | +0.028 |
Neg logit contributions | |
pole | -0.024 |
Charlie | -0.024 |
warrior | -0.024 |
Bernie | -0.023 |
trolls | -0.023 |
Token | super |
Token ID | 2208 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
L | +0.054 |
shampoo | +0.052 |
fault | +0.051 |
vinegar | +0.050 |
common | +0.050 |
Neg logit contributions | |
warrior | -0.046 |
pole | -0.043 |
stone | -0.042 |
eagle | -0.042 |
ados | -0.041 |
Token | strong |
Token ID | 1913 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
shampoo | +0.189 |
fault | +0.185 |
vinegar | +0.180 |
common | +0.178 |
L | +0.177 |
Neg logit contributions | |
pole | -0.201 |
warrior | -0.193 |
emaker | -0.193 |
ickets | -0.187 |
ados | -0.184 |
Token | work |
Token ID | 670 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
shampoo | +0.078 |
vinegar | +0.076 |
L | +0.076 |
fault | +0.076 |
bruises | +0.075 |
Neg logit contributions | |
warrior | -0.067 |
pole | -0.065 |
emaker | -0.063 |
ados | -0.061 |
eagle | -0.060 |
Token | that |
Token ID | 326 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
shampoo | +0.022 |
fault | +0.021 |
vinegar | +0.021 |
common | +0.021 |
L | +0.021 |
Neg logit contributions | |
pole | -0.019 |
emaker | -0.018 |
warrior | -0.018 |
ickets | -0.017 |
ados | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
aj | +0.031 |
shampoo | +0.031 |
fault | +0.030 |
bruises | +0.030 |
vinegar | +0.029 |
Neg logit contributions | |
pole | -0.051 |
warrior | -0.049 |
emaker | -0.048 |
stone | -0.047 |
ickets | -0.046 |
Token | all |
Token ID | 477 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
shampoo | +0.010 |
fault | +0.010 |
vinegar | +0.010 |
common | +0.010 |
L | +0.010 |
Neg logit contributions | |
pole | -0.015 |
emaker | -0.015 |
warrior | -0.015 |
ickets | -0.014 |
ados | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
shampoo | +0.043 |
fault | +0.042 |
vinegar | +0.040 |
L | +0.040 |
common | +0.040 |
Neg logit contributions | |
pole | -0.051 |
emaker | -0.049 |
warrior | -0.049 |
ickets | -0.048 |
ados | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
shampoo | +0.006 |
fault | +0.006 |
vinegar | +0.006 |
common | +0.006 |
L | +0.006 |
Neg logit contributions | |
pole | -0.004 |
emaker | -0.004 |
warrior | -0.004 |
ickets | -0.004 |
ados | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
pole | +0.013 |
warrior | +0.012 |
King | +0.011 |
lf | +0.011 |
emaker | +0.011 |
Neg logit contributions | |
fault | -0.013 |
vinegar | -0.013 |
common | -0.012 |
shampoo | -0.012 |
bruises | -0.012 |
Token | wearing |
Token ID | 5762 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
fault | +0.013 |
vinegar | +0.013 |
shampoo | +0.013 |
common | +0.013 |
bruises | +0.013 |
Neg logit contributions | |
pole | -0.011 |
warrior | -0.010 |
emaker | -0.010 |
King | -0.009 |
ickets | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
fault | +0.004 |
vinegar | +0.003 |
ours | +0.003 |
bruises | +0.003 |
shampoo | +0.003 |
Neg logit contributions | |
warrior | -0.003 |
pole | -0.003 |
King | -0.003 |
ados | -0.003 |
Charlie | -0.003 |
Token | brand |
Token ID | 4508 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
fault | +0.050 |
vinegar | +0.050 |
shampoo | +0.047 |
ours | +0.045 |
bruises | +0.045 |
Neg logit contributions | |
pole | -0.055 |
warrior | -0.054 |
King | -0.052 |
ados | -0.051 |
ickets | -0.050 |
Token | new |
Token ID | 649 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
fault | +0.164 |
bruises | +0.157 |
vinegar | +0.157 |
shampoo | +0.154 |
common | +0.149 |
Neg logit contributions | |
pole | -0.220 |
ados | -0.205 |
emaker | -0.205 |
umbo | -0.205 |
ickets | -0.205 |
Token | icy |
Token ID | 30284 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
fault | +0.109 |
shampoo | +0.109 |
vinegar | +0.108 |
bruises | +0.103 |
common | +0.103 |
Neg logit contributions | |
pole | -0.127 |
warrior | -0.122 |
emaker | -0.119 |
ickets | -0.116 |
ados | -0.116 |
Token | blue |
Token ID | 4171 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
shampoo | +0.103 |
fault | +0.102 |
vinegar | +0.099 |
common | +0.097 |
L | +0.096 |
Neg logit contributions | |
pole | -0.136 |
warrior | -0.131 |
emaker | -0.131 |
ickets | -0.128 |
ados | -0.126 |
Token | jacket |
Token ID | 15224 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
fault | +0.062 |
vinegar | +0.061 |
common | +0.059 |
bruises | +0.058 |
shampoo | +0.057 |
Neg logit contributions | |
pole | -0.066 |
warrior | -0.063 |
ickets | -0.063 |
emaker | -0.062 |
ados | -0.062 |
Token | as |
Token ID | 355 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
shampoo | +0.029 |
fault | +0.029 |
vinegar | +0.028 |
common | +0.027 |
L | +0.027 |
Neg logit contributions | |
pole | -0.029 |
emaker | -0.028 |
warrior | -0.028 |
ickets | -0.027 |
ados | -0.027 |
Token | hours |
Token ID | 2250 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
shampoo | +0.026 |
common | +0.025 |
fault | +0.024 |
bruises | +0.024 |
vinegar | +0.024 |
Neg logit contributions | |
pole | -0.025 |
emaker | -0.024 |
ickets | -0.024 |
warrior | -0.023 |
ados | -0.023 |
Token | helping |
Token ID | 5742 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
shampoo | +0.034 |
fault | +0.034 |
vinegar | +0.033 |
common | +0.033 |
L | +0.032 |
Neg logit contributions | |
pole | -0.030 |
emaker | -0.028 |
warrior | -0.028 |
ickets | -0.027 |
ados | -0.027 |
Token | people |
Token ID | 661 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
shampoo | +0.022 |
common | +0.021 |
L | +0.021 |
fault | +0.021 |
vinegar | +0.020 |
Neg logit contributions | |
pole | -0.018 |
emaker | -0.018 |
warrior | -0.018 |
ickets | -0.017 |
umbo | -0.017 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
shampoo | +0.033 |
fault | +0.031 |
common | +0.031 |
L | +0.030 |
vinegar | +0.030 |
Neg logit contributions | |
emaker | -0.036 |
pole | -0.036 |
warrior | -0.036 |
ados | -0.035 |
ickets | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
vinegar | +0.024 |
fault | +0.024 |
shampoo | +0.023 |
ses | +0.023 |
bruises | +0.023 |
Neg logit contributions | |
pole | -0.018 |
ados | -0.017 |
emaker | -0.017 |
warrior | -0.017 |
King | -0.016 |
Token | history |
Token ID | 2106 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
shampoo | +0.103 |
vinegar | +0.101 |
L | +0.098 |
fault | +0.096 |
bruises | +0.095 |
Neg logit contributions | |
warrior | -0.099 |
pole | -0.097 |
ados | -0.095 |
emaker | -0.093 |
trolls | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
shampoo | +0.170 |
fault | +0.168 |
common | +0.162 |
vinegar | +0.160 |
L | +0.158 |
Neg logit contributions | |
pole | -0.214 |
emaker | -0.208 |
warrior | -0.205 |
ickets | -0.201 |
ados | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
shampoo | +0.003 |
vinegar | +0.003 |
bruises | +0.003 |
fault | +0.003 |
common | +0.003 |
Neg logit contributions | |
pole | -0.003 |
ickets | -0.003 |
emaker | -0.003 |
umbo | -0.003 |
warrior | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
shampoo | +0.006 |
vinegar | +0.006 |
fault | +0.006 |
bruises | +0.006 |
common | +0.006 |
Neg logit contributions | |
pole | -0.006 |
ickets | -0.006 |
emaker | -0.006 |
warrior | -0.006 |
umbo | -0.006 |
Token | One |
Token ID | 3198 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
shampoo | +0.001 |
fault | +0.001 |
vinegar | +0.001 |
bruises | +0.001 |
common | +0.001 |
Neg logit contributions | |
pole | -0.002 |
warrior | -0.002 |
emaker | -0.002 |
ickets | -0.002 |
umbo | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
shampoo | +0.087 |
common | +0.083 |
fault | +0.083 |
L | +0.083 |
vinegar | +0.082 |
Neg logit contributions | |
pole | -0.064 |
emaker | -0.061 |
warrior | -0.059 |
ados | -0.059 |
ickets | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
fault | +0.023 |
aj | +0.022 |
ses | +0.022 |
bruises | +0.022 |
vinegar | +0.022 |
Neg logit contributions | |
pole | -0.017 |
ados | -0.017 |
warrior | -0.017 |
down | -0.016 |
King | -0.016 |
Token | tree |
Token ID | 5509 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.013 |
emaker | +0.013 |
ados | +0.012 |
stone | +0.012 |
Neg logit contributions | |
shampoo | -0.038 |
fault | -0.038 |
common | -0.037 |
vinegar | -0.037 |
L | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
pole | +0.028 |
emaker | +0.028 |
warrior | +0.028 |
ickets | +0.027 |
ados | +0.026 |
Neg logit contributions | |
shampoo | -0.033 |
fault | -0.032 |
vinegar | -0.031 |
L | -0.031 |
common | -0.031 |
Token | its |
Token ID | 663 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
fault | +0.025 |
shampoo | +0.025 |
aj | +0.025 |
ours | +0.024 |
vinegar | +0.024 |
Neg logit contributions | |
pole | -0.020 |
warrior | -0.020 |
emaker | -0.019 |
King | -0.019 |
Charlie | -0.018 |
Token | once |
Token ID | 1752 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
shampoo | +0.044 |
vinegar | +0.044 |
fault | +0.042 |
L | +0.042 |
common | +0.042 |
Neg logit contributions | |
pole | -0.031 |
warrior | -0.029 |
stone | -0.027 |
ados | -0.027 |
emaker | -0.027 |
Token | former |
Token ID | 1966 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
fault | +0.058 |
shampoo | +0.058 |
vinegar | +0.057 |
common | +0.056 |
ours | +0.055 |
Neg logit contributions | |
pole | -0.046 |
emaker | -0.041 |
est | -0.041 |
warrior | -0.041 |
stone | -0.040 |
Token | beauty |
Token ID | 8737 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
shampoo | +0.182 |
fault | +0.173 |
vinegar | +0.172 |
L | +0.172 |
bruises | +0.166 |
Neg logit contributions | |
pole | -0.202 |
warrior | -0.193 |
ados | -0.189 |
emaker | -0.189 |
ickets | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
shampoo | +0.058 |
fault | +0.057 |
vinegar | +0.055 |
common | +0.054 |
L | +0.054 |
Neg logit contributions | |
pole | -0.058 |
warrior | -0.055 |
emaker | -0.055 |
ickets | -0.053 |
ados | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
shampoo | +0.004 |
vinegar | +0.003 |
bruises | +0.003 |
common | +0.003 |
ruined | +0.003 |
Neg logit contributions | |
pole | -0.002 |
warrior | -0.002 |
ickets | -0.002 |
umbo | -0.002 |
person | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
fault | +0.006 |
shampoo | +0.005 |
vinegar | +0.005 |
common | +0.005 |
L | +0.005 |
Neg logit contributions | |
pole | -0.008 |
warrior | -0.007 |
stone | -0.007 |
emaker | -0.007 |
eagle | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
shampoo | +0.042 |
vinegar | +0.042 |
fault | +0.042 |
common | +0.041 |
bruises | +0.040 |
Neg logit contributions | |
pole | -0.034 |
warrior | -0.030 |
emaker | -0.030 |
King | -0.029 |
stone | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
fault | +0.014 |
common | +0.014 |
vinegar | +0.013 |
shampoo | +0.013 |
Qu | +0.013 |
Neg logit contributions | |
pole | -0.014 |
emaker | -0.013 |
stone | -0.013 |
on | -0.012 |
owl | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
pole | +0.003 |
stone | +0.003 |
emaker | +0.003 |
owl | +0.003 |
ard | +0.003 |
Neg logit contributions | |
common | -0.003 |
vinegar | -0.003 |
shampoo | -0.003 |
fault | -0.003 |
Qu | -0.003 |
Token | told |
Token ID | 1297 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
common | +0.044 |
vinegar | +0.043 |
Qu | +0.043 |
shampoo | +0.042 |
fault | +0.042 |
Neg logit contributions | |
pole | -0.041 |
stone | -0.040 |
on | -0.039 |
emaker | -0.037 |
oon | -0.037 |
Token | him |
Token ID | 683 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
pole | +0.023 |
emaker | +0.022 |
warrior | +0.021 |
ickets | +0.021 |
ados | +0.021 |
Neg logit contributions | |
shampoo | -0.032 |
fault | -0.032 |
vinegar | -0.031 |
common | -0.031 |
bruises | -0.030 |
Token | long |
Token ID | 890 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
shampoo | +0.045 |
vinegar | +0.044 |
common | +0.043 |
aj | +0.042 |
bruises | +0.042 |
Neg logit contributions | |
pole | -0.036 |
stone | -0.034 |
warrior | -0.034 |
emaker | -0.034 |
ados | -0.033 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Qu | +0.059 |
vinegar | +0.056 |
common | +0.055 |
ours | +0.055 |
Aw | +0.054 |
Neg logit contributions | |
est | -0.051 |
warrior | -0.049 |
emaker | -0.047 |
ados | -0.047 |
owl | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-04 |
Pos logit contributions | |
shampoo | +0.214 |
vinegar | +0.212 |
common | +0.210 |
Qu | +0.206 |
fault | +0.205 |
Neg logit contributions | |
pole | -0.160 |
ados | -0.144 |
emaker | -0.143 |
lf | -0.141 |
person | -0.139 |
Token | The |
Token ID | 383 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
pole | +0.000 |
warrior | +0.000 |
ickets | +0.000 |
ados | +0.000 |
Charlie | +0.000 |
Neg logit contributions | |
fault | -0.001 |
shampoo | -0.001 |
common | -0.001 |
vinegar | -0.001 |
bruises | -0.001 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
fault | +0.042 |
common | +0.041 |
ours | +0.041 |
shampoo | +0.040 |
vinegar | +0.039 |
Neg logit contributions | |
warrior | -0.029 |
King | -0.027 |
eagle | -0.026 |
owl | -0.026 |
pole | -0.025 |
Token | spread |
Token ID | 4104 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
fault | +0.019 |
shampoo | +0.018 |
common | +0.017 |
vinegar | +0.017 |
L | +0.016 |
Neg logit contributions | |
pole | -0.028 |
emaker | -0.026 |
warrior | -0.026 |
stone | -0.025 |
ickets | -0.025 |
Token | out |
Token ID | 503 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
pole | +0.024 |
emaker | +0.023 |
warrior | +0.023 |
ickets | +0.022 |
ados | +0.022 |
Neg logit contributions | |
fault | -0.029 |
shampoo | -0.029 |
common | -0.028 |
vinegar | -0.028 |
bruises | -0.027 |
Token | brother |
Token ID | 3956 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
vinegar | +0.015 |
fault | +0.015 |
common | +0.015 |
ours | +0.014 |
bruises | +0.014 |
Neg logit contributions | |
warrior | -0.011 |
emaker | -0.011 |
owl | -0.010 |
King | -0.010 |
knight | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
vinegar | +0.062 |
fault | +0.062 |
common | +0.062 |
shampoo | +0.059 |
bruises | +0.058 |
Neg logit contributions | |
pole | -0.080 |
emaker | -0.079 |
warrior | -0.077 |
ickets | -0.075 |
umbo | -0.074 |
Token | wear |
Token ID | 5806 |
Feature activation | -9.15e-03 |
Pos logit contributions | |
vinegar | +0.019 |
fault | +0.019 |
bruises | +0.019 |
aj | +0.018 |
shampoo | +0.018 |
Neg logit contributions | |
pole | -0.014 |
warrior | -0.013 |
ickets | -0.012 |
amber | -0.012 |
emaker | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
around | +0.015 |
down | +0.013 |
through | +0.013 |
outdoors | +0.013 |
outside | +0.013 |
Neg logit contributions | |
fault | -0.014 |
ses | -0.013 |
vinegar | -0.013 |
arose | -0.013 |
bruises | -0.013 |
Token | bath |
Token ID | 7837 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
fault | +0.053 |
arose | +0.051 |
ours | +0.049 |
vinegar | +0.049 |
rou | +0.048 |
Neg logit contributions | |
around | -0.033 |
est | -0.032 |
outdoors | -0.030 |
King | -0.028 |
down | -0.028 |
Token | ro |
Token ID | 305 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
fault | +0.156 |
vinegar | +0.152 |
bruises | +0.151 |
common | +0.148 |
shampoo | +0.145 |
Neg logit contributions | |
pole | -0.084 |
ickets | -0.080 |
oon | -0.077 |
est | -0.076 |
ados | -0.076 |
Token | bes |
Token ID | 12636 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
fault | +0.204 |
vinegar | +0.203 |
shampoo | +0.198 |
L | +0.195 |
bruises | +0.194 |
Neg logit contributions | |
pole | -0.169 |
emaker | -0.159 |
warrior | -0.158 |
oon | -0.156 |
lf | -0.155 |
Token | together |
Token ID | 1978 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
shampoo | +0.030 |
fault | +0.029 |
common | +0.028 |
L | +0.028 |
vinegar | +0.028 |
Neg logit contributions | |
pole | -0.029 |
emaker | -0.028 |
warrior | -0.028 |
ickets | -0.027 |
ados | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
vinegar | +0.004 |
fault | +0.004 |
bruises | +0.004 |
shampoo | +0.004 |
common | +0.004 |
Neg logit contributions | |
pole | -0.002 |
warrior | -0.002 |
emaker | -0.002 |
stone | -0.002 |
ickets | -0.002 |
Token | play |
Token ID | 711 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
fault | +0.014 |
ours | +0.014 |
vinegar | +0.014 |
bruises | +0.014 |
aj | +0.013 |
Neg logit contributions | |
forth | -0.011 |
around | -0.011 |
pole | -0.011 |
King | -0.011 |
Charlie | -0.011 |
Token | games |
Token ID | 1830 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
fault | +0.054 |
vinegar | +0.050 |
bruises | +0.050 |
common | +0.048 |
shampoo | +0.047 |
Neg logit contributions | |
pole | -0.030 |
warrior | -0.030 |
around | -0.029 |
oon | -0.028 |
emaker | -0.027 |
Token | feeling |
Token ID | 4203 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
pole | +0.012 |
warrior | +0.012 |
King | +0.011 |
stone | +0.011 |
emaker | +0.011 |
Neg logit contributions | |
fault | -0.018 |
vinegar | -0.017 |
shampoo | -0.017 |
bruises | -0.016 |
aj | -0.016 |
Token | good |
Token ID | 922 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
warrior | +0.008 |
King | +0.008 |
around | +0.008 |
pole | +0.008 |
forward | +0.008 |
Neg logit contributions | |
fault | -0.012 |
aj | -0.012 |
ses | -0.011 |
vinegar | -0.011 |
omo | -0.011 |
Token | because |
Token ID | 780 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
vinegar | +0.031 |
shampoo | +0.030 |
common | +0.030 |
bruises | +0.029 |
fault | +0.029 |
Neg logit contributions | |
warrior | -0.020 |
pole | -0.020 |
emaker | -0.020 |
stone | -0.019 |
ados | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
fault | +0.010 |
shampoo | +0.010 |
vinegar | +0.009 |
common | +0.009 |
aj | +0.009 |
Neg logit contributions | |
pole | -0.006 |
warrior | -0.005 |
emaker | -0.005 |
ickets | -0.005 |
ados | -0.005 |
Token | special |
Token ID | 2041 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
shampoo | +0.087 |
vinegar | +0.087 |
fault | +0.086 |
L | +0.085 |
bruises | +0.084 |
Neg logit contributions | |
warrior | -0.061 |
pole | -0.060 |
ados | -0.058 |
King | -0.057 |
emaker | -0.057 |
Token | doctor |
Token ID | 6253 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bruises | +0.109 |
vinegar | +0.109 |
L | +0.107 |
Qu | +0.106 |
fault | +0.106 |
Neg logit contributions | |
pole | -0.080 |
est | -0.079 |
warrior | -0.078 |
King | -0.077 |
person | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
vinegar | +0.154 |
shampoo | +0.151 |
bruises | +0.147 |
fault | +0.145 |
common | +0.144 |
Neg logit contributions | |
pole | -0.220 |
stone | -0.206 |
warrior | -0.206 |
emaker | -0.206 |
King | -0.201 |
Token | coming |
Token ID | 2406 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
fault | +0.041 |
vinegar | +0.041 |
ses | +0.040 |
shampoo | +0.040 |
bruises | +0.040 |
Neg logit contributions | |
pole | -0.035 |
King | -0.031 |
warrior | -0.031 |
emaker | -0.030 |
stone | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +5.19e-04 |
Pos logit contributions | |
fault | +0.003 |
shampoo | +0.003 |
vinegar | +0.003 |
bruises | +0.003 |
common | +0.003 |
Neg logit contributions | |
pole | -0.002 |
emaker | -0.002 |
warrior | -0.002 |
ados | -0.002 |
stone | -0.002 |
Token | visit |
Token ID | 3187 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
fault | +0.001 |
ours | +0.001 |
aj | +0.001 |
outed | +0.001 |
vinegar | +0.001 |
Neg logit contributions | |
pole | -0.001 |
King | -0.001 |
warrior | -0.001 |
Charlie | -0.001 |
owl | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-03 |
Pos logit contributions | |
shampoo | +0.007 |
fault | +0.007 |
vinegar | +0.007 |
bruises | +0.007 |
common | +0.007 |
Neg logit contributions | |
pole | -0.006 |
warrior | -0.006 |
emaker | -0.006 |
ados | -0.005 |
stone | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ours | +0.082 |
shampoo | +0.082 |
vinegar | +0.081 |
aj | +0.081 |
common | +0.080 |
Neg logit contributions | |
pole | -0.050 |
ados | -0.050 |
warrior | -0.049 |
emaker | -0.049 |
King | -0.045 |
Token | friend |
Token ID | 1545 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
shampoo | +0.034 |
L | +0.034 |
Qu | +0.034 |
ours | +0.033 |
vinegar | +0.032 |
Neg logit contributions | |
warrior | -0.025 |
pole | -0.024 |
King | -0.023 |
owl | -0.022 |
eagle | -0.022 |
Token | because |
Token ID | 780 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
vinegar | +0.063 |
shampoo | +0.062 |
common | +0.061 |
fault | +0.059 |
ours | +0.059 |
Neg logit contributions | |
pole | -0.039 |
emaker | -0.037 |
warrior | -0.036 |
stone | -0.034 |
ados | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
shampoo | +0.032 |
fault | +0.032 |
vinegar | +0.031 |
common | +0.031 |
aj | +0.031 |
Neg logit contributions | |
pole | -0.018 |
emaker | -0.018 |
warrior | -0.018 |
ados | -0.016 |
ickets | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
aj | +0.052 |
ours | +0.050 |
shampoo | +0.049 |
fault | +0.048 |
vinegar | +0.048 |
Neg logit contributions | |
ados | -0.028 |
Charlie | -0.027 |
Mickey | -0.026 |
pole | -0.026 |
emaker | -0.026 |
Token | selfish |
Token ID | 20363 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
shampoo | +0.080 |
L | +0.080 |
Qu | +0.078 |
vinegar | +0.076 |
ours | +0.076 |
Neg logit contributions | |
warrior | -0.062 |
pole | -0.058 |
King | -0.057 |
owl | -0.057 |
eagle | -0.057 |
Token | ness |
Token ID | 1108 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
shampoo | +0.191 |
vinegar | +0.183 |
common | +0.183 |
fault | +0.182 |
L | +0.182 |
Neg logit contributions | |
pole | -0.179 |
warrior | -0.175 |
emaker | -0.172 |
ados | -0.167 |
ickets | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
vinegar | +0.068 |
shampoo | +0.068 |
common | +0.068 |
ours | +0.067 |
L | +0.066 |
Neg logit contributions | |
pole | -0.064 |
emaker | -0.062 |
ickets | -0.059 |
stone | -0.059 |
warrior | -0.058 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
shampoo | +0.008 |
fault | +0.007 |
vinegar | +0.007 |
common | +0.007 |
bruises | +0.007 |
Neg logit contributions | |
pole | -0.010 |
emaker | -0.010 |
warrior | -0.009 |
ickets | -0.009 |
ados | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
fault | +0.012 |
shampoo | +0.012 |
vinegar | +0.012 |
bruises | +0.012 |
ours | +0.011 |
Neg logit contributions | |
pole | -0.011 |
ickets | -0.011 |
emaker | -0.010 |
oon | -0.010 |
warrior | -0.010 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
shampoo | +0.046 |
fault | +0.044 |
vinegar | +0.043 |
common | +0.042 |
bruises | +0.041 |
Neg logit contributions | |
pole | -0.078 |
emaker | -0.076 |
warrior | -0.074 |
ickets | -0.073 |
ados | -0.072 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
pole | +0.029 |
emaker | +0.028 |
warrior | +0.028 |
ickets | +0.027 |
ados | +0.027 |
Neg logit contributions | |
shampoo | -0.016 |
fault | -0.015 |
vinegar | -0.015 |
L | -0.014 |
common | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ses | +0.047 |
vinegar | +0.046 |
ours | +0.045 |
fault | +0.045 |
etchup | +0.044 |
Neg logit contributions | |
ados | -0.027 |
owl | -0.026 |
Charlie | -0.025 |
stone | -0.025 |
Mickey | -0.025 |
Token | even |
Token ID | 772 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
shampoo | +0.038 |
fault | +0.037 |
vinegar | +0.036 |
common | +0.036 |
L | +0.035 |
Neg logit contributions | |
pole | -0.047 |
emaker | -0.046 |
warrior | -0.046 |
ickets | -0.044 |
ados | -0.044 |
Token | though |
Token ID | 996 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
fault | +0.024 |
aj | +0.023 |
ses | +0.022 |
vinegar | +0.022 |
shampoo | +0.022 |
Neg logit contributions | |
warrior | -0.017 |
emaker | -0.016 |
pole | -0.016 |
stone | -0.015 |
ados | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
aj | +0.031 |
fault | +0.030 |
vinegar | +0.030 |
ses | +0.030 |
outed | +0.030 |
Neg logit contributions | |
ados | -0.016 |
warrior | -0.015 |
Charlie | -0.015 |
lf | -0.015 |
emaker | -0.015 |
Token | license |
Token ID | 5964 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
L | +0.095 |
vinegar | +0.094 |
arose | +0.091 |
Qu | +0.090 |
ours | +0.088 |
Neg logit contributions | |
warrior | -0.069 |
eagle | -0.063 |
emaker | -0.057 |
owl | -0.057 |
image | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
common | +0.133 |
vinegar | +0.132 |
L | +0.131 |
shampoo | +0.131 |
aj | +0.125 |
Neg logit contributions | |
pole | -0.222 |
emaker | -0.220 |
warrior | -0.216 |
stone | -0.212 |
est | -0.208 |
Token | special |
Token ID | 2041 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
ours | +0.050 |
L | +0.049 |
aj | +0.049 |
ses | +0.049 |
unison | +0.049 |
Neg logit contributions | |
pole | -0.043 |
stone | -0.039 |
owl | -0.039 |
down | -0.038 |
around | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
warrior | +0.005 |
pole | +0.005 |
ados | +0.005 |
emaker | +0.005 |
stone | +0.005 |
Neg logit contributions | |
common | -0.012 |
vinegar | -0.012 |
shampoo | -0.012 |
L | -0.011 |
aj | -0.011 |
Token | valuable |
Token ID | 8119 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
stone | +0.036 |
pole | +0.034 |
warrior | +0.034 |
ados | +0.033 |
emaker | +0.033 |
Neg logit contributions | |
aj | -0.048 |
shampoo | -0.047 |
fault | -0.046 |
common | -0.045 |
L | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
aj | +0.033 |
vinegar | +0.032 |
common | +0.032 |
ours | +0.031 |
bruises | +0.031 |
Neg logit contributions | |
stone | -0.022 |
emaker | -0.022 |
warrior | -0.021 |
ados | -0.021 |
est | -0.021 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
aj | +0.002 |
ours | +0.002 |
outed | +0.002 |
fault | +0.002 |
omo | +0.002 |
Neg logit contributions | |
King | -0.001 |
owl | -0.001 |
mushroom | -0.001 |
trolls | -0.001 |
pole | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
fault | +0.004 |
shampoo | +0.004 |
vinegar | +0.004 |
bruises | +0.004 |
common | +0.004 |
Neg logit contributions | |
pole | -0.003 |
warrior | -0.003 |
stone | -0.003 |
emaker | -0.003 |
ados | -0.003 |
Token | people |
Token ID | 661 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
trolls | +0.004 |
King | +0.004 |
owl | +0.004 |
dragons | +0.004 |
warrior | +0.003 |
Neg logit contributions | |
aj | -0.008 |
fault | -0.008 |
ours | -0.008 |
ucker | -0.008 |
etchup | -0.008 |
Token | from |
Token ID | 422 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
fault | +0.035 |
vinegar | +0.034 |
shampoo | +0.034 |
bruises | +0.034 |
common | +0.033 |
Neg logit contributions | |
pole | -0.029 |
emaker | -0.027 |
stone | -0.026 |
warrior | -0.026 |
King | -0.025 |
Token | long |
Token ID | 890 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
aj | +0.022 |
omo | +0.021 |
fault | +0.021 |
ucker | +0.020 |
bruises | +0.020 |
Neg logit contributions | |
King | -0.013 |
around | -0.012 |
warrior | -0.012 |
angel | -0.012 |
kingdom | -0.012 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
vinegar | +0.055 |
shampoo | +0.055 |
fault | +0.051 |
Qu | +0.051 |
common | +0.051 |
Neg logit contributions | |
ados | -0.059 |
pole | -0.058 |
warrior | -0.058 |
emaker | -0.057 |
trolls | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
shampoo | +0.218 |
vinegar | +0.216 |
common | +0.212 |
Qu | +0.209 |
fault | +0.207 |
Neg logit contributions | |
pole | -0.144 |
ados | -0.134 |
lf | -0.132 |
emaker | -0.123 |
on | -0.123 |
Token | Sam |
Token ID | 3409 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
shampoo | +0.020 |
fault | +0.020 |
common | +0.019 |
vinegar | +0.019 |
bruises | +0.019 |
Neg logit contributions | |
pole | -0.021 |
warrior | -0.020 |
ickets | -0.020 |
emaker | -0.020 |
ados | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
pole | +0.021 |
warrior | +0.021 |
emaker | +0.020 |
stone | +0.020 |
King | +0.019 |
Neg logit contributions | |
fault | -0.015 |
vinegar | -0.015 |
shampoo | -0.014 |
common | -0.014 |
bruises | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
vinegar | +0.019 |
shampoo | +0.019 |
common | +0.018 |
fault | +0.018 |
bruises | +0.018 |
Neg logit contributions | |
warrior | -0.019 |
King | -0.018 |
pole | -0.017 |
emaker | -0.017 |
trolls | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
fault | +0.033 |
common | +0.032 |
vinegar | +0.031 |
shampoo | +0.031 |
bruises | +0.030 |
Neg logit contributions | |
pole | -0.038 |
emaker | -0.035 |
warrior | -0.034 |
stone | -0.033 |
King | -0.033 |
Token | made |
Token ID | 925 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
pole | +0.063 |
warrior | +0.061 |
King | +0.059 |
around | +0.056 |
Charlie | +0.056 |
Neg logit contributions | |
fault | -0.064 |
vinegar | -0.060 |
common | -0.059 |
shampoo | -0.059 |
bruises | -0.058 |
Token | him |
Token ID | 683 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
pole | +0.054 |
emaker | +0.052 |
around | +0.052 |
ickets | +0.052 |
ados | +0.051 |
Neg logit contributions | |
common | -0.067 |
aj | -0.063 |
vinegar | -0.063 |
fault | -0.062 |
bruises | -0.061 |
Token | an |
Token ID | 281 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
pole | +0.045 |
ickets | +0.041 |
warrior | +0.040 |
down | +0.040 |
emaker | +0.040 |
Neg logit contributions | |
vinegar | -0.061 |
common | -0.059 |
shampoo | -0.059 |
fault | -0.058 |
ours | -0.057 |
Token | even |
Token ID | 772 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
emaker | +0.075 |
pole | +0.074 |
ickets | +0.072 |
warrior | +0.072 |
ados | +0.070 |
Neg logit contributions | |
shampoo | -0.063 |
fault | -0.062 |
vinegar | -0.060 |
L | -0.057 |
bruises | -0.057 |
Token | y |
Token ID | 331 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
pole | +0.054 |
down | +0.049 |
warrior | +0.049 |
around | +0.048 |
est | +0.047 |
Neg logit contributions | |
fault | -0.075 |
common | -0.065 |
ses | -0.065 |
Qu | -0.065 |
aj | -0.063 |
Token | umm |
Token ID | 13929 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
pole | +0.080 |
warrior | +0.072 |
emaker | +0.071 |
stone | +0.065 |
King | +0.065 |
Neg logit contributions | |
shampoo | -0.140 |
fault | -0.139 |
vinegar | -0.136 |
L | -0.130 |
common | -0.130 |
Token | ier |
Token ID | 959 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
pole | +0.106 |
emaker | +0.101 |
warrior | +0.093 |
ickets | +0.088 |
ados | +0.088 |
Neg logit contributions | |
shampoo | -0.307 |
fault | -0.300 |
common | -0.299 |
vinegar | -0.296 |
L | -0.294 |
Token | snack |
Token ID | 26906 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
pole | +0.032 |
emaker | +0.031 |
warrior | +0.031 |
ickets | +0.029 |
ados | +0.029 |
Neg logit contributions | |
shampoo | -0.037 |
fault | -0.036 |
vinegar | -0.035 |
common | -0.035 |
L | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
shampoo | +0.028 |
fault | +0.027 |
common | +0.026 |
vinegar | +0.026 |
bruises | +0.026 |
Neg logit contributions | |
pole | -0.027 |
emaker | -0.026 |
warrior | -0.025 |
ickets | -0.025 |
ados | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | +7.48e-04 |
Pos logit contributions | |
pole | +0.005 |
stone | +0.004 |
ados | +0.004 |
forth | +0.004 |
lf | +0.004 |
Neg logit contributions | |
fault | -0.006 |
common | -0.005 |
aj | -0.005 |
ses | -0.005 |
ours | -0.005 |
Token | both |
Token ID | 1111 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
fault | +0.001 |
shampoo | +0.001 |
common | +0.001 |
aj | +0.001 |
vinegar | +0.001 |
Neg logit contributions | |
pole | -0.001 |
emaker | -0.001 |
warrior | -0.001 |
ickets | -0.001 |
stone | -0.001 |
Token | idea |
Token ID | 2126 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
warrior | +0.052 |
pole | +0.048 |
est | +0.046 |
lf | +0.046 |
outdoors | +0.045 |
Neg logit contributions | |
Qu | -0.078 |
L | -0.078 |
fault | -0.078 |
bruises | -0.078 |
vinegar | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -9.82e-03 |
Pos logit contributions | |
pole | +0.103 |
emaker | +0.098 |
warrior | +0.097 |
stone | +0.093 |
ickets | +0.093 |
Neg logit contributions | |
shampoo | -0.104 |
fault | -0.102 |
vinegar | -0.100 |
common | -0.099 |
bruises | -0.097 |
Token | He |
Token ID | 679 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
pole | +0.012 |
emaker | +0.012 |
warrior | +0.011 |
ickets | +0.011 |
stone | +0.011 |
Neg logit contributions | |
fault | -0.017 |
shampoo | -0.017 |
L | -0.016 |
vinegar | -0.016 |
common | -0.016 |
Token | brought |
Token ID | 3181 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
pole | +0.020 |
warrior | +0.019 |
stone | +0.018 |
emaker | +0.018 |
eagle | +0.017 |
Neg logit contributions | |
fault | -0.017 |
shampoo | -0.017 |
vinegar | -0.016 |
common | -0.016 |
bruises | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
pole | +0.054 |
emaker | +0.051 |
warrior | +0.051 |
ickets | +0.050 |
ados | +0.050 |
Neg logit contributions | |
shampoo | -0.042 |
fault | -0.042 |
vinegar | -0.040 |
common | -0.040 |
L | -0.039 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
warrior | +0.050 |
pole | +0.049 |
stone | +0.047 |
mushroom | +0.047 |
King | +0.044 |
Neg logit contributions | |
fault | -0.056 |
L | -0.053 |
bruises | -0.053 |
vinegar | -0.051 |
Qu | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
warrior | +0.225 |
emaker | +0.222 |
trolls | +0.209 |
ados | +0.208 |
ickets | +0.208 |
Neg logit contributions | |
shampoo | -0.178 |
L | -0.171 |
vinegar | -0.167 |
fault | -0.163 |
towels | -0.160 |
Token | filled |
Token ID | 5901 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
stone | +0.040 |
pole | +0.039 |
ados | +0.038 |
warrior | +0.038 |
Charlie | +0.038 |
Neg logit contributions | |
fault | -0.047 |
common | -0.041 |
vinegar | -0.037 |
shampoo | -0.037 |
bruises | -0.037 |
Token | it |
Token ID | 340 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
pole | +0.042 |
ados | +0.040 |
emaker | +0.038 |
warrior | +0.038 |
stone | +0.037 |
Neg logit contributions | |
fault | -0.049 |
bruises | -0.044 |
shampoo | -0.044 |
aj | -0.043 |
vinegar | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
emaker | +0.034 |
warrior | +0.033 |
ickets | +0.031 |
pole | +0.031 |
eagle | +0.029 |
Neg logit contributions | |
shampoo | -0.043 |
fault | -0.041 |
vinegar | -0.041 |
L | -0.041 |
common | -0.040 |
Token | things |
Token ID | 1243 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ados | +0.022 |
pole | +0.021 |
down | +0.021 |
King | +0.021 |
mushroom | +0.021 |
Neg logit contributions | |
fault | -0.033 |
aj | -0.032 |
ours | -0.031 |
ses | -0.031 |
common | -0.030 |
Token | Here |
Token ID | 3423 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
pole | +0.022 |
emaker | +0.021 |
warrior | +0.021 |
ickets | +0.020 |
ados | +0.020 |
Neg logit contributions | |
shampoo | -0.024 |
fault | -0.023 |
vinegar | -0.023 |
common | -0.022 |
L | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
pole | +0.006 |
warrior | +0.006 |
emaker | +0.006 |
ados | +0.006 |
stone | +0.006 |
Neg logit contributions | |
fault | -0.008 |
shampoo | -0.008 |
vinegar | -0.008 |
bruises | -0.008 |
common | -0.008 |
Token | take |
Token ID | 1011 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
pole | +0.041 |
warrior | +0.039 |
emaker | +0.038 |
ickets | +0.037 |
stone | +0.036 |
Neg logit contributions | |
fault | -0.051 |
shampoo | -0.050 |
common | -0.048 |
vinegar | -0.048 |
bruises | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
pole | +0.067 |
emaker | +0.064 |
warrior | +0.064 |
ickets | +0.063 |
ados | +0.061 |
Neg logit contributions | |
shampoo | -0.050 |
fault | -0.048 |
L | -0.047 |
vinegar | -0.047 |
common | -0.047 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
pole | +0.029 |
emaker | +0.029 |
warrior | +0.028 |
ickets | +0.028 |
ados | +0.027 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.027 |
vinegar | -0.026 |
common | -0.026 |
L | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
warrior | +0.099 |
forth | +0.095 |
traveller | +0.094 |
eagle | +0.091 |
trolls | +0.090 |
Neg logit contributions | |
shampoo | -0.119 |
vinegar | -0.118 |
L | -0.118 |
fault | -0.116 |
common | -0.112 |
Token | on |
Token ID | 261 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
warrior | +0.134 |
pole | +0.129 |
traveller | +0.124 |
jack | +0.120 |
trolls | +0.118 |
Neg logit contributions | |
shampoo | -0.265 |
L | -0.261 |
vinegar | -0.260 |
common | -0.251 |
lemon | -0.242 |
Token | ." |
Token ID | 526 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
warrior | +0.135 |
Charlie | +0.125 |
emaker | +0.124 |
eagle | +0.124 |
traveller | +0.122 |
Neg logit contributions | |
L | -0.069 |
shampoo | -0.067 |
vinegar | -0.061 |
fault | -0.059 |
Sara | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -4.28e-04 |
Pos logit contributions | |
pole | +0.009 |
emaker | +0.008 |
warrior | +0.008 |
ickets | +0.008 |
ados | +0.008 |
Neg logit contributions | |
shampoo | -0.006 |
fault | -0.006 |
vinegar | -0.006 |
L | -0.006 |
common | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
pole | +0.001 |
emaker | +0.001 |
ickets | +0.001 |
warrior | +0.001 |
ados | +0.001 |
Neg logit contributions | |
fault | -0.001 |
shampoo | -0.001 |
vinegar | -0.001 |
common | -0.001 |
bruises | -0.000 |
Token | They |
Token ID | 2990 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.003 |
ados | +0.003 |
warrior | +0.003 |
est | +0.003 |
Neg logit contributions | |
shampoo | -0.002 |
L | -0.002 |
bruises | -0.002 |
common | -0.002 |
vinegar | -0.001 |
Token | ier |
Token ID | 959 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
emaker | +0.112 |
pole | +0.108 |
ados | +0.102 |
ickets | +0.097 |
warrior | +0.096 |
Neg logit contributions | |
shampoo | -0.244 |
common | -0.240 |
fault | -0.237 |
bruises | -0.235 |
vinegar | -0.233 |
Token | ? |
Token ID | 30 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
pole | +0.035 |
warrior | +0.034 |
emaker | +0.034 |
ados | +0.033 |
stone | +0.033 |
Neg logit contributions | |
shampoo | -0.052 |
bruises | -0.050 |
vinegar | -0.050 |
fault | -0.049 |
common | -0.048 |
Token | You |
Token ID | 921 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
pole | +0.014 |
ados | +0.013 |
warrior | +0.013 |
emaker | +0.013 |
ickets | +0.013 |
Neg logit contributions | |
fault | -0.017 |
shampoo | -0.017 |
common | -0.017 |
vinegar | -0.016 |
bruises | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
shampoo | +0.003 |
fault | +0.003 |
common | +0.002 |
bruises | +0.002 |
vinegar | +0.002 |
Neg logit contributions | |
pole | -0.004 |
warrior | -0.004 |
emaker | -0.003 |
ickets | -0.003 |
stone | -0.003 |
Token | y |
Token ID | 331 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
pole | +0.039 |
emaker | +0.038 |
warrior | +0.038 |
ickets | +0.037 |
ados | +0.036 |
Neg logit contributions | |
shampoo | -0.028 |
vinegar | -0.027 |
fault | -0.027 |
L | -0.026 |
common | -0.026 |
Token | umm |
Token ID | 13929 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
pole | +0.080 |
warrior | +0.074 |
King | +0.067 |
emaker | +0.067 |
eagle | +0.066 |
Neg logit contributions | |
shampoo | -0.108 |
vinegar | -0.107 |
fault | -0.107 |
ours | -0.103 |
aj | -0.103 |
Token | ier |
Token ID | 959 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
pole | +0.154 |
emaker | +0.148 |
warrior | +0.146 |
ickets | +0.140 |
ados | +0.138 |
Neg logit contributions | |
shampoo | -0.237 |
fault | -0.234 |
vinegar | -0.228 |
common | -0.227 |
L | -0.225 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
pole | +0.059 |
warrior | +0.057 |
emaker | +0.057 |
ados | +0.054 |
ickets | +0.054 |
Neg logit contributions | |
shampoo | -0.071 |
fault | -0.069 |
vinegar | -0.068 |
common | -0.067 |
L | -0.066 |
Token | You |
Token ID | 921 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
pole | +0.027 |
emaker | +0.026 |
warrior | +0.026 |
ickets | +0.025 |
ados | +0.025 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.028 |
common | -0.027 |
vinegar | -0.027 |
bruises | -0.026 |
Token | are |
Token ID | 389 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
fault | +0.004 |
shampoo | +0.004 |
common | +0.004 |
vinegar | +0.004 |
L | +0.004 |
Neg logit contributions | |
pole | -0.006 |
warrior | -0.006 |
emaker | -0.006 |
ickets | -0.006 |
stone | -0.006 |
Token | my |
Token ID | 616 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
pole | +0.032 |
emaker | +0.031 |
warrior | +0.031 |
ickets | +0.030 |
ados | +0.029 |
Neg logit contributions | |
shampoo | -0.022 |
vinegar | -0.021 |
fault | -0.020 |
L | -0.020 |
common | -0.020 |
Token | want |
Token ID | 765 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
bruises | +0.019 |
aj | +0.018 |
vinegar | +0.018 |
outed | +0.017 |
belts | +0.017 |
Neg logit contributions | |
warrior | -0.012 |
emaker | -0.011 |
orn | -0.011 |
umb | -0.011 |
string | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
ados | +0.042 |
stone | +0.040 |
pole | +0.039 |
umbo | +0.037 |
King | +0.036 |
Neg logit contributions | |
fault | -0.078 |
common | -0.075 |
ses | -0.075 |
aj | -0.074 |
bruises | -0.074 |
Token | make |
Token ID | 787 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
pole | +0.010 |
warrior | +0.009 |
emaker | +0.009 |
ickets | +0.009 |
ados | +0.009 |
Neg logit contributions | |
fault | -0.010 |
shampoo | -0.010 |
vinegar | -0.010 |
bruises | -0.009 |
L | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
pole | +0.046 |
ados | +0.044 |
ickets | +0.043 |
emaker | +0.043 |
warrior | +0.043 |
Neg logit contributions | |
fault | -0.035 |
common | -0.034 |
shampoo | -0.033 |
vinegar | -0.033 |
bruises | -0.033 |
Token | da |
Token ID | 12379 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
pole | +0.077 |
emaker | +0.075 |
warrior | +0.074 |
ickets | +0.073 |
ados | +0.072 |
Neg logit contributions | |
shampoo | -0.054 |
fault | -0.053 |
vinegar | -0.051 |
L | -0.051 |
common | -0.050 |
Token | isy |
Token ID | 13560 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
warrior | +0.121 |
Charlie | +0.118 |
person | +0.117 |
ados | +0.113 |
traveller | +0.112 |
Neg logit contributions | |
shampoo | -0.142 |
rou | -0.134 |
lemon | -0.133 |
L | -0.131 |
aj | -0.130 |
Token | necklace |
Token ID | 38987 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
warrior | +0.198 |
emaker | +0.197 |
pole | +0.193 |
ickets | +0.186 |
person | +0.184 |
Neg logit contributions | |
shampoo | -0.189 |
L | -0.181 |
fault | -0.176 |
vinegar | -0.175 |
common | -0.170 |
Token | too |
Token ID | 1165 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
emaker | +0.052 |
warrior | +0.052 |
person | +0.049 |
eagle | +0.049 |
ados | +0.049 |
Neg logit contributions | |
L | -0.032 |
shampoo | -0.029 |
fault | -0.028 |
common | -0.028 |
cheaper | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
shampoo | +0.047 |
fault | +0.046 |
common | +0.045 |
vinegar | +0.044 |
L | +0.044 |
Neg logit contributions | |
pole | -0.038 |
emaker | -0.037 |
warrior | -0.036 |
ickets | -0.035 |
ados | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
pole | +0.042 |
warrior | +0.039 |
emaker | +0.038 |
ickets | +0.037 |
umbo | +0.036 |
Neg logit contributions | |
fault | -0.048 |
shampoo | -0.048 |
common | -0.047 |
vinegar | -0.047 |
bruises | -0.047 |
Token | I |
Token ID | 314 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
pole | +0.063 |
warrior | +0.054 |
stone | +0.054 |
King | +0.052 |
mushroom | +0.052 |
Neg logit contributions | |
fault | -0.112 |
bruises | -0.107 |
aj | -0.106 |
common | -0.103 |
scratches | -0.102 |
Token | " |
Token ID | 1 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
pole | +0.013 |
emaker | +0.012 |
warrior | +0.012 |
ickets | +0.012 |
stone | +0.011 |
Neg logit contributions | |
fault | -0.023 |
shampoo | -0.022 |
vinegar | -0.022 |
common | -0.021 |
bruises | -0.021 |
Token | Is |
Token ID | 3792 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
pole | +0.058 |
warrior | +0.055 |
emaker | +0.055 |
ickets | +0.052 |
stone | +0.051 |
Neg logit contributions | |
fault | -0.061 |
aj | -0.053 |
vinegar | -0.052 |
ours | -0.051 |
shampoo | -0.051 |
Token | it |
Token ID | 340 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
bruises | +0.064 |
common | +0.063 |
fault | +0.062 |
ses | +0.061 |
unison | +0.061 |
Neg logit contributions | |
ados | -0.037 |
stone | -0.036 |
pole | -0.035 |
King | -0.033 |
eagle | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
pole | +0.099 |
stone | +0.090 |
ados | +0.090 |
ickets | +0.089 |
King | +0.089 |
Neg logit contributions | |
fault | -0.075 |
bruises | -0.072 |
common | -0.070 |
shampoo | -0.070 |
vinegar | -0.067 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
warrior | +0.042 |
pole | +0.041 |
King | +0.040 |
mushroom | +0.039 |
eagle | +0.037 |
Neg logit contributions | |
fault | -0.047 |
bruises | -0.047 |
ours | -0.047 |
aj | -0.047 |
outed | -0.046 |
Token | ay |
Token ID | 323 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
warrior | +0.091 |
traveller | +0.083 |
trolls | +0.083 |
eagle | +0.080 |
pole | +0.079 |
Neg logit contributions | |
shampoo | -0.143 |
vinegar | -0.139 |
fault | -0.137 |
aj | -0.134 |
L | -0.134 |
Token | on |
Token ID | 261 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
warrior | +0.076 |
pole | +0.075 |
trolls | +0.061 |
emaker | +0.061 |
traveller | +0.059 |
Neg logit contributions | |
shampoo | -0.308 |
vinegar | -0.298 |
L | -0.296 |
fault | -0.290 |
common | -0.287 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
pole | +0.108 |
warrior | +0.106 |
emaker | +0.105 |
ickets | +0.101 |
ados | +0.101 |
Neg logit contributions | |
shampoo | -0.102 |
fault | -0.099 |
vinegar | -0.097 |
L | -0.095 |
common | -0.095 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
King | +0.008 |
warrior | +0.008 |
Charlie | +0.008 |
emaker | +0.007 |
pole | +0.007 |
Neg logit contributions | |
fault | -0.009 |
rou | -0.008 |
bruises | -0.007 |
vinegar | -0.007 |
aj | -0.007 |
Token | asks |
Token ID | 7893 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
pole | +0.032 |
emaker | +0.031 |
warrior | +0.030 |
ickets | +0.030 |
ados | +0.030 |
Neg logit contributions | |
shampoo | -0.017 |
fault | -0.016 |
L | -0.015 |
vinegar | -0.015 |
common | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
pole | +0.034 |
emaker | +0.034 |
warrior | +0.033 |
ados | +0.032 |
ickets | +0.031 |
Neg logit contributions | |
fault | -0.037 |
shampoo | -0.036 |
common | -0.035 |
vinegar | -0.035 |
bruises | -0.034 |
Token | he |
Token ID | 339 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
pole | +0.051 |
emaker | +0.050 |
warrior | +0.049 |
ados | +0.047 |
stone | +0.046 |
Neg logit contributions | |
fault | -0.061 |
shampoo | -0.060 |
vinegar | -0.059 |
aj | -0.058 |
common | -0.058 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
common | +0.003 |
fault | +0.003 |
shampoo | +0.003 |
vinegar | +0.003 |
aj | +0.003 |
Neg logit contributions | |
emaker | -0.004 |
pole | -0.004 |
warrior | -0.004 |
stone | -0.004 |
umbo | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
pole | +0.022 |
warrior | +0.021 |
emaker | +0.020 |
ados | +0.019 |
stone | +0.019 |
Neg logit contributions | |
shampoo | -0.034 |
fault | -0.033 |
vinegar | -0.032 |
L | -0.032 |
common | -0.032 |
Token | make |
Token ID | 787 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
pole | +0.069 |
ados | +0.066 |
emaker | +0.063 |
trolls | +0.063 |
ickets | +0.062 |
Neg logit contributions | |
shampoo | -0.037 |
L | -0.035 |
common | -0.033 |
Qu | -0.031 |
ruined | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ados | +0.036 |
pole | +0.035 |
emaker | +0.035 |
warrior | +0.034 |
umbo | +0.033 |
Neg logit contributions | |
aj | -0.036 |
vinegar | -0.035 |
shampoo | -0.035 |
bruises | -0.034 |
common | -0.034 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
pole | +0.063 |
emaker | +0.062 |
ickets | +0.060 |
warrior | +0.060 |
ados | +0.059 |
Neg logit contributions | |
shampoo | -0.034 |
fault | -0.034 |
common | -0.031 |
vinegar | -0.031 |
L | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
warrior | +0.191 |
pole | +0.188 |
emaker | +0.187 |
ados | +0.184 |
ickets | +0.183 |
Neg logit contributions | |
shampoo | -0.184 |
fault | -0.179 |
vinegar | -0.174 |
L | -0.174 |
common | -0.171 |
Token | He |
Token ID | 679 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
shampoo | +0.004 |
fault | +0.004 |
vinegar | +0.004 |
common | +0.004 |
L | +0.004 |
Neg logit contributions | |
pole | -0.004 |
emaker | -0.004 |
warrior | -0.004 |
ickets | -0.004 |
ados | -0.003 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
pole | +0.006 |
warrior | +0.006 |
emaker | +0.006 |
forth | +0.005 |
stone | +0.005 |
Neg logit contributions | |
fault | -0.006 |
common | -0.006 |
aj | -0.006 |
vinegar | -0.006 |
bruises | -0.005 |
Token | sad |
Token ID | 6507 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
around | +0.005 |
forward | +0.005 |
down | +0.005 |
warrior | +0.005 |
alone | +0.005 |
Neg logit contributions | |
aj | -0.009 |
fault | -0.008 |
ours | -0.008 |
common | -0.008 |
omo | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
shampoo | +0.089 |
common | +0.088 |
vinegar | +0.087 |
fault | +0.085 |
bruises | +0.085 |
Neg logit contributions | |
pole | -0.058 |
warrior | -0.057 |
emaker | -0.057 |
ickets | -0.053 |
ados | -0.053 |
Token | chair |
Token ID | 5118 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
shampoo | +0.005 |
fault | +0.005 |
vinegar | +0.005 |
common | +0.005 |
L | +0.005 |
Neg logit contributions | |
pole | -0.004 |
emaker | -0.004 |
warrior | -0.003 |
ickets | -0.003 |
ados | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
vinegar | +0.051 |
common | +0.051 |
shampoo | +0.050 |
fault | +0.049 |
Qu | +0.048 |
Neg logit contributions | |
pole | -0.024 |
emaker | -0.021 |
warrior | -0.020 |
down | -0.020 |
around | -0.020 |
Token | takes |
Token ID | 2753 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
fault | +0.012 |
shampoo | +0.011 |
vinegar | +0.011 |
common | +0.011 |
bruises | +0.011 |
Neg logit contributions | |
pole | -0.014 |
warrior | -0.014 |
emaker | -0.013 |
stone | -0.013 |
ados | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
emaker | +0.021 |
pole | +0.021 |
warrior | +0.020 |
ados | +0.020 |
King | +0.019 |
Neg logit contributions | |
fault | -0.035 |
vinegar | -0.034 |
shampoo | -0.034 |
common | -0.033 |
aj | -0.033 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
pole | +0.032 |
warrior | +0.031 |
emaker | +0.031 |
ickets | +0.030 |
stone | +0.029 |
Neg logit contributions | |
fault | -0.033 |
shampoo | -0.033 |
vinegar | -0.032 |
common | -0.031 |
bruises | -0.031 |
Token | ay |
Token ID | 323 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
warrior | +0.100 |
forth | +0.095 |
trolls | +0.090 |
ados | +0.090 |
traveller | +0.089 |
Neg logit contributions | |
shampoo | -0.127 |
fault | -0.127 |
aj | -0.122 |
bruises | -0.119 |
L | -0.118 |
Token | on |
Token ID | 261 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
pole | +0.108 |
warrior | +0.106 |
ados | +0.092 |
trolls | +0.090 |
traveller | +0.086 |
Neg logit contributions | |
shampoo | -0.283 |
L | -0.273 |
vinegar | -0.267 |
bruises | -0.266 |
common | -0.262 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
warrior | +0.099 |
pole | +0.096 |
emaker | +0.094 |
ados | +0.092 |
ickets | +0.092 |
Neg logit contributions | |
shampoo | -0.079 |
fault | -0.076 |
L | -0.075 |
vinegar | -0.071 |
bruises | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
stone | +0.044 |
warrior | +0.044 |
on | +0.043 |
Charlie | +0.043 |
down | +0.043 |
Neg logit contributions | |
fault | -0.046 |
common | -0.042 |
omo | -0.040 |
rou | -0.040 |
ucker | -0.039 |
Token | paper |
Token ID | 3348 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
pole | +0.011 |
warrior | +0.011 |
stone | +0.010 |
emaker | +0.010 |
King | +0.010 |
Neg logit contributions | |
fault | -0.013 |
common | -0.012 |
shampoo | -0.012 |
vinegar | -0.012 |
L | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
pole | +0.052 |
emaker | +0.049 |
warrior | +0.049 |
stone | +0.047 |
ados | +0.047 |
Neg logit contributions | |
shampoo | -0.054 |
fault | -0.054 |
common | -0.053 |
vinegar | -0.052 |
bruises | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -9.36e-03 |
Pos logit contributions | |
aj | +0.026 |
fault | +0.026 |
ours | +0.025 |
bruises | +0.024 |
outed | +0.024 |
Neg logit contributions | |
ados | -0.021 |
warrior | -0.020 |
Charlie | -0.020 |
pole | -0.019 |
down | -0.019 |
Token | basketball |
Token ID | 9669 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
warrior | +0.012 |
eagle | +0.011 |
pole | +0.011 |
King | +0.011 |
mushroom | +0.011 |
Neg logit contributions | |
L | -0.015 |
common | -0.015 |
ours | -0.015 |
fault | -0.015 |
Qu | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
shampoo | +0.010 |
fault | +0.010 |
vinegar | +0.010 |
L | +0.010 |
common | +0.009 |
Neg logit contributions | |
pole | -0.011 |
emaker | -0.011 |
warrior | -0.011 |
ickets | -0.011 |
ados | -0.010 |
Token | making |
Token ID | 1642 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
fault | +0.003 |
aj | +0.003 |
common | +0.003 |
shampoo | +0.003 |
ours | +0.003 |
Neg logit contributions | |
warrior | -0.003 |
pole | -0.003 |
King | -0.003 |
forth | -0.003 |
emaker | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
pole | +0.029 |
warrior | +0.028 |
ados | +0.028 |
Charlie | +0.027 |
emaker | +0.027 |
Neg logit contributions | |
aj | -0.032 |
common | -0.031 |
bruises | -0.031 |
shampoo | -0.031 |
fault | -0.031 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
pole | +0.037 |
warrior | +0.037 |
ickets | +0.034 |
emaker | +0.034 |
umbo | +0.034 |
Neg logit contributions | |
fault | -0.031 |
shampoo | -0.030 |
bruises | -0.029 |
vinegar | -0.029 |
common | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
pole | +0.181 |
warrior | +0.179 |
emaker | +0.178 |
ados | +0.170 |
ickets | +0.170 |
Neg logit contributions | |
shampoo | -0.190 |
fault | -0.186 |
vinegar | -0.181 |
L | -0.179 |
common | -0.179 |
Token | Sally |
Token ID | 25737 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
pole | +0.011 |
warrior | +0.011 |
ickets | +0.010 |
emaker | +0.010 |
umbo | +0.010 |
Neg logit contributions | |
shampoo | -0.019 |
fault | -0.018 |
vinegar | -0.018 |
common | -0.018 |
bruises | -0.018 |
Token | cheered |
Token ID | 34767 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
pole | +0.063 |
warrior | +0.061 |
emaker | +0.061 |
ickets | +0.059 |
stone | +0.058 |
Neg logit contributions | |
shampoo | -0.037 |
fault | -0.036 |
vinegar | -0.035 |
common | -0.035 |
bruises | -0.033 |
Token | each |
Token ID | 1123 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
umb | +0.032 |
orn | +0.032 |
emaker | +0.031 |
ickets | +0.031 |
warrior | +0.030 |
Neg logit contributions | |
L | -0.018 |
their | -0.016 |
Sara | -0.014 |
shampoo | -0.014 |
Qu | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
shampoo | +0.024 |
fault | +0.022 |
L | +0.021 |
vinegar | +0.021 |
common | +0.021 |
Neg logit contributions | |
pole | -0.040 |
ados | -0.039 |
emaker | -0.039 |
stone | -0.038 |
warrior | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
pole | +0.094 |
warrior | +0.090 |
emaker | +0.089 |
stone | +0.086 |
ados | +0.086 |
Neg logit contributions | |
shampoo | -0.112 |
vinegar | -0.110 |
fault | -0.109 |
common | -0.107 |
bruises | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
pole | +0.017 |
warrior | +0.016 |
eagle | +0.015 |
emaker | +0.015 |
Charlie | +0.015 |
Neg logit contributions | |
shampoo | -0.025 |
vinegar | -0.025 |
fault | -0.025 |
common | -0.025 |
ours | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
pole | +0.034 |
warrior | +0.033 |
stone | +0.032 |
King | +0.032 |
Charlie | +0.031 |
Neg logit contributions | |
fault | -0.042 |
aj | -0.042 |
shampoo | -0.040 |
vinegar | -0.040 |
ours | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
shampoo | +0.009 |
fault | +0.009 |
vinegar | +0.008 |
common | +0.008 |
L | +0.008 |
Neg logit contributions | |
pole | -0.016 |
emaker | -0.015 |
warrior | -0.015 |
ickets | -0.015 |
ados | -0.015 |
Token | pri |
Token ID | 1293 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
vinegar | +0.032 |
bruises | +0.032 |
shampoo | +0.031 |
fault | +0.031 |
ses | +0.030 |
Neg logit contributions | |
pole | -0.028 |
King | -0.024 |
Charlie | -0.023 |
emaker | -0.023 |
est | -0.023 |
Token | ve |
Token ID | 303 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
pole | +0.034 |
emaker | +0.032 |
warrior | +0.031 |
ickets | +0.030 |
stone | +0.029 |
Neg logit contributions | |
shampoo | -0.064 |
fault | -0.064 |
vinegar | -0.062 |
common | -0.061 |
bruises | -0.061 |
Token | leg |
Token ID | 1455 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
pole | +0.151 |
emaker | +0.142 |
warrior | +0.139 |
stone | +0.134 |
ickets | +0.132 |
Neg logit contributions | |
shampoo | -0.223 |
fault | -0.219 |
vinegar | -0.216 |
common | -0.213 |
L | -0.211 |
Token | ed |
Token ID | 276 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
pole | +0.012 |
emaker | +0.011 |
ickets | +0.011 |
stone | +0.010 |
warrior | +0.010 |
Neg logit contributions | |
fault | -0.028 |
bruises | -0.028 |
shampoo | -0.028 |
vinegar | -0.027 |
common | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
pole | +0.039 |
warrior | +0.036 |
emaker | +0.035 |
ados | +0.034 |
stone | +0.033 |
Neg logit contributions | |
shampoo | -0.072 |
fault | -0.072 |
vinegar | -0.071 |
aj | -0.069 |
common | -0.069 |
Token | be |
Token ID | 307 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
fault | +0.024 |
aj | +0.023 |
shampoo | +0.023 |
bruises | +0.022 |
vinegar | +0.022 |
Neg logit contributions | |
pole | -0.020 |
warrior | -0.020 |
King | -0.019 |
emaker | -0.018 |
Charlie | -0.018 |
Token | part |
Token ID | 636 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
fault | +0.038 |
shampoo | +0.037 |
vinegar | +0.037 |
bruises | +0.035 |
common | +0.035 |
Neg logit contributions | |
pole | -0.035 |
warrior | -0.032 |
emaker | -0.031 |
King | -0.030 |
stone | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
pole | +0.030 |
warrior | +0.029 |
emaker | +0.029 |
ados | +0.028 |
ickets | +0.028 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.028 |
vinegar | -0.027 |
common | -0.026 |
L | -0.026 |
Token | make |
Token ID | 787 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
shampoo | +0.013 |
fault | +0.012 |
common | +0.012 |
vinegar | +0.012 |
L | +0.012 |
Neg logit contributions | |
pole | -0.014 |
emaker | -0.013 |
warrior | -0.013 |
ados | -0.013 |
ickets | -0.013 |
Token | an |
Token ID | 281 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
pole | +0.035 |
warrior | +0.034 |
emaker | +0.034 |
ados | +0.033 |
ickets | +0.033 |
Neg logit contributions | |
fault | -0.018 |
shampoo | -0.018 |
common | -0.018 |
vinegar | -0.017 |
bruises | -0.017 |
Token | ash |
Token ID | 12530 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
emaker | +0.080 |
ickets | +0.075 |
oon | +0.075 |
pole | +0.075 |
warrior | +0.074 |
Neg logit contributions | |
fault | -0.060 |
shampoo | -0.059 |
vinegar | -0.056 |
L | -0.055 |
cheaper | -0.053 |
Token | tr |
Token ID | 2213 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
emaker | +0.010 |
warrior | +0.010 |
pole | +0.010 |
ickets | +0.010 |
ados | +0.010 |
Neg logit contributions | |
shampoo | -0.005 |
fault | -0.005 |
vinegar | -0.005 |
L | -0.005 |
bruises | -0.004 |
Token | ay |
Token ID | 323 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
warrior | +0.011 |
pole | +0.011 |
emaker | +0.010 |
ados | +0.009 |
eagle | +0.009 |
Neg logit contributions | |
fault | -0.031 |
shampoo | -0.031 |
L | -0.030 |
vinegar | -0.030 |
bruises | -0.030 |
Token | out |
Token ID | 503 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
warrior | +0.208 |
pole | +0.203 |
ados | +0.198 |
umbo | +0.194 |
traveller | +0.193 |
Neg logit contributions | |
shampoo | -0.159 |
L | -0.155 |
fault | -0.152 |
gas | -0.141 |
ruined | -0.140 |
Token | of |
Token ID | 286 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
pole | +0.048 |
emaker | +0.047 |
warrior | +0.045 |
ickets | +0.043 |
stone | +0.042 |
Neg logit contributions | |
fault | -0.115 |
shampoo | -0.111 |
vinegar | -0.109 |
common | -0.108 |
aj | -0.105 |
Token | clay |
Token ID | 21558 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
aj | +0.007 |
ours | +0.007 |
ucker | +0.007 |
outed | +0.007 |
fault | +0.007 |
Neg logit contributions | |
Charlie | -0.004 |
on | -0.004 |
King | -0.003 |
ados | -0.003 |
Mickey | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
pole | +0.009 |
emaker | +0.009 |
warrior | +0.009 |
ickets | +0.009 |
ados | +0.008 |
Neg logit contributions | |
shampoo | -0.008 |
fault | -0.008 |
vinegar | -0.008 |
L | -0.008 |
common | -0.007 |
Token | As |
Token ID | 1081 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
L | +0.003 |
shampoo | +0.003 |
vinegar | +0.002 |
fault | +0.002 |
Qu | +0.002 |
Neg logit contributions | |
emaker | -0.002 |
pole | -0.002 |
warrior | -0.002 |
ickets | -0.002 |
quet | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.003 |
warrior | +0.003 |
ickets | +0.003 |
ados | +0.003 |
Neg logit contributions | |
fault | -0.004 |
shampoo | -0.004 |
common | -0.004 |
vinegar | -0.004 |
bruises | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
Charlie | +0.025 |
pole | +0.025 |
King | +0.024 |
stone | +0.024 |
on | +0.024 |
Neg logit contributions | |
fault | -0.033 |
common | -0.029 |
aj | -0.029 |
shampoo | -0.027 |
ses | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
pole | +0.002 |
emaker | +0.002 |
stone | +0.002 |
warrior | +0.002 |
ickets | +0.002 |
Neg logit contributions | |
fault | -0.002 |
common | -0.002 |
aj | -0.002 |
shampoo | -0.002 |
bruises | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
aj | +0.028 |
fault | +0.027 |
bruises | +0.027 |
ses | +0.027 |
ours | +0.027 |
Neg logit contributions | |
pole | -0.024 |
mushroom | -0.021 |
Charlie | -0.021 |
down | -0.020 |
around | -0.020 |
Token | y |
Token ID | 331 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
pole | +0.059 |
warrior | +0.057 |
emaker | +0.053 |
eagle | +0.053 |
King | +0.053 |
Neg logit contributions | |
L | -0.062 |
shampoo | -0.060 |
common | -0.059 |
vinegar | -0.058 |
fault | -0.058 |
Token | umm |
Token ID | 13929 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
pole | +0.057 |
warrior | +0.054 |
emaker | +0.052 |
stone | +0.047 |
King | +0.047 |
Neg logit contributions | |
vinegar | -0.096 |
shampoo | -0.094 |
fault | -0.091 |
common | -0.089 |
mustard | -0.087 |
Token | iest |
Token ID | 6386 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
pole | +0.115 |
warrior | +0.111 |
emaker | +0.103 |
ickets | +0.103 |
ados | +0.099 |
Neg logit contributions | |
shampoo | -0.256 |
fault | -0.252 |
vinegar | -0.251 |
common | -0.243 |
L | -0.242 |
Token | steak |
Token ID | 26320 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
pole | +0.043 |
warrior | +0.042 |
emaker | +0.041 |
ados | +0.040 |
ickets | +0.039 |
Neg logit contributions | |
fault | -0.047 |
shampoo | -0.046 |
L | -0.045 |
common | -0.045 |
bruises | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
pole | +0.023 |
warrior | +0.022 |
emaker | +0.022 |
ickets | +0.022 |
ados | +0.021 |
Neg logit contributions | |
shampoo | -0.022 |
fault | -0.021 |
vinegar | -0.021 |
L | -0.020 |
common | -0.020 |
Token | ever |
Token ID | 1683 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
pole | +0.027 |
warrior | +0.026 |
stone | +0.025 |
emaker | +0.025 |
King | +0.025 |
Neg logit contributions | |
fault | -0.024 |
shampoo | -0.024 |
vinegar | -0.022 |
bruises | -0.022 |
ours | -0.021 |
Token | tasted |
Token ID | 29187 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
fault | +0.031 |
shampoo | +0.031 |
ours | +0.028 |
aj | +0.028 |
bruises | +0.028 |
Neg logit contributions | |
stone | -0.021 |
pole | -0.020 |
emaker | -0.020 |
warrior | -0.020 |
ard | -0.019 |
Token | berries |
Token ID | 36322 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
pole | +0.035 |
ados | +0.034 |
warrior | +0.033 |
stone | +0.032 |
mushroom | +0.031 |
Neg logit contributions | |
fault | -0.044 |
aj | -0.041 |
common | -0.040 |
shampoo | -0.039 |
bruises | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -7.20e-05 |
Pos logit contributions | |
pole | +0.039 |
emaker | +0.037 |
warrior | +0.037 |
ickets | +0.036 |
ados | +0.035 |
Neg logit contributions | |
shampoo | -0.044 |
fault | -0.043 |
vinegar | -0.042 |
common | -0.042 |
bruises | -0.041 |
Token | make |
Token ID | 787 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
pole | +0.000 |
ickets | +0.000 |
warrior | +0.000 |
emaker | +0.000 |
ados | +0.000 |
Neg logit contributions | |
fault | -0.000 |
aj | -0.000 |
bruises | -0.000 |
shampoo | -0.000 |
common | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
pole | +0.049 |
emaker | +0.046 |
warrior | +0.046 |
ados | +0.046 |
ickets | +0.046 |
Neg logit contributions | |
fault | -0.041 |
shampoo | -0.040 |
common | -0.039 |
vinegar | -0.038 |
bruises | -0.038 |
Token | y |
Token ID | 331 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
emaker | +0.079 |
pole | +0.077 |
ickets | +0.075 |
warrior | +0.075 |
ados | +0.073 |
Neg logit contributions | |
shampoo | -0.055 |
fault | -0.053 |
vinegar | -0.052 |
common | -0.051 |
L | -0.051 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
warrior | +0.143 |
pole | +0.136 |
King | +0.135 |
person | +0.134 |
emaker | +0.131 |
Neg logit contributions | |
shampoo | -0.152 |
vinegar | -0.148 |
omo | -0.148 |
lemon | -0.147 |
ucker | -0.142 |
Token | snack |
Token ID | 26906 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
emaker | +0.227 |
pole | +0.219 |
warrior | +0.218 |
ickets | +0.211 |
umbo | +0.206 |
Neg logit contributions | |
shampoo | -0.156 |
vinegar | -0.149 |
fault | -0.139 |
lemon | -0.136 |
common | -0.133 |
Token | !" |
Token ID | 2474 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
warrior | +0.043 |
emaker | +0.043 |
pole | +0.042 |
ickets | +0.039 |
umbo | +0.039 |
Neg logit contributions | |
shampoo | -0.045 |
fault | -0.044 |
vinegar | -0.044 |
L | -0.043 |
common | -0.042 |
Token | The |
Token ID | 383 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
pole | +0.016 |
emaker | +0.016 |
warrior | +0.016 |
ickets | +0.015 |
umbo | +0.015 |
Neg logit contributions | |
shampoo | -0.013 |
L | -0.012 |
vinegar | -0.012 |
fault | -0.011 |
bruises | -0.011 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
shampoo | +0.036 |
fault | +0.035 |
vinegar | +0.034 |
common | +0.034 |
L | +0.033 |
Neg logit contributions | |
pole | -0.030 |
emaker | -0.029 |
warrior | -0.029 |
ickets | -0.028 |
ados | -0.027 |
Token | agreed |
Token ID | 4987 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
shampoo | +0.002 |
fault | +0.002 |
L | +0.002 |
vinegar | +0.002 |
common | +0.002 |
Neg logit contributions | |
pole | -0.005 |
emaker | -0.005 |
warrior | -0.005 |
ados | -0.005 |
ickets | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-03 |
Pos logit contributions | |
shampoo | +0.004 |
fault | +0.004 |
vinegar | +0.004 |
L | +0.004 |
common | +0.004 |
Neg logit contributions | |
pole | -0.005 |
emaker | -0.005 |
warrior | -0.005 |
ickets | -0.005 |
ados | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
bruises | +0.004 |
common | +0.004 |
fault | +0.004 |
shampoo | +0.004 |
vinegar | +0.004 |
Neg logit contributions | |
pole | -0.003 |
umbo | -0.003 |
ickets | -0.003 |
emaker | -0.003 |
warrior | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
warrior | +0.040 |
pole | +0.040 |
King | +0.038 |
owl | +0.037 |
kingdom | +0.036 |
Neg logit contributions | |
fault | -0.045 |
vinegar | -0.044 |
common | -0.041 |
shampoo | -0.040 |
bruises | -0.040 |
Token | brought |
Token ID | 3181 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
fault | +0.021 |
vinegar | +0.021 |
shampoo | +0.020 |
bruises | +0.019 |
common | +0.018 |
Neg logit contributions | |
warrior | -0.021 |
pole | -0.021 |
stone | -0.019 |
emaker | -0.019 |
King | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
pole | +0.054 |
warrior | +0.052 |
emaker | +0.052 |
ados | +0.051 |
ickets | +0.051 |
Neg logit contributions | |
fault | -0.035 |
shampoo | -0.035 |
vinegar | -0.034 |
common | -0.033 |
bruises | -0.033 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
pole | +0.046 |
warrior | +0.045 |
stone | +0.043 |
emaker | +0.043 |
ickets | +0.043 |
Neg logit contributions | |
fault | -0.044 |
shampoo | -0.043 |
vinegar | -0.043 |
bruises | -0.042 |
L | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
warrior | +0.233 |
emaker | +0.229 |
ickets | +0.217 |
ados | +0.212 |
eagle | +0.211 |
Neg logit contributions | |
shampoo | -0.145 |
L | -0.144 |
cheaper | -0.134 |
fault | -0.130 |
Sara | -0.130 |
Token | some |
Token ID | 617 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ados | +0.028 |
pole | +0.026 |
King | +0.026 |
stone | +0.025 |
mushroom | +0.024 |
Neg logit contributions | |
fault | -0.061 |
aj | -0.057 |
ses | -0.054 |
ours | -0.053 |
vinegar | -0.052 |
Token | bread |
Token ID | 8509 |
Feature activation | -9.20e-03 |
Pos logit contributions | |
fault | +0.038 |
L | +0.033 |
aj | +0.033 |
rou | +0.033 |
omo | +0.033 |
Neg logit contributions | |
pole | -0.020 |
ados | -0.020 |
mushroom | -0.020 |
stone | -0.019 |
owl | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
pole | +0.011 |
ados | +0.010 |
stone | +0.010 |
emaker | +0.010 |
ickets | +0.010 |
Neg logit contributions | |
fault | -0.016 |
shampoo | -0.016 |
common | -0.016 |
bruises | -0.016 |
vinegar | -0.015 |
Token | cheese |
Token ID | 9891 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
mushroom | +0.007 |
Charlie | +0.006 |
owl | +0.006 |
stone | +0.006 |
ados | +0.006 |
Neg logit contributions | |
fault | -0.011 |
rou | -0.010 |
aj | -0.010 |
outed | -0.009 |
ours | -0.009 |
Token | Can |
Token ID | 1680 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
pole | +0.021 |
warrior | +0.020 |
ickets | +0.019 |
emaker | +0.019 |
ados | +0.019 |
Neg logit contributions | |
fault | -0.026 |
shampoo | -0.026 |
vinegar | -0.025 |
common | -0.024 |
bruises | -0.024 |
Token | I |
Token ID | 314 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
pole | +0.002 |
emaker | +0.002 |
warrior | +0.002 |
ickets | +0.002 |
ados | +0.002 |
Neg logit contributions | |
shampoo | -0.002 |
fault | -0.002 |
vinegar | -0.002 |
common | -0.002 |
L | -0.002 |
Token | have |
Token ID | 423 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
pole | +0.039 |
emaker | +0.037 |
ickets | +0.036 |
warrior | +0.036 |
umbo | +0.036 |
Neg logit contributions | |
fault | -0.042 |
vinegar | -0.039 |
shampoo | -0.039 |
bruises | -0.039 |
aj | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
on | +0.032 |
ados | +0.031 |
Charlie | +0.028 |
pole | +0.028 |
ons | +0.028 |
Neg logit contributions | |
ses | -0.039 |
fault | -0.039 |
aj | -0.037 |
rou | -0.036 |
common | -0.035 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
warrior | +0.019 |
pole | +0.019 |
mushroom | +0.018 |
King | +0.017 |
eagle | +0.017 |
Neg logit contributions | |
bruises | -0.022 |
L | -0.022 |
fault | -0.021 |
shampoo | -0.021 |
vinegar | -0.021 |
Token | ay |
Token ID | 323 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
warrior | +0.079 |
trolls | +0.072 |
pole | +0.072 |
traveller | +0.070 |
ados | +0.069 |
Neg logit contributions | |
fault | -0.142 |
shampoo | -0.139 |
omo | -0.133 |
aj | -0.132 |
vinegar | -0.132 |
Token | on |
Token ID | 261 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
pole | +0.097 |
warrior | +0.094 |
trolls | +0.082 |
traveller | +0.077 |
stone | +0.076 |
Neg logit contributions | |
shampoo | -0.281 |
vinegar | -0.270 |
bruises | -0.266 |
L | -0.265 |
common | -0.261 |
Token | instead |
Token ID | 2427 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
pole | +0.090 |
warrior | +0.087 |
emaker | +0.086 |
ickets | +0.083 |
ados | +0.083 |
Neg logit contributions | |
shampoo | -0.081 |
fault | -0.079 |
vinegar | -0.077 |
L | -0.076 |
common | -0.076 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
pole | +0.050 |
warrior | +0.049 |
emaker | +0.049 |
ickets | +0.047 |
ados | +0.047 |
Neg logit contributions | |
shampoo | -0.046 |
fault | -0.045 |
vinegar | -0.044 |
common | -0.043 |
L | -0.043 |
Token | Her |
Token ID | 2332 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
Charlie | +0.010 |
ados | +0.010 |
warrior | +0.010 |
emaker | +0.010 |
pole | +0.010 |
Neg logit contributions | |
vinegar | -0.012 |
fault | -0.012 |
shampoo | -0.012 |
common | -0.012 |
ruined | -0.011 |
Token | uncle |
Token ID | 7711 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
vinegar | +0.007 |
shampoo | +0.007 |
common | +0.006 |
fault | +0.006 |
bruises | +0.006 |
Neg logit contributions | |
warrior | -0.007 |
pole | -0.007 |
emaker | -0.007 |
owl | -0.006 |
eagle | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
shampoo | +0.004 |
fault | +0.004 |
L | +0.004 |
vinegar | +0.004 |
common | +0.004 |
Neg logit contributions | |
pole | -0.003 |
emaker | -0.003 |
warrior | -0.002 |
ickets | -0.002 |
ados | -0.002 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
pole | +0.054 |
King | +0.050 |
lf | +0.050 |
warrior | +0.049 |
owl | +0.048 |
Neg logit contributions | |
fault | -0.063 |
vinegar | -0.058 |
shampoo | -0.055 |
bruises | -0.055 |
ours | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
pole | +0.040 |
ados | +0.038 |
Charlie | +0.038 |
trolls | +0.038 |
King | +0.038 |
Neg logit contributions | |
aj | -0.057 |
fault | -0.057 |
common | -0.056 |
shampoo | -0.056 |
vinegar | -0.055 |
Token | make |
Token ID | 787 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
pole | +0.044 |
warrior | +0.042 |
emaker | +0.042 |
ickets | +0.041 |
ados | +0.040 |
Neg logit contributions | |
fault | -0.043 |
shampoo | -0.043 |
vinegar | -0.042 |
L | -0.041 |
common | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
ados | +0.053 |
pole | +0.052 |
stone | +0.049 |
emaker | +0.049 |
warrior | +0.048 |
Neg logit contributions | |
common | -0.050 |
fault | -0.050 |
shampoo | -0.047 |
vinegar | -0.046 |
bruises | -0.046 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pole | +0.074 |
warrior | +0.071 |
emaker | +0.070 |
ickets | +0.068 |
ados | +0.067 |
Neg logit contributions | |
shampoo | -0.075 |
fault | -0.074 |
vinegar | -0.072 |
common | -0.071 |
L | -0.071 |
Token | perfume |
Token ID | 40094 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
emaker | +0.213 |
pole | +0.212 |
warrior | +0.205 |
ickets | +0.205 |
umbo | +0.197 |
Neg logit contributions | |
shampoo | -0.164 |
vinegar | -0.150 |
fault | -0.145 |
common | -0.144 |
L | -0.142 |
Token | for |
Token ID | 329 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
emaker | +0.061 |
warrior | +0.060 |
pole | +0.060 |
ickets | +0.058 |
ados | +0.056 |
Neg logit contributions | |
shampoo | -0.052 |
fault | -0.048 |
vinegar | -0.047 |
L | -0.047 |
common | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ados | +0.039 |
pole | +0.038 |
ickets | +0.036 |
emaker | +0.036 |
quet | +0.035 |
Neg logit contributions | |
fault | -0.068 |
shampoo | -0.063 |
common | -0.062 |
vinegar | -0.062 |
aj | -0.061 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
pole | +0.036 |
angel | +0.034 |
owl | +0.034 |
ados | +0.034 |
King | +0.034 |
Neg logit contributions | |
vinegar | -0.050 |
ours | -0.049 |
common | -0.048 |
shampoo | -0.048 |
bruises | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
shampoo | +0.002 |
fault | +0.002 |
vinegar | +0.002 |
bruises | +0.002 |
common | +0.002 |
Neg logit contributions | |
pole | -0.001 |
emaker | -0.001 |
stone | -0.001 |
warrior | -0.001 |
ickets | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
fault | +0.031 |
shampoo | +0.030 |
vinegar | +0.029 |
common | +0.028 |
bruises | +0.028 |
Neg logit contributions | |
pole | -0.023 |
emaker | -0.022 |
ickets | -0.022 |
warrior | -0.022 |
umbo | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
pole | +0.033 |
emaker | +0.032 |
warrior | +0.032 |
ickets | +0.031 |
umbo | +0.030 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.028 |
L | -0.027 |
vinegar | -0.026 |
common | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
shampoo | +0.009 |
fault | +0.009 |
L | +0.009 |
vinegar | +0.009 |
common | +0.008 |
Neg logit contributions | |
pole | -0.007 |
emaker | -0.007 |
warrior | -0.007 |
stone | -0.007 |
ickets | -0.007 |
Token | brought |
Token ID | 3181 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
pole | +0.034 |
warrior | +0.033 |
emaker | +0.031 |
eagle | +0.031 |
King | +0.031 |
Neg logit contributions | |
fault | -0.032 |
vinegar | -0.031 |
bruises | -0.031 |
common | -0.031 |
shampoo | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
pole | +0.043 |
warrior | +0.042 |
emaker | +0.041 |
ickets | +0.040 |
umbo | +0.039 |
Neg logit contributions | |
shampoo | -0.027 |
L | -0.025 |
fault | -0.024 |
vinegar | -0.024 |
common | -0.023 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pole | +0.043 |
warrior | +0.042 |
emaker | +0.040 |
stone | +0.040 |
ickets | +0.039 |
Neg logit contributions | |
fault | -0.045 |
shampoo | -0.044 |
vinegar | -0.044 |
L | -0.043 |
bruises | -0.043 |
Token | of |
Token ID | 286 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
warrior | +0.250 |
emaker | +0.236 |
trolls | +0.231 |
ickets | +0.226 |
eagle | +0.225 |
Neg logit contributions | |
shampoo | -0.137 |
L | -0.131 |
cheaper | -0.119 |
fault | -0.117 |
Sara | -0.117 |
Token | treats |
Token ID | 18432 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
pole | +0.028 |
warrior | +0.027 |
ados | +0.027 |
emaker | +0.026 |
ickets | +0.026 |
Neg logit contributions | |
fault | -0.025 |
shampoo | -0.023 |
common | -0.023 |
vinegar | -0.023 |
L | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
pole | +0.060 |
warrior | +0.058 |
emaker | +0.058 |
ickets | +0.056 |
ados | +0.055 |
Neg logit contributions | |
shampoo | -0.063 |
fault | -0.061 |
vinegar | -0.060 |
L | -0.059 |
common | -0.059 |
Token | share |
Token ID | 2648 |
Feature activation | -9.18e-03 |
Pos logit contributions | |
fault | +0.024 |
bruises | +0.021 |
shampoo | +0.021 |
aj | +0.021 |
vinegar | +0.021 |
Neg logit contributions | |
pole | -0.015 |
warrior | -0.013 |
King | -0.013 |
emaker | -0.013 |
ados | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
pole | +0.012 |
emaker | +0.011 |
warrior | +0.011 |
ados | +0.011 |
ickets | +0.011 |
Neg logit contributions | |
fault | -0.015 |
shampoo | -0.015 |
vinegar | -0.015 |
common | -0.014 |
bruises | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
shampoo | +0.023 |
fault | +0.022 |
L | +0.021 |
vinegar | +0.021 |
common | +0.021 |
Neg logit contributions | |
pole | -0.019 |
emaker | -0.018 |
warrior | -0.018 |
ickets | -0.018 |
ados | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
pole | +0.022 |
warrior | +0.021 |
emaker | +0.021 |
ados | +0.021 |
stone | +0.020 |
Neg logit contributions | |
fault | -0.028 |
shampoo | -0.027 |
common | -0.026 |
vinegar | -0.026 |
aj | -0.025 |
Token | finally |
Token ID | 3443 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
pole | +0.011 |
warrior | +0.011 |
emaker | +0.011 |
ickets | +0.010 |
stone | +0.010 |
Neg logit contributions | |
shampoo | -0.007 |
fault | -0.007 |
common | -0.006 |
vinegar | -0.006 |
bruises | -0.006 |
Token | made |
Token ID | 925 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
shampoo | +0.032 |
fault | +0.031 |
vinegar | +0.030 |
bruises | +0.030 |
common | +0.030 |
Neg logit contributions | |
pole | -0.039 |
warrior | -0.038 |
emaker | -0.038 |
ickets | -0.036 |
stone | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
pole | +0.034 |
emaker | +0.034 |
warrior | +0.033 |
ados | +0.033 |
ickets | +0.032 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.027 |
common | -0.027 |
vinegar | -0.027 |
bruises | -0.026 |
Token | basket |
Token ID | 7988 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pole | +0.052 |
warrior | +0.051 |
emaker | +0.050 |
ickets | +0.049 |
ados | +0.048 |
Neg logit contributions | |
shampoo | -0.040 |
fault | -0.039 |
vinegar | -0.038 |
common | -0.037 |
L | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
warrior | +0.202 |
emaker | +0.194 |
ados | +0.193 |
trolls | +0.190 |
ickets | +0.189 |
Neg logit contributions | |
shampoo | -0.162 |
L | -0.162 |
fault | -0.157 |
cheaper | -0.154 |
ruined | -0.153 |
Token | He |
Token ID | 679 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
pole | +0.009 |
emaker | +0.009 |
warrior | +0.009 |
ickets | +0.009 |
ados | +0.008 |
Neg logit contributions | |
shampoo | -0.008 |
fault | -0.008 |
common | -0.008 |
vinegar | -0.008 |
bruises | -0.007 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
pole | +0.017 |
warrior | +0.016 |
emaker | +0.016 |
stone | +0.016 |
umbo | +0.015 |
Neg logit contributions | |
fault | -0.008 |
shampoo | -0.008 |
common | -0.008 |
vinegar | -0.008 |
bruises | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.013 |
emaker | +0.013 |
ickets | +0.012 |
ados | +0.012 |
Neg logit contributions | |
fault | -0.017 |
shampoo | -0.016 |
vinegar | -0.016 |
common | -0.016 |
aj | -0.016 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
shampoo | +0.009 |
common | +0.008 |
vinegar | +0.008 |
L | +0.008 |
fault | +0.008 |
Neg logit contributions | |
pole | -0.012 |
emaker | -0.012 |
warrior | -0.012 |
ados | -0.012 |
ickets | -0.012 |
Token | bite |
Token ID | 13197 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
pole | +0.023 |
warrior | +0.022 |
emaker | +0.021 |
ados | +0.021 |
stone | +0.020 |
Neg logit contributions | |
fault | -0.025 |
shampoo | -0.025 |
bruises | -0.024 |
L | -0.024 |
common | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
fault | +0.022 |
common | +0.021 |
aj | +0.021 |
bruises | +0.021 |
shampoo | +0.021 |
Neg logit contributions | |
pole | -0.015 |
emaker | -0.015 |
ickets | -0.014 |
ados | -0.014 |
warrior | -0.014 |
Token | makes |
Token ID | 1838 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
down | +0.021 |
warrior | +0.021 |
mushroom | +0.021 |
King | +0.021 |
Charlie | +0.020 |
Neg logit contributions | |
fault | -0.024 |
aj | -0.022 |
common | -0.022 |
injuries | -0.021 |
outed | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
pole | +0.013 |
Charlie | +0.013 |
on | +0.013 |
ados | +0.013 |
King | +0.013 |
Neg logit contributions | |
common | -0.013 |
aj | -0.013 |
bruises | -0.013 |
fault | -0.012 |
shampoo | -0.012 |
Token | y |
Token ID | 331 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
pole | +0.054 |
warrior | +0.053 |
ickets | +0.050 |
emaker | +0.049 |
eagle | +0.048 |
Neg logit contributions | |
fault | -0.056 |
shampoo | -0.055 |
common | -0.052 |
bruises | -0.051 |
L | -0.051 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pole | +0.121 |
warrior | +0.118 |
emaker | +0.110 |
stone | +0.107 |
King | +0.105 |
Neg logit contributions | |
shampoo | -0.188 |
vinegar | -0.187 |
fault | -0.183 |
common | -0.180 |
omo | -0.176 |
Token | sound |
Token ID | 2128 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
pole | +0.200 |
emaker | +0.193 |
warrior | +0.193 |
ickets | +0.187 |
ados | +0.185 |
Neg logit contributions | |
shampoo | -0.165 |
fault | -0.163 |
vinegar | -0.156 |
common | -0.155 |
L | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e-04 |
Pos logit contributions | |
pole | +0.050 |
emaker | +0.048 |
warrior | +0.047 |
ickets | +0.046 |
ados | +0.045 |
Neg logit contributions | |
fault | -0.051 |
shampoo | -0.051 |
common | -0.050 |
vinegar | -0.048 |
bruises | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-05 |
Pos logit contributions | |
fault | +0.001 |
shampoo | +0.001 |
bruises | +0.001 |
common | +0.001 |
ruined | +0.001 |
Neg logit contributions | |
ickets | -0.000 |
pole | -0.000 |
warrior | -0.000 |
Charlie | -0.000 |
ados | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
shampoo | +0.000 |
fault | +0.000 |
vinegar | +0.000 |
bruises | +0.000 |
common | +0.000 |
Neg logit contributions | |
pole | -0.000 |
ickets | -0.000 |
emaker | -0.000 |
warrior | -0.000 |
umbo | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
pole | +0.002 |
emaker | +0.002 |
ados | +0.002 |
warrior | +0.002 |
stone | +0.002 |
Neg logit contributions | |
shampoo | -0.002 |
common | -0.002 |
L | -0.002 |
vinegar | -0.002 |
bruises | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
pole | +0.084 |
warrior | +0.081 |
emaker | +0.080 |
ados | +0.079 |
stone | +0.078 |
Neg logit contributions | |
shampoo | -0.063 |
fault | -0.062 |
vinegar | -0.060 |
common | -0.060 |
L | -0.059 |
Token | flowers |
Token ID | 12734 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
around | +0.017 |
mushroom | +0.017 |
owl | +0.017 |
angel | +0.017 |
ados | +0.017 |
Neg logit contributions | |
fault | -0.024 |
ours | -0.023 |
L | -0.023 |
omo | -0.023 |
common | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
pole | +0.088 |
emaker | +0.086 |
warrior | +0.086 |
ickets | +0.083 |
umbo | +0.081 |
Neg logit contributions | |
shampoo | -0.095 |
fault | -0.093 |
vinegar | -0.090 |
common | -0.089 |
L | -0.088 |
Token | make |
Token ID | 787 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
owl | +0.030 |
mushroom | +0.029 |
trolls | +0.028 |
ados | +0.027 |
dragons | +0.026 |
Neg logit contributions | |
fault | -0.060 |
omo | -0.057 |
ours | -0.056 |
aj | -0.056 |
rou | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
pole | +0.045 |
ados | +0.045 |
ickets | +0.041 |
stone | +0.041 |
angel | +0.040 |
Neg logit contributions | |
common | -0.049 |
omo | -0.048 |
aj | -0.048 |
fault | -0.048 |
shampoo | -0.046 |
Token | bou |
Token ID | 35833 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pole | +0.059 |
warrior | +0.056 |
stone | +0.053 |
mushroom | +0.053 |
emaker | +0.053 |
Neg logit contributions | |
fault | -0.061 |
shampoo | -0.060 |
vinegar | -0.059 |
bruises | -0.058 |
common | -0.057 |
Token | quet |
Token ID | 21108 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
warrior | +0.112 |
Charlie | +0.094 |
ogre | +0.090 |
eagle | +0.090 |
trolls | +0.088 |
Neg logit contributions | |
shampoo | -0.266 |
bruises | -0.244 |
aj | -0.243 |
cheaper | -0.241 |
towels | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
pole | +0.189 |
warrior | +0.188 |
emaker | +0.188 |
ickets | +0.181 |
ados | +0.180 |
Neg logit contributions | |
shampoo | -0.155 |
fault | -0.153 |
vinegar | -0.147 |
L | -0.147 |
common | -0.144 |
Token | We |
Token ID | 775 |
Feature activation | +8.96e-04 |
Pos logit contributions | |
pole | +0.017 |
warrior | +0.017 |
ickets | +0.016 |
Charlie | +0.016 |
ados | +0.016 |
Neg logit contributions | |
fault | -0.023 |
shampoo | -0.023 |
ruined | -0.023 |
common | -0.023 |
arose | -0.022 |
Token | can |
Token ID | 460 |
Feature activation | +6.39e-03 |
Pos logit contributions | |
aj | +0.001 |
shampoo | +0.001 |
fault | +0.001 |
vinegar | +0.001 |
L | +0.001 |
Neg logit contributions | |
pole | -0.002 |
warrior | -0.002 |
emaker | -0.002 |
stone | -0.001 |
King | -0.001 |
Token | also |
Token ID | 635 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
shampoo | +0.008 |
fault | +0.008 |
vinegar | +0.008 |
common | +0.008 |
L | +0.008 |
Neg logit contributions | |
pole | -0.011 |
emaker | -0.010 |
warrior | -0.010 |
ados | -0.010 |
ickets | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
L | +0.049 |
Sara | +0.047 |
ours | +0.047 |
Qu | +0.047 |
rou | +0.046 |
Neg logit contributions | |
warrior | -0.035 |
lf | -0.035 |
kingdom | -0.034 |
est | -0.034 |
ados | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
Qu | +0.137 |
shampoo | +0.136 |
vinegar | +0.134 |
L | +0.134 |
ses | +0.133 |
Neg logit contributions | |
pole | -0.082 |
stone | -0.079 |
around | -0.079 |
emaker | -0.078 |
on | -0.077 |
Token | their |
Token ID | 511 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
aj | +0.006 |
common | +0.006 |
fault | +0.005 |
Qu | +0.005 |
ours | +0.005 |
Neg logit contributions | |
forth | -0.005 |
emaker | -0.005 |
down | -0.005 |
around | -0.005 |
lf | -0.004 |
Token | new |
Token ID | 649 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
ours | +0.066 |
ucker | +0.064 |
stro | +0.064 |
Does | +0.062 |
L | +0.062 |
Neg logit contributions | |
image | -0.038 |
King | -0.038 |
missile | -0.038 |
lf | -0.037 |
warrior | -0.037 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
vinegar | +0.161 |
ours | +0.154 |
L | +0.153 |
wasteful | +0.151 |
bleach | +0.150 |
Neg logit contributions | |
warrior | -0.093 |
est | -0.088 |
pole | -0.087 |
King | -0.085 |
angel | -0.084 |
Token | car |
Token ID | 1097 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
shampoo | +0.120 |
common | +0.120 |
vinegar | +0.118 |
fault | +0.116 |
L | +0.113 |
Neg logit contributions | |
pole | -0.110 |
emaker | -0.106 |
warrior | -0.105 |
stone | -0.103 |
ados | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
shampoo | +0.155 |
common | +0.154 |
vinegar | +0.154 |
ours | +0.149 |
Qu | +0.147 |
Neg logit contributions | |
pole | -0.126 |
emaker | -0.120 |
stone | -0.118 |
around | -0.113 |
down | -0.111 |
Token | They |
Token ID | 1119 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
shampoo | +0.007 |
rou | +0.007 |
scar | +0.007 |
aj | +0.006 |
fault | +0.006 |
Neg logit contributions | |
Charlie | -0.005 |
person | -0.004 |
ados | -0.004 |
pole | -0.004 |
Hope | -0.004 |
Token | wished |
Token ID | 16555 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
pole | +0.004 |
warrior | +0.003 |
emaker | +0.003 |
King | +0.003 |
jack | +0.003 |
Neg logit contributions | |
fault | -0.004 |
common | -0.004 |
aj | -0.003 |
shampoo | -0.003 |
vinegar | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
aj | +0.009 |
shampoo | +0.009 |
common | +0.009 |
fault | +0.008 |
ours | +0.008 |
Neg logit contributions | |
Charlie | -0.010 |
Peter | -0.009 |
ados | -0.009 |
fully | -0.009 |
King | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
pole | +0.035 |
emaker | +0.035 |
warrior | +0.033 |
stone | +0.033 |
person | +0.032 |
Neg logit contributions | |
fault | -0.033 |
shampoo | -0.032 |
vinegar | -0.032 |
common | -0.031 |
ours | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
common | +0.033 |
vinegar | +0.032 |
fault | +0.031 |
shampoo | +0.030 |
aj | +0.030 |
Neg logit contributions | |
pole | -0.019 |
down | -0.019 |
around | -0.017 |
ring | -0.017 |
string | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
common | +0.034 |
vinegar | +0.034 |
cheaper | +0.033 |
shampoo | +0.033 |
fault | +0.033 |
Neg logit contributions | |
ados | -0.007 |
ickets | -0.006 |
Charlie | -0.006 |
amber | -0.005 |
emaker | -0.005 |
Token | cried |
Token ID | 16896 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
on | +0.014 |
emaker | +0.013 |
around | +0.013 |
owl | +0.013 |
lf | +0.013 |
Neg logit contributions | |
fault | -0.033 |
common | -0.032 |
theirs | -0.029 |
ours | -0.028 |
cheaper | -0.028 |
Token | louder |
Token ID | 27089 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
shampoo | +0.019 |
L | +0.019 |
fault | +0.019 |
bruises | +0.018 |
vinegar | +0.018 |
Neg logit contributions | |
pole | -0.022 |
warrior | -0.021 |
emaker | -0.021 |
ickets | -0.020 |
stone | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
shampoo | +0.171 |
fault | +0.169 |
vinegar | +0.164 |
common | +0.164 |
bruises | +0.157 |
Neg logit contributions | |
pole | -0.121 |
emaker | -0.117 |
warrior | -0.115 |
ickets | -0.111 |
ados | -0.110 |
Token | louder |
Token ID | 27089 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
fault | +0.036 |
common | +0.033 |
habitats | +0.030 |
omo | +0.029 |
former | +0.029 |
Neg logit contributions | |
down | -0.029 |
forth | -0.026 |
owl | -0.025 |
stone | -0.023 |
around | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
shampoo | +0.132 |
fault | +0.130 |
common | +0.126 |
vinegar | +0.125 |
bruises | +0.119 |
Neg logit contributions | |
pole | -0.128 |
emaker | -0.124 |
warrior | -0.123 |
ados | -0.119 |
ickets | -0.119 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
vinegar | +0.040 |
common | +0.040 |
cheaper | +0.039 |
fault | +0.039 |
shampoo | +0.039 |
Neg logit contributions | |
ados | -0.015 |
Charlie | -0.014 |
ickets | -0.014 |
amber | -0.013 |
Mickey | -0.013 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
fault | +0.019 |
common | +0.019 |
shampoo | +0.018 |
vinegar | +0.018 |
L | +0.017 |
Neg logit contributions | |
pole | -0.023 |
emaker | -0.023 |
warrior | -0.023 |
ickets | -0.022 |
stone | -0.021 |
Token | sorry |
Token ID | 7926 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
aj | +0.004 |
fault | +0.004 |
common | +0.004 |
omo | +0.004 |
ours | +0.004 |
Neg logit contributions | |
around | -0.003 |
down | -0.003 |
emaker | -0.003 |
taker | -0.003 |
alone | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
shampoo | +0.046 |
fault | +0.045 |
common | +0.044 |
vinegar | +0.044 |
bruises | +0.043 |
Neg logit contributions | |
pole | -0.038 |
emaker | -0.036 |
warrior | -0.036 |
ickets | -0.035 |
ados | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
shampoo | +0.074 |
fault | +0.073 |
L | +0.071 |
common | +0.071 |
vinegar | +0.071 |
Neg logit contributions | |
pole | -0.056 |
emaker | -0.054 |
warrior | -0.054 |
ickets | -0.052 |
ados | -0.051 |
Token | there |
Token ID | 612 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
pole | +0.011 |
emaker | +0.010 |
warrior | +0.010 |
stone | +0.009 |
ickets | +0.009 |
Neg logit contributions | |
fault | -0.013 |
shampoo | -0.013 |
vinegar | -0.013 |
bruises | -0.013 |
common | -0.012 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
on | +0.028 |
pole | +0.028 |
emaker | +0.028 |
est | +0.027 |
he | +0.027 |
Neg logit contributions | |
aj | -0.030 |
fault | -0.029 |
bruises | -0.029 |
vinegar | -0.029 |
cheaper | -0.028 |
Token | two |
Token ID | 734 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
fault | +0.026 |
shampoo | +0.026 |
vinegar | +0.025 |
common | +0.024 |
L | +0.023 |
Neg logit contributions | |
pole | -0.061 |
warrior | -0.059 |
emaker | -0.059 |
ickets | -0.058 |
ados | -0.057 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
shampoo | +0.033 |
fault | +0.032 |
vinegar | +0.032 |
L | +0.031 |
bruises | +0.031 |
Neg logit contributions | |
pole | -0.034 |
emaker | -0.033 |
warrior | -0.032 |
ickets | -0.031 |
stone | -0.031 |
Token | named |
Token ID | 3706 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
pole | +0.048 |
warrior | +0.047 |
emaker | +0.047 |
ickets | +0.045 |
ados | +0.045 |
Neg logit contributions | |
shampoo | -0.033 |
fault | -0.032 |
vinegar | -0.031 |
L | -0.031 |
common | -0.030 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
shampoo | +0.107 |
fault | +0.104 |
vinegar | +0.100 |
common | +0.099 |
L | +0.098 |
Neg logit contributions | |
pole | -0.183 |
emaker | -0.178 |
warrior | -0.177 |
ickets | -0.173 |
ados | -0.171 |
Token | and |
Token ID | 290 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
pole | +0.021 |
emaker | +0.020 |
warrior | +0.020 |
ickets | +0.019 |
ados | +0.019 |
Neg logit contributions | |
shampoo | -0.022 |
fault | -0.021 |
vinegar | -0.021 |
common | -0.021 |
L | -0.021 |
Token | Sally |
Token ID | 25737 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
shampoo | +0.036 |
fault | +0.035 |
L | +0.035 |
common | +0.034 |
vinegar | +0.034 |
Neg logit contributions | |
pole | -0.044 |
emaker | -0.043 |
warrior | -0.042 |
ickets | -0.042 |
ados | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
pole | +0.004 |
warrior | +0.004 |
emaker | +0.004 |
ickets | +0.004 |
ados | +0.004 |
Neg logit contributions | |
shampoo | -0.003 |
fault | -0.003 |
L | -0.003 |
vinegar | -0.003 |
common | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | -6.54e-04 |
Pos logit contributions | |
fault | +0.023 |
shampoo | +0.023 |
L | +0.023 |
vinegar | +0.022 |
common | +0.022 |
Neg logit contributions | |
pole | -0.052 |
emaker | -0.051 |
warrior | -0.050 |
stone | -0.049 |
ickets | -0.048 |
Token | understand |
Token ID | 1833 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
shampoo | +0.012 |
fault | +0.012 |
vinegar | +0.012 |
common | +0.012 |
L | +0.012 |
Neg logit contributions | |
pole | -0.012 |
warrior | -0.012 |
emaker | -0.012 |
ickets | -0.012 |
ados | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ses | +0.010 |
bruises | +0.010 |
aj | +0.010 |
fault | +0.010 |
vinegar | +0.010 |
Neg logit contributions | |
pole | -0.008 |
ados | -0.008 |
King | -0.007 |
emaker | -0.007 |
warrior | -0.007 |
Token | world |
Token ID | 995 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
shampoo | +0.057 |
vinegar | +0.055 |
fault | +0.055 |
L | +0.055 |
common | +0.054 |
Neg logit contributions | |
pole | -0.055 |
warrior | -0.054 |
emaker | -0.051 |
ados | -0.051 |
ickets | -0.051 |
Token | around |
Token ID | 1088 |
Feature activation | +9.20e-04 |
Pos logit contributions | |
shampoo | +0.021 |
fault | +0.020 |
vinegar | +0.020 |
bruises | +0.020 |
L | +0.019 |
Neg logit contributions | |
pole | -0.025 |
warrior | -0.024 |
emaker | -0.023 |
ickets | -0.023 |
stone | -0.023 |
Token | us |
Token ID | 514 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
fault | +0.001 |
shampoo | +0.001 |
vinegar | +0.001 |
bruises | +0.001 |
aj | +0.001 |
Neg logit contributions | |
pole | -0.001 |
warrior | -0.001 |
emaker | -0.001 |
ados | -0.001 |
ickets | -0.001 |
Token | better |
Token ID | 1365 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
shampoo | +0.103 |
vinegar | +0.100 |
fault | +0.100 |
bruises | +0.098 |
common | +0.097 |
Neg logit contributions | |
pole | -0.091 |
warrior | -0.086 |
ickets | -0.084 |
emaker | -0.084 |
ados | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +9.52e-04 |
Pos logit contributions | |
vinegar | +0.156 |
shampoo | +0.156 |
bruises | +0.154 |
fault | +0.151 |
ours | +0.146 |
Neg logit contributions | |
warrior | -0.105 |
pole | -0.103 |
ados | -0.100 |
emaker | -0.097 |
trolls | -0.095 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
common | +0.002 |
fault | +0.002 |
shampoo | +0.002 |
vinegar | +0.002 |
bruises | +0.002 |
Neg logit contributions | |
pole | -0.001 |
umbo | -0.001 |
ados | -0.001 |
Charlie | -0.001 |
ickets | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
shampoo | +0.020 |
fault | +0.020 |
vinegar | +0.019 |
common | +0.019 |
L | +0.018 |
Neg logit contributions | |
pole | -0.034 |
warrior | -0.033 |
emaker | -0.032 |
ickets | -0.031 |
stone | -0.031 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
vinegar | +0.062 |
shampoo | +0.060 |
common | +0.060 |
fault | +0.059 |
bruises | +0.057 |
Neg logit contributions | |
pole | -0.038 |
warrior | -0.034 |
King | -0.033 |
emaker | -0.032 |
Charlie | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
pole | +0.005 |
emaker | +0.005 |
warrior | +0.005 |
ickets | +0.005 |
ados | +0.005 |
Neg logit contributions | |
shampoo | -0.004 |
fault | -0.004 |
vinegar | -0.004 |
L | -0.004 |
common | -0.004 |
Token | or |
Token ID | 393 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
bruises | +0.013 |
shampoo | +0.013 |
fault | +0.013 |
aj | +0.013 |
vinegar | +0.013 |
Neg logit contributions | |
pole | -0.013 |
warrior | -0.012 |
emaker | -0.012 |
stone | -0.012 |
ickets | -0.012 |
Token | frogs |
Token ID | 37475 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
fault | +0.012 |
aj | +0.012 |
omo | +0.012 |
ucker | +0.011 |
rou | +0.011 |
Neg logit contributions | |
warrior | -0.011 |
trolls | -0.011 |
King | -0.011 |
mushroom | -0.010 |
Charlie | -0.010 |
Token | or |
Token ID | 393 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
pole | +0.030 |
emaker | +0.027 |
warrior | +0.027 |
ickets | +0.027 |
stone | +0.026 |
Neg logit contributions | |
fault | -0.035 |
shampoo | -0.035 |
vinegar | -0.034 |
bruises | -0.034 |
common | -0.033 |
Token | snakes |
Token ID | 26042 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
aj | +0.035 |
fault | +0.035 |
outed | +0.035 |
omo | +0.035 |
ucker | +0.034 |
Neg logit contributions | |
warrior | -0.028 |
mushroom | -0.027 |
trolls | -0.027 |
King | -0.026 |
eagle | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
shampoo | +0.033 |
fault | +0.032 |
vinegar | +0.032 |
common | +0.032 |
bruises | +0.032 |
Neg logit contributions | |
pole | -0.026 |
emaker | -0.023 |
warrior | -0.023 |
ickets | -0.023 |
stone | -0.022 |
Token | Some |
Token ID | 2773 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
pole | +0.009 |
warrior | +0.008 |
ickets | +0.008 |
ados | +0.008 |
trolls | +0.008 |
Neg logit contributions | |
shampoo | -0.008 |
fault | -0.008 |
common | -0.008 |
bruises | -0.007 |
ruined | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
fault | +0.171 |
aj | +0.159 |
rou | +0.152 |
shampoo | +0.151 |
L | +0.146 |
Neg logit contributions | |
ickets | -0.134 |
pole | -0.130 |
warrior | -0.129 |
trolls | -0.127 |
eagle | -0.127 |
Token | them |
Token ID | 606 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
aj | +0.028 |
fault | +0.028 |
bruises | +0.024 |
outed | +0.024 |
rou | +0.024 |
Neg logit contributions | |
pole | -0.025 |
ados | -0.023 |
warrior | -0.022 |
mushroom | -0.022 |
Charlie | -0.022 |
Token | might |
Token ID | 1244 |
Feature activation | +7.24e-04 |
Pos logit contributions | |
fault | +0.013 |
shampoo | +0.013 |
vinegar | +0.013 |
bruises | +0.013 |
L | +0.013 |
Neg logit contributions | |
pole | -0.017 |
warrior | -0.016 |
ickets | -0.016 |
stone | -0.016 |
emaker | -0.015 |
Token | be |
Token ID | 307 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
aj | +0.001 |
ours | +0.001 |
shampoo | +0.001 |
bruises | +0.001 |
fault | +0.001 |
Neg logit contributions | |
pole | -0.001 |
warrior | -0.001 |
ickets | -0.001 |
eagle | -0.001 |
mushroom | -0.001 |
Token | friendly |
Token ID | 8030 |
Feature activation | -6.01e-04 |
Pos logit contributions | |
shampoo | +0.015 |
fault | +0.015 |
ours | +0.015 |
bruises | +0.015 |
arose | +0.015 |
Neg logit contributions | |
pole | -0.016 |
around | -0.014 |
warrior | -0.014 |
down | -0.014 |
trolls | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
pole | +0.057 |
warrior | +0.056 |
emaker | +0.055 |
stone | +0.054 |
ickets | +0.053 |
Neg logit contributions | |
shampoo | -0.043 |
fault | -0.042 |
vinegar | -0.042 |
common | -0.040 |
bruises | -0.039 |
Token | ordinary |
Token ID | 8850 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
vinegar | +0.021 |
ours | +0.020 |
shampoo | +0.020 |
common | +0.019 |
L | +0.019 |
Neg logit contributions | |
warrior | -0.011 |
owl | -0.011 |
King | -0.011 |
eagle | -0.011 |
angel | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
shampoo | +0.073 |
fault | +0.072 |
vinegar | +0.071 |
L | +0.070 |
common | +0.070 |
Neg logit contributions | |
pole | -0.051 |
warrior | -0.050 |
emaker | -0.049 |
ickets | -0.046 |
stone | -0.046 |
Token | turned |
Token ID | 2900 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
fault | +0.088 |
shampoo | +0.087 |
vinegar | +0.085 |
common | +0.083 |
bruises | +0.081 |
Neg logit contributions | |
pole | -0.077 |
emaker | -0.074 |
warrior | -0.074 |
ickets | -0.071 |
stone | -0.071 |
Token | into |
Token ID | 656 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
fault | +0.074 |
shampoo | +0.074 |
vinegar | +0.073 |
common | +0.072 |
bruises | +0.072 |
Neg logit contributions | |
pole | -0.040 |
warrior | -0.038 |
emaker | -0.038 |
ados | -0.037 |
ickets | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ours | +0.010 |
outed | +0.010 |
fault | +0.009 |
aj | +0.009 |
ucker | +0.009 |
Neg logit contributions | |
Charlie | -0.007 |
King | -0.007 |
mushroom | -0.007 |
warrior | -0.007 |
ados | -0.007 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
fault | +0.038 |
shampoo | +0.036 |
ours | +0.036 |
vinegar | +0.036 |
bruises | +0.036 |
Neg logit contributions | |
warrior | -0.030 |
pole | -0.029 |
eagle | -0.027 |
King | -0.026 |
stone | -0.026 |
Token | adventure |
Token ID | 8855 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
pole | +0.028 |
warrior | +0.027 |
emaker | +0.026 |
stone | +0.025 |
ickets | +0.025 |
Neg logit contributions | |
shampoo | -0.037 |
fault | -0.037 |
vinegar | -0.036 |
bruises | -0.036 |
L | -0.035 |
Token | ! |
Token ID | 0 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
pole | +0.009 |
emaker | +0.009 |
warrior | +0.009 |
ickets | +0.008 |
ados | +0.008 |
Neg logit contributions | |
shampoo | -0.010 |
fault | -0.010 |
vinegar | -0.010 |
common | -0.010 |
bruises | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
pole | +0.005 |
emaker | +0.005 |
warrior | +0.005 |
ickets | +0.005 |
ados | +0.005 |
Neg logit contributions | |
shampoo | -0.003 |
fault | -0.003 |
vinegar | -0.003 |
common | -0.003 |
L | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
fault | +0.009 |
shampoo | +0.009 |
vinegar | +0.008 |
bruises | +0.008 |
common | +0.008 |
Neg logit contributions | |
pole | -0.012 |
emaker | -0.011 |
ickets | -0.011 |
warrior | -0.011 |
umbo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
pole | +0.069 |
warrior | +0.068 |
emaker | +0.064 |
ados | +0.064 |
down | +0.063 |
Neg logit contributions | |
shampoo | -0.098 |
vinegar | -0.097 |
fault | -0.095 |
bruises | -0.093 |
aj | -0.091 |
Token | He |
Token ID | 679 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
pole | +0.007 |
warrior | +0.007 |
ickets | +0.007 |
umbo | +0.007 |
emaker | +0.007 |
Neg logit contributions | |
shampoo | -0.011 |
vinegar | -0.010 |
fault | -0.010 |
common | -0.010 |
bruises | -0.010 |
Token | realized |
Token ID | 6939 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
pole | +0.008 |
warrior | +0.008 |
King | +0.007 |
eagle | +0.007 |
stone | +0.007 |
Neg logit contributions | |
fault | -0.009 |
vinegar | -0.008 |
shampoo | -0.008 |
common | -0.008 |
bruises | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
vinegar | +0.037 |
fault | +0.037 |
ses | +0.037 |
common | +0.036 |
shampoo | +0.036 |
Neg logit contributions | |
warrior | -0.021 |
eagle | -0.020 |
pole | -0.020 |
Charlie | -0.020 |
King | -0.020 |
Token | voice |
Token ID | 3809 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
warrior | +0.017 |
eagle | +0.016 |
King | +0.016 |
owl | +0.015 |
pole | +0.015 |
Neg logit contributions | |
ours | -0.025 |
aj | -0.025 |
L | -0.024 |
fault | -0.024 |
shampoo | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
fault | +0.029 |
vinegar | +0.029 |
shampoo | +0.029 |
common | +0.027 |
aj | +0.027 |
Neg logit contributions | |
pole | -0.038 |
warrior | -0.036 |
emaker | -0.035 |
stone | -0.035 |
ickets | -0.034 |
Token | right |
Token ID | 826 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
ours | +0.033 |
aj | +0.032 |
fault | +0.032 |
vinegar | +0.032 |
bruises | +0.031 |
Neg logit contributions | |
pole | -0.026 |
Charlie | -0.024 |
King | -0.024 |
warrior | -0.023 |
around | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
pole | +0.029 |
warrior | +0.029 |
down | +0.029 |
stone | +0.027 |
around | +0.026 |
Neg logit contributions | |
vinegar | -0.063 |
shampoo | -0.062 |
bruises | -0.061 |
fault | -0.059 |
ours | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
pole | +0.028 |
warrior | +0.026 |
eagle | +0.025 |
Charlie | +0.024 |
King | +0.024 |
Neg logit contributions | |
fault | -0.044 |
common | -0.043 |
vinegar | -0.043 |
shampoo | -0.042 |
ours | -0.041 |
Token | stair |
Token ID | 18761 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
warrior | +0.021 |
King | +0.020 |
eagle | +0.019 |
owl | +0.019 |
angel | +0.019 |
Neg logit contributions | |
fault | -0.038 |
ours | -0.038 |
aj | -0.036 |
ucker | -0.036 |
vinegar | -0.036 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.87e-04 |
Pos logit contributions | |
pole | +0.077 |
emaker | +0.069 |
warrior | +0.069 |
stone | +0.068 |
jack | +0.067 |
Neg logit contributions | |
shampoo | -0.054 |
fault | -0.053 |
common | -0.052 |
vinegar | -0.052 |
aj | -0.049 |
Token | so |
Token ID | 523 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
pole | +0.041 |
warrior | +0.039 |
emaker | +0.037 |
stone | +0.036 |
King | +0.035 |
Neg logit contributions | |
vinegar | -0.055 |
fault | -0.055 |
shampoo | -0.055 |
bruises | -0.052 |
common | -0.051 |
Token | grateful |
Token ID | 14066 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
pole | +0.011 |
warrior | +0.011 |
emaker | +0.010 |
ickets | +0.010 |
stone | +0.010 |
Neg logit contributions | |
shampoo | -0.014 |
fault | -0.014 |
vinegar | -0.014 |
common | -0.013 |
bruises | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
pole | +0.049 |
warrior | +0.045 |
stone | +0.045 |
emaker | +0.044 |
ados | +0.043 |
Neg logit contributions | |
shampoo | -0.062 |
vinegar | -0.062 |
bruises | -0.060 |
fault | -0.060 |
common | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
shampoo | +0.067 |
fault | +0.066 |
L | +0.064 |
common | +0.064 |
vinegar | +0.063 |
Neg logit contributions | |
pole | -0.073 |
emaker | -0.070 |
warrior | -0.070 |
ickets | -0.068 |
ados | -0.067 |
Token | fairy |
Token ID | 25607 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
warrior | +0.011 |
eagle | +0.011 |
King | +0.010 |
pole | +0.010 |
owl | +0.010 |
Neg logit contributions | |
ours | -0.015 |
vinegar | -0.015 |
fault | -0.015 |
shampoo | -0.015 |
L | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
shampoo | +0.053 |
fault | +0.052 |
vinegar | +0.051 |
common | +0.050 |
L | +0.049 |
Neg logit contributions | |
pole | -0.050 |
warrior | -0.048 |
emaker | -0.048 |
ickets | -0.046 |
ados | -0.045 |
Token | had |
Token ID | 550 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
fault | +0.065 |
shampoo | +0.064 |
vinegar | +0.063 |
bruises | +0.059 |
common | +0.059 |
Neg logit contributions | |
pole | -0.084 |
warrior | -0.082 |
emaker | -0.082 |
stone | -0.079 |
King | -0.077 |
Token | helped |
Token ID | 4193 |
Feature activation | -4.30e-03 |
Pos logit contributions | |
vinegar | +0.049 |
shampoo | +0.049 |
fault | +0.049 |
ours | +0.046 |
L | +0.045 |
Neg logit contributions | |
pole | -0.056 |
warrior | -0.053 |
emaker | -0.052 |
stone | -0.051 |
ickets | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
pole | +0.006 |
emaker | +0.006 |
warrior | +0.006 |
ickets | +0.006 |
ados | +0.006 |
Neg logit contributions | |
shampoo | -0.007 |
fault | -0.006 |
vinegar | -0.006 |
common | -0.006 |
L | -0.006 |
Token | find |
Token ID | 1064 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
warrior | +0.028 |
pole | +0.027 |
King | +0.026 |
stone | +0.026 |
kingdom | +0.025 |
Neg logit contributions | |
vinegar | -0.043 |
shampoo | -0.041 |
ours | -0.040 |
bruises | -0.040 |
fault | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
pole | +0.036 |
warrior | +0.034 |
emaker | +0.034 |
ados | +0.033 |
stone | +0.033 |
Neg logit contributions | |
shampoo | -0.035 |
fault | -0.034 |
vinegar | -0.034 |
common | -0.033 |
bruises | -0.032 |
Token | skipped |
Token ID | 26684 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.004 |
warrior | +0.004 |
ickets | +0.004 |
stone | +0.004 |
Neg logit contributions | |
shampoo | -0.003 |
fault | -0.003 |
vinegar | -0.003 |
common | -0.003 |
bruises | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
L | +0.008 |
shampoo | +0.008 |
common | +0.008 |
Qu | +0.007 |
their | +0.007 |
Neg logit contributions | |
emaker | -0.009 |
warrior | -0.008 |
pole | -0.008 |
ados | -0.008 |
ickets | -0.008 |
Token | skipped |
Token ID | 26684 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
fault | +0.027 |
shampoo | +0.026 |
vinegar | +0.026 |
common | +0.025 |
bruises | +0.025 |
Neg logit contributions | |
pole | -0.031 |
emaker | -0.030 |
warrior | -0.030 |
ickets | -0.029 |
stone | -0.029 |
Token | until |
Token ID | 1566 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
L | +0.007 |
shampoo | +0.006 |
common | +0.006 |
Qu | +0.006 |
their | +0.006 |
Neg logit contributions | |
emaker | -0.006 |
pole | -0.006 |
warrior | -0.006 |
ados | -0.006 |
ickets | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
fault | +0.034 |
shampoo | +0.032 |
bruises | +0.031 |
vinegar | +0.031 |
aj | +0.030 |
Neg logit contributions | |
pole | -0.051 |
emaker | -0.050 |
warrior | -0.049 |
ados | -0.048 |
ickets | -0.048 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
shampoo | +0.018 |
fault | +0.017 |
vinegar | +0.017 |
common | +0.016 |
L | +0.016 |
Neg logit contributions | |
pole | -0.023 |
emaker | -0.022 |
warrior | -0.022 |
ickets | -0.021 |
ados | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
aj | +0.055 |
common | +0.049 |
bruises | +0.048 |
ucker | +0.048 |
omo | +0.048 |
Neg logit contributions | |
Charlie | -0.038 |
King | -0.036 |
down | -0.035 |
pole | -0.035 |
around | -0.035 |
Token | boat |
Token ID | 8848 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
pole | +0.021 |
warrior | +0.020 |
eagle | +0.019 |
ickets | +0.018 |
King | +0.018 |
Neg logit contributions | |
bruises | -0.030 |
L | -0.030 |
shampoo | -0.030 |
fault | -0.030 |
vinegar | -0.029 |
Token | again |
Token ID | 757 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
fault | +0.014 |
shampoo | +0.014 |
vinegar | +0.013 |
bruises | +0.013 |
common | +0.013 |
Neg logit contributions | |
pole | -0.012 |
stone | -0.010 |
emaker | -0.010 |
warrior | -0.010 |
ickets | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
fault | +0.087 |
shampoo | +0.084 |
vinegar | +0.083 |
bruises | +0.083 |
ses | +0.077 |
Neg logit contributions | |
pole | -0.057 |
warrior | -0.051 |
stone | -0.050 |
down | -0.050 |
ickets | -0.048 |
Token | " |
Token ID | 366 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
shampoo | +0.004 |
fault | +0.004 |
vinegar | +0.004 |
L | +0.004 |
common | +0.004 |
Neg logit contributions | |
pole | -0.006 |
emaker | -0.005 |
warrior | -0.005 |
ickets | -0.005 |
ados | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
pole | +0.056 |
emaker | +0.054 |
warrior | +0.053 |
ickets | +0.052 |
ados | +0.051 |
Neg logit contributions | |
shampoo | -0.049 |
fault | -0.048 |
L | -0.047 |
vinegar | -0.046 |
common | -0.046 |
Token | she |
Token ID | 673 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
shampoo | +0.031 |
fault | +0.030 |
L | +0.030 |
common | +0.029 |
vinegar | +0.029 |
Neg logit contributions | |
pole | -0.028 |
warrior | -0.027 |
emaker | -0.026 |
ickets | -0.026 |
ados | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.004 |
warrior | +0.004 |
ados | +0.004 |
ickets | +0.004 |
Neg logit contributions | |
shampoo | -0.002 |
L | -0.002 |
fault | -0.002 |
vinegar | -0.002 |
common | -0.002 |
Token | able |
Token ID | 1498 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
shampoo | +0.064 |
fault | +0.062 |
L | +0.061 |
bruises | +0.059 |
ruined | +0.059 |
Neg logit contributions | |
pole | -0.048 |
warrior | -0.048 |
ickets | -0.046 |
emaker | -0.046 |
ados | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -8.19e-04 |
Pos logit contributions | |
pole | +0.078 |
emaker | +0.075 |
warrior | +0.075 |
ickets | +0.072 |
ados | +0.072 |
Neg logit contributions | |
shampoo | -0.071 |
fault | -0.069 |
vinegar | -0.068 |
common | -0.067 |
L | -0.066 |
Token | visit |
Token ID | 3187 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
pole | +0.001 |
emaker | +0.001 |
warrior | +0.001 |
ados | +0.001 |
ickets | +0.001 |
Neg logit contributions | |
shampoo | -0.001 |
fault | -0.001 |
common | -0.001 |
L | -0.001 |
vinegar | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
shampoo | +0.013 |
fault | +0.013 |
vinegar | +0.012 |
common | +0.012 |
bruises | +0.012 |
Neg logit contributions | |
pole | -0.013 |
warrior | -0.013 |
emaker | -0.013 |
ados | -0.012 |
ickets | -0.012 |
Token | library |
Token ID | 5888 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
pole | +0.037 |
emaker | +0.036 |
warrior | +0.035 |
ickets | +0.035 |
ados | +0.034 |
Neg logit contributions | |
shampoo | -0.025 |
fault | -0.024 |
L | -0.024 |
common | -0.023 |
vinegar | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
shampoo | +0.076 |
fault | +0.075 |
L | +0.073 |
common | +0.072 |
vinegar | +0.071 |
Neg logit contributions | |
pole | -0.078 |
emaker | -0.077 |
warrior | -0.076 |
ickets | -0.074 |
ados | -0.073 |
Token | find |
Token ID | 1064 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
pole | +0.010 |
warrior | +0.009 |
emaker | +0.009 |
King | +0.009 |
stone | +0.009 |
Neg logit contributions | |
fault | -0.012 |
vinegar | -0.012 |
shampoo | -0.012 |
common | -0.012 |
bruises | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
pole | +0.083 |
emaker | +0.080 |
warrior | +0.080 |
ados | +0.077 |
stone | +0.077 |
Neg logit contributions | |
fault | -0.067 |
shampoo | -0.067 |
vinegar | -0.066 |
common | -0.065 |
bruises | -0.063 |
Token | immediately |
Token ID | 3393 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
pole | +0.063 |
warrior | +0.060 |
emaker | +0.060 |
ickets | +0.058 |
stone | +0.058 |
Neg logit contributions | |
shampoo | -0.054 |
fault | -0.053 |
vinegar | -0.051 |
common | -0.051 |
bruises | -0.050 |
Token | hung |
Token ID | 9174 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
fault | +0.038 |
shampoo | +0.036 |
vinegar | +0.036 |
common | +0.035 |
bruises | +0.034 |
Neg logit contributions | |
pole | -0.038 |
warrior | -0.037 |
stone | -0.036 |
emaker | -0.035 |
person | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
pole | +0.008 |
emaker | +0.008 |
warrior | +0.008 |
ickets | +0.008 |
ados | +0.007 |
Neg logit contributions | |
shampoo | -0.008 |
fault | -0.007 |
L | -0.007 |
vinegar | -0.007 |
common | -0.007 |
Token | h |
Token ID | 289 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
pole | +0.052 |
warrior | +0.051 |
stone | +0.051 |
emaker | +0.049 |
eagle | +0.047 |
Neg logit contributions | |
fault | -0.065 |
common | -0.063 |
vinegar | -0.063 |
shampoo | -0.062 |
Qu | -0.060 |
Token | anger |
Token ID | 2564 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
pole | +0.027 |
warrior | +0.026 |
emaker | +0.025 |
ados | +0.024 |
ickets | +0.024 |
Neg logit contributions | |
shampoo | -0.028 |
fault | -0.027 |
L | -0.027 |
vinegar | -0.026 |
bruises | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
warrior | +0.007 |
emaker | +0.007 |
ickets | +0.007 |
umbo | +0.006 |
ados | +0.006 |
Neg logit contributions | |
shampoo | -0.008 |
fault | -0.008 |
L | -0.008 |
ruined | -0.007 |
bruises | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.014 |
emaker | +0.014 |
ados | +0.013 |
King | +0.013 |
Neg logit contributions | |
fault | -0.015 |
shampoo | -0.015 |
vinegar | -0.014 |
aj | -0.014 |
bruises | -0.014 |
Token | wall |
Token ID | 3355 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
pole | +0.002 |
emaker | +0.002 |
warrior | +0.002 |
ickets | +0.002 |
ados | +0.002 |
Neg logit contributions | |
shampoo | -0.003 |
fault | -0.003 |
vinegar | -0.003 |
common | -0.003 |
L | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
shampoo | +0.003 |
fault | +0.003 |
vinegar | +0.003 |
common | +0.003 |
L | +0.003 |
Neg logit contributions | |
pole | -0.003 |
emaker | -0.003 |
warrior | -0.003 |
ickets | -0.003 |
ados | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.004 |
warrior | +0.004 |
ickets | +0.004 |
stone | +0.004 |
Neg logit contributions | |
shampoo | -0.005 |
fault | -0.005 |
L | -0.005 |
vinegar | -0.005 |
common | -0.005 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
pole | +0.010 |
warrior | +0.009 |
stone | +0.009 |
emaker | +0.009 |
King | +0.009 |
Neg logit contributions | |
fault | -0.009 |
vinegar | -0.008 |
common | -0.008 |
shampoo | -0.008 |
bruises | -0.008 |
Token | can |
Token ID | 460 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
fault | +0.029 |
shampoo | +0.029 |
vinegar | +0.029 |
bruises | +0.029 |
common | +0.027 |
Neg logit contributions | |
pole | -0.041 |
warrior | -0.040 |
emaker | -0.039 |
ickets | -0.038 |
umbo | -0.037 |
Token | take |
Token ID | 1011 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
shampoo | +0.057 |
fault | +0.055 |
common | +0.053 |
L | +0.053 |
vinegar | +0.052 |
Neg logit contributions | |
pole | -0.064 |
emaker | -0.062 |
warrior | -0.062 |
ados | -0.060 |
ickets | -0.059 |
Token | care |
Token ID | 1337 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ados | +0.038 |
warrior | +0.038 |
pole | +0.036 |
emaker | +0.036 |
King | +0.035 |
Neg logit contributions | |
fault | -0.041 |
vinegar | -0.039 |
ses | -0.038 |
aj | -0.038 |
bruises | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
pole | +0.035 |
emaker | +0.033 |
warrior | +0.033 |
ickets | +0.032 |
stone | +0.031 |
Neg logit contributions | |
shampoo | -0.068 |
fault | -0.068 |
vinegar | -0.066 |
common | -0.066 |
bruises | -0.064 |
Token | him |
Token ID | 683 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
fault | +0.021 |
outed | +0.021 |
vinegar | +0.021 |
aj | +0.021 |
ses | +0.020 |
Neg logit contributions | |
pole | -0.013 |
warrior | -0.013 |
Charlie | -0.013 |
ados | -0.013 |
King | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
shampoo | +0.034 |
vinegar | +0.034 |
fault | +0.034 |
common | +0.033 |
bruises | +0.033 |
Neg logit contributions | |
pole | -0.028 |
warrior | -0.026 |
emaker | -0.025 |
ados | -0.025 |
ickets | -0.025 |
Token | â |
Token ID | 22940 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
pole | +0.015 |
warrior | +0.015 |
ickets | +0.014 |
emaker | +0.014 |
umbo | +0.014 |
Neg logit contributions | |
fault | -0.020 |
shampoo | -0.019 |
vinegar | -0.019 |
common | -0.019 |
bruises | -0.019 |
Token | € |
Token ID | 26391 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
shampoo | +0.010 |
common | +0.010 |
fault | +0.010 |
vinegar | +0.010 |
L | +0.010 |
Neg logit contributions | |
pole | -0.009 |
warrior | -0.009 |
emaker | -0.009 |
ados | -0.009 |
ickets | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
shampoo | +0.013 |
fault | +0.012 |
vinegar | +0.012 |
common | +0.012 |
L | +0.012 |
Neg logit contributions | |
pole | -0.013 |
emaker | -0.012 |
warrior | -0.012 |
ickets | -0.012 |
ados | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
fault | +0.018 |
ses | +0.017 |
vinegar | +0.017 |
ruined | +0.016 |
shampoo | +0.016 |
Neg logit contributions | |
ickets | -0.011 |
pole | -0.010 |
on | -0.010 |
oon | -0.010 |
he | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
fault | +0.007 |
ses | +0.006 |
vinegar | +0.006 |
shampoo | +0.006 |
common | +0.006 |
Neg logit contributions | |
pole | -0.004 |
ickets | -0.004 |
warrior | -0.004 |
emaker | -0.004 |
quet | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
vinegar | +0.000 |
shampoo | +0.000 |
fault | +0.000 |
aj | +0.000 |
ours | +0.000 |
Neg logit contributions | |
warrior | -0.000 |
pole | -0.000 |
ados | -0.000 |
emaker | -0.000 |
stone | -0.000 |
Token | long |
Token ID | 890 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
shampoo | +0.031 |
common | +0.030 |
cheaper | +0.029 |
gas | +0.029 |
L | +0.028 |
Neg logit contributions | |
emaker | -0.033 |
ickets | -0.032 |
ados | -0.032 |
anes | -0.030 |
pole | -0.029 |
Token | journey |
Token ID | 7002 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ickets | +0.027 |
ados | +0.026 |
emaker | +0.026 |
anes | +0.025 |
umbo | +0.025 |
Neg logit contributions | |
common | -0.028 |
shampoo | -0.028 |
L | -0.026 |
gas | -0.025 |
scratches | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
emaker | +0.031 |
warrior | +0.030 |
ickets | +0.030 |
pole | +0.030 |
ados | +0.029 |
Neg logit contributions | |
shampoo | -0.025 |
fault | -0.025 |
L | -0.025 |
common | -0.024 |
bruises | -0.023 |
Token | find |
Token ID | 1064 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
fault | +0.038 |
shampoo | +0.038 |
vinegar | +0.037 |
aj | +0.036 |
bruises | +0.036 |
Neg logit contributions | |
pole | -0.019 |
warrior | -0.018 |
emaker | -0.017 |
stone | -0.016 |
King | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
pole | +0.079 |
warrior | +0.076 |
emaker | +0.075 |
ados | +0.073 |
stone | +0.073 |
Neg logit contributions | |
shampoo | -0.058 |
fault | -0.058 |
vinegar | -0.055 |
common | -0.055 |
bruises | -0.053 |
Token | magical |
Token ID | 10883 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
pole | +0.038 |
emaker | +0.037 |
warrior | +0.036 |
ickets | +0.035 |
ados | +0.034 |
Neg logit contributions | |
shampoo | -0.066 |
fault | -0.065 |
vinegar | -0.064 |
common | -0.063 |
L | -0.063 |
Token | sword |
Token ID | 8429 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
shampoo | +0.014 |
fault | +0.014 |
common | +0.013 |
vinegar | +0.013 |
L | +0.013 |
Neg logit contributions | |
pole | -0.007 |
emaker | -0.007 |
ickets | -0.006 |
ados | -0.006 |
warrior | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
shampoo | +0.016 |
fault | +0.015 |
vinegar | +0.015 |
common | +0.015 |
L | +0.015 |
Neg logit contributions | |
pole | -0.017 |
warrior | -0.016 |
emaker | -0.016 |
ickets | -0.015 |
stone | -0.015 |
Token | Along |
Token ID | 17159 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
shampoo | +0.005 |
fault | +0.005 |
vinegar | +0.005 |
common | +0.005 |
L | +0.005 |
Neg logit contributions | |
pole | -0.005 |
emaker | -0.005 |
warrior | -0.005 |
ickets | -0.004 |
ados | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
pole | +0.021 |
emaker | +0.020 |
warrior | +0.020 |
ickets | +0.019 |
ados | +0.019 |
Neg logit contributions | |
shampoo | -0.018 |
fault | -0.017 |
vinegar | -0.017 |
bruises | -0.016 |
common | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
pole | +0.045 |
warrior | +0.044 |
emaker | +0.043 |
ickets | +0.042 |
ados | +0.042 |
Neg logit contributions | |
fault | -0.042 |
shampoo | -0.041 |
vinegar | -0.040 |
common | -0.039 |
bruises | -0.039 |
Token | but |
Token ID | 475 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
pole | +0.025 |
warrior | +0.023 |
ickets | +0.023 |
emaker | +0.022 |
stone | +0.022 |
Neg logit contributions | |
shampoo | -0.031 |
fault | -0.031 |
vinegar | -0.030 |
common | -0.030 |
bruises | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
pole | +0.064 |
warrior | +0.060 |
emaker | +0.060 |
ados | +0.057 |
stone | +0.056 |
Neg logit contributions | |
shampoo | -0.079 |
fault | -0.079 |
vinegar | -0.077 |
common | -0.076 |
bruises | -0.074 |
Token | didn |
Token ID | 1422 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
pole | +0.010 |
warrior | +0.010 |
emaker | +0.010 |
eagle | +0.010 |
orn | +0.010 |
Neg logit contributions | |
fault | -0.008 |
vinegar | -0.008 |
common | -0.008 |
shampoo | -0.008 |
bruises | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
pole | +0.012 |
warrior | +0.012 |
emaker | +0.011 |
ados | +0.011 |
stone | +0.011 |
Neg logit contributions | |
shampoo | -0.015 |
fault | -0.014 |
L | -0.014 |
common | -0.014 |
vinegar | -0.014 |
Token | know |
Token ID | 760 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
ados | +0.036 |
pole | +0.035 |
ickets | +0.034 |
stone | +0.033 |
quet | +0.033 |
Neg logit contributions | |
L | -0.012 |
common | -0.011 |
Sara | -0.010 |
shampoo | -0.010 |
don | -0.009 |
Token | how |
Token ID | 703 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
pole | +0.052 |
emaker | +0.050 |
stone | +0.048 |
ados | +0.047 |
owl | +0.047 |
Neg logit contributions | |
common | -0.048 |
ses | -0.044 |
aj | -0.044 |
shampoo | -0.044 |
fault | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
shampoo | +0.024 |
vinegar | +0.023 |
fault | +0.023 |
common | +0.023 |
bruises | +0.022 |
Neg logit contributions | |
pole | -0.018 |
warrior | -0.018 |
emaker | -0.018 |
stone | -0.018 |
ados | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
shampoo | +0.032 |
common | +0.032 |
L | +0.032 |
Sara | +0.029 |
gas | +0.028 |
Neg logit contributions | |
ados | -0.055 |
emaker | -0.051 |
pole | -0.051 |
umbo | -0.050 |
warrior | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
fault | +0.001 |
shampoo | +0.001 |
L | +0.001 |
common | +0.001 |
vinegar | +0.001 |
Neg logit contributions | |
emaker | -0.002 |
pole | -0.002 |
warrior | -0.002 |
ickets | -0.002 |
stone | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
shampoo | +0.014 |
fault | +0.014 |
vinegar | +0.014 |
bruises | +0.013 |
common | +0.013 |
Neg logit contributions | |
pole | -0.015 |
emaker | -0.014 |
ickets | -0.014 |
warrior | -0.014 |
umbo | -0.014 |
Token | making |
Token ID | 1642 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
common | +0.026 |
fault | +0.026 |
vinegar | +0.024 |
shampoo | +0.024 |
aj | +0.024 |
Neg logit contributions | |
pole | -0.019 |
warrior | -0.016 |
down | -0.016 |
ados | -0.016 |
Charlie | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
pole | +0.029 |
ados | +0.028 |
ickets | +0.027 |
stone | +0.027 |
warrior | +0.027 |
Neg logit contributions | |
common | -0.028 |
fault | -0.027 |
aj | -0.026 |
vinegar | -0.026 |
shampoo | -0.026 |
Token | rum |
Token ID | 7440 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
pole | +0.032 |
warrior | +0.030 |
emaker | +0.029 |
ickets | +0.029 |
stone | +0.029 |
Neg logit contributions | |
shampoo | -0.035 |
fault | -0.035 |
vinegar | -0.034 |
common | -0.034 |
bruises | -0.033 |
Token | ble |
Token ID | 903 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
shampoo | +0.028 |
fault | +0.027 |
vinegar | +0.027 |
L | +0.027 |
bruises | +0.026 |
Neg logit contributions | |
pole | -0.016 |
warrior | -0.016 |
emaker | -0.015 |
ickets | -0.015 |
ados | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
emaker | +0.035 |
warrior | +0.035 |
pole | +0.034 |
umbo | +0.033 |
ickets | +0.033 |
Neg logit contributions | |
shampoo | -0.035 |
fault | -0.033 |
L | -0.032 |
vinegar | -0.032 |
ruined | -0.030 |
Token | wh |
Token ID | 348 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
fault | +0.017 |
common | +0.017 |
shampoo | +0.015 |
vinegar | +0.015 |
aj | +0.015 |
Neg logit contributions | |
pole | -0.013 |
down | -0.013 |
forth | -0.012 |
around | -0.011 |
stone | -0.011 |
Token | ir |
Token ID | 343 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.004 |
warrior | +0.004 |
ickets | +0.004 |
ados | +0.003 |
Neg logit contributions | |
shampoo | -0.004 |
fault | -0.004 |
vinegar | -0.004 |
L | -0.004 |
common | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
warrior | +0.010 |
pole | +0.009 |
emaker | +0.009 |
ickets | +0.008 |
ados | +0.008 |
Neg logit contributions | |
fault | -0.021 |
shampoo | -0.021 |
L | -0.020 |
vinegar | -0.020 |
common | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
shampoo | +0.023 |
L | +0.023 |
fault | +0.023 |
common | +0.022 |
vinegar | +0.021 |
Neg logit contributions | |
emaker | -0.030 |
pole | -0.030 |
warrior | -0.030 |
ickets | -0.028 |
stone | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
shampoo | +0.024 |
fault | +0.023 |
vinegar | +0.022 |
common | +0.022 |
L | +0.022 |
Neg logit contributions | |
pole | -0.037 |
emaker | -0.036 |
warrior | -0.036 |
ickets | -0.035 |
ados | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
shampoo | +0.021 |
common | +0.020 |
L | +0.020 |
bruises | +0.019 |
ruined | +0.018 |
Neg logit contributions | |
pole | -0.020 |
emaker | -0.020 |
ados | -0.020 |
warrior | -0.020 |
umbo | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
pole | +0.005 |
warrior | +0.005 |
emaker | +0.004 |
stone | +0.004 |
ados | +0.004 |
Neg logit contributions | |
shampoo | -0.005 |
fault | -0.005 |
vinegar | -0.005 |
bruises | -0.005 |
common | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
pole | +0.029 |
warrior | +0.028 |
ickets | +0.028 |
emaker | +0.027 |
ados | +0.026 |
Neg logit contributions | |
fault | -0.035 |
shampoo | -0.034 |
common | -0.034 |
vinegar | -0.033 |
ruined | -0.032 |
Token | want |
Token ID | 765 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
warrior | +0.004 |
around | +0.004 |
est | +0.004 |
pole | +0.004 |
age | +0.004 |
Neg logit contributions | |
bruises | -0.007 |
vinegar | -0.006 |
aj | -0.006 |
shampoo | -0.006 |
injuries | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ados | +0.059 |
ickets | +0.059 |
pole | +0.059 |
trolls | +0.058 |
owl | +0.057 |
Neg logit contributions | |
fault | -0.097 |
common | -0.095 |
aj | -0.095 |
ses | -0.092 |
ours | -0.091 |
Token | help |
Token ID | 1037 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
pole | +0.017 |
owl | +0.017 |
ickets | +0.017 |
warrior | +0.017 |
King | +0.016 |
Neg logit contributions | |
ours | -0.030 |
outed | -0.028 |
vinegar | -0.028 |
fault | -0.028 |
aj | -0.027 |
Token | all |
Token ID | 477 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
pole | +0.020 |
warrior | +0.019 |
emaker | +0.019 |
umbo | +0.018 |
stone | +0.018 |
Neg logit contributions | |
shampoo | -0.018 |
L | -0.018 |
vinegar | -0.017 |
common | -0.016 |
fault | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
pole | +0.130 |
warrior | +0.127 |
emaker | +0.125 |
ados | +0.120 |
ickets | +0.120 |
Neg logit contributions | |
shampoo | -0.115 |
L | -0.108 |
fault | -0.108 |
vinegar | -0.108 |
common | -0.107 |
Token | animals |
Token ID | 4695 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
pole | +0.009 |
warrior | +0.008 |
ados | +0.008 |
emaker | +0.008 |
ickets | +0.008 |
Neg logit contributions | |
fault | -0.016 |
shampoo | -0.016 |
vinegar | -0.015 |
common | -0.015 |
bruises | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
pole | +0.018 |
warrior | +0.017 |
emaker | +0.017 |
ickets | +0.016 |
ados | +0.016 |
Neg logit contributions | |
shampoo | -0.018 |
fault | -0.018 |
vinegar | -0.017 |
common | -0.017 |
bruises | -0.017 |
Token | even |
Token ID | 772 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
pole | +0.019 |
warrior | +0.017 |
owl | +0.017 |
ickets | +0.017 |
King | +0.017 |
Neg logit contributions | |
fault | -0.025 |
common | -0.025 |
vinegar | -0.025 |
ours | -0.024 |
shampoo | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
warrior | +0.013 |
pole | +0.013 |
owl | +0.012 |
down | +0.012 |
stone | +0.012 |
Neg logit contributions | |
fault | -0.021 |
aj | -0.019 |
ses | -0.019 |
omo | -0.019 |
outed | -0.018 |
Token | are |
Token ID | 389 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
pole | +0.014 |
warrior | +0.014 |
emaker | +0.014 |
ickets | +0.014 |
stone | +0.013 |
Neg logit contributions | |
fault | -0.012 |
shampoo | -0.012 |
vinegar | -0.012 |
common | -0.011 |
bruises | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
pole | +0.024 |
warrior | +0.023 |
emaker | +0.022 |
ickets | +0.022 |
ados | +0.021 |
Neg logit contributions | |
shampoo | -0.022 |
fault | -0.022 |
vinegar | -0.021 |
common | -0.021 |
L | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
ickets | +0.012 |
ados | +0.012 |
warrior | +0.012 |
pole | +0.011 |
trolls | +0.011 |
Neg logit contributions | |
fault | -0.017 |
shampoo | -0.017 |
common | -0.017 |
vinegar | -0.016 |
cheaper | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
ickets | +0.003 |
Everyone | +0.003 |
Everybody | +0.003 |
amber | +0.003 |
Charlie | +0.003 |
Neg logit contributions | |
fault | -0.007 |
rou | -0.007 |
ruined | -0.007 |
bruises | -0.007 |
cheaper | -0.006 |
Token | are |
Token ID | 389 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
pole | +0.017 |
warrior | +0.017 |
emaker | +0.016 |
ickets | +0.016 |
stone | +0.016 |
Neg logit contributions | |
shampoo | -0.011 |
fault | -0.011 |
vinegar | -0.010 |
common | -0.010 |
bruises | -0.010 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
pole | +0.015 |
warrior | +0.014 |
emaker | +0.014 |
ickets | +0.013 |
ados | +0.013 |
Neg logit contributions | |
shampoo | -0.015 |
fault | -0.015 |
vinegar | -0.014 |
common | -0.014 |
bruises | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
pole | +0.121 |
emaker | +0.117 |
warrior | +0.117 |
ickets | +0.113 |
ados | +0.112 |
Neg logit contributions | |
shampoo | -0.089 |
fault | -0.087 |
L | -0.083 |
vinegar | -0.083 |
common | -0.083 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
ickets | +0.007 |
Everyone | +0.006 |
Everybody | +0.006 |
Charlie | +0.006 |
amber | +0.006 |
Neg logit contributions | |
fault | -0.015 |
rou | -0.014 |
ruined | -0.014 |
bruises | -0.013 |
cheaper | -0.013 |
Token | L |
Token ID | 43 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
fault | +0.003 |
shampoo | +0.003 |
vinegar | +0.003 |
bruises | +0.003 |
common | +0.003 |
Neg logit contributions | |
pole | -0.004 |
emaker | -0.004 |
ickets | -0.004 |
warrior | -0.004 |
ados | -0.004 |
Token | ily |
Token ID | 813 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
shampoo | +0.021 |
fault | +0.020 |
vinegar | +0.019 |
L | +0.019 |
common | +0.018 |
Neg logit contributions | |
pole | -0.049 |
warrior | -0.048 |
emaker | -0.048 |
ickets | -0.047 |
ados | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
shampoo | +0.017 |
fault | +0.017 |
L | +0.016 |
vinegar | +0.016 |
common | +0.016 |
Neg logit contributions | |
pole | -0.021 |
emaker | -0.020 |
warrior | -0.020 |
ickets | -0.020 |
ados | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
shampoo | +0.071 |
L | +0.067 |
fault | +0.067 |
common | +0.067 |
vinegar | +0.067 |
Neg logit contributions | |
pole | -0.055 |
emaker | -0.051 |
warrior | -0.051 |
ados | -0.051 |
ickets | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
L | +0.004 |
common | +0.003 |
shampoo | +0.003 |
gas | +0.003 |
their | +0.003 |
Neg logit contributions | |
pole | -0.005 |
emaker | -0.005 |
ickets | -0.005 |
umb | -0.005 |
quet | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
pole | +0.037 |
emaker | +0.036 |
warrior | +0.036 |
ickets | +0.035 |
ados | +0.034 |
Neg logit contributions | |
shampoo | -0.047 |
fault | -0.046 |
vinegar | -0.045 |
common | -0.045 |
L | -0.044 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
warrior | +0.022 |
pole | +0.022 |
emaker | +0.021 |
ickets | +0.021 |
trolls | +0.020 |
Neg logit contributions | |
shampoo | -0.017 |
fault | -0.017 |
vinegar | -0.016 |
bruises | -0.016 |
common | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
fault | +0.025 |
aj | +0.024 |
common | +0.023 |
ucker | +0.023 |
ours | +0.022 |
Neg logit contributions | |
King | -0.020 |
Charlie | -0.020 |
on | -0.019 |
owl | -0.019 |
warrior | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
warrior | +0.026 |
pole | +0.025 |
eagle | +0.023 |
King | +0.023 |
stone | +0.023 |
Neg logit contributions | |
fault | -0.034 |
bruises | -0.032 |
shampoo | -0.031 |
vinegar | -0.031 |
common | -0.030 |
Token | building |
Token ID | 2615 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
pole | +0.097 |
emaker | +0.095 |
ickets | +0.094 |
warrior | +0.087 |
ados | +0.086 |
Neg logit contributions | |
shampoo | -0.112 |
vinegar | -0.105 |
L | -0.105 |
fault | -0.103 |
common | -0.102 |
Token | far |
Token ID | 1290 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
pole | +0.024 |
emaker | +0.023 |
warrior | +0.023 |
ickets | +0.022 |
ados | +0.022 |
Neg logit contributions | |
shampoo | -0.029 |
fault | -0.028 |
vinegar | -0.028 |
L | -0.027 |
common | -0.027 |
Token | away |
Token ID | 1497 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
pole | +0.035 |
emaker | +0.035 |
ickets | +0.034 |
warrior | +0.034 |
ados | +0.033 |
Neg logit contributions | |
shampoo | -0.060 |
common | -0.058 |
L | -0.057 |
vinegar | -0.056 |
fault | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
pole | +0.090 |
emaker | +0.086 |
warrior | +0.086 |
ickets | +0.083 |
ados | +0.082 |
Neg logit contributions | |
shampoo | -0.083 |
fault | -0.081 |
vinegar | -0.079 |
common | -0.079 |
L | -0.078 |
Token | It |
Token ID | 632 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
emaker | +0.030 |
pole | +0.029 |
warrior | +0.027 |
ickets | +0.027 |
stone | +0.027 |
Neg logit contributions | |
L | -0.023 |
shampoo | -0.022 |
gas | -0.022 |
vinegar | -0.022 |
bruises | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
fault | +0.058 |
shampoo | +0.058 |
vinegar | +0.056 |
common | +0.056 |
bruises | +0.056 |
Neg logit contributions | |
pole | -0.051 |
emaker | -0.044 |
ados | -0.043 |
ickets | -0.043 |
down | -0.043 |
Token | They |
Token ID | 1119 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
bruises | +0.016 |
ruined | +0.015 |
swollen | +0.014 |
fault | +0.014 |
rou | +0.014 |
Neg logit contributions | |
around | -0.011 |
down | -0.011 |
amber | -0.011 |
Everybody | -0.010 |
Everyone | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
pole | +0.009 |
warrior | +0.009 |
emaker | +0.008 |
umbo | +0.008 |
ickets | +0.008 |
Neg logit contributions | |
fault | -0.007 |
vinegar | -0.007 |
shampoo | -0.007 |
common | -0.006 |
bruises | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
aj | +0.016 |
common | +0.015 |
ucker | +0.014 |
injuries | +0.014 |
fault | +0.013 |
Neg logit contributions | |
owl | -0.010 |
eagle | -0.010 |
down | -0.009 |
pole | -0.009 |
ados | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
pole | +0.024 |
warrior | +0.023 |
stone | +0.022 |
emaker | +0.022 |
eagle | +0.021 |
Neg logit contributions | |
fault | -0.029 |
shampoo | -0.027 |
vinegar | -0.027 |
bruises | -0.027 |
common | -0.026 |
Token | pile |
Token ID | 14540 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
pole | +0.092 |
emaker | +0.091 |
ickets | +0.089 |
warrior | +0.085 |
ados | +0.083 |
Neg logit contributions | |
shampoo | -0.106 |
vinegar | -0.100 |
L | -0.099 |
fault | -0.097 |
common | -0.097 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
warrior | +0.102 |
pole | +0.099 |
emaker | +0.099 |
ados | +0.095 |
ickets | +0.094 |
Neg logit contributions | |
shampoo | -0.132 |
vinegar | -0.127 |
L | -0.127 |
fault | -0.123 |
bruises | -0.121 |
Token | ash |
Token ID | 12530 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
pole | +0.018 |
ados | +0.018 |
warrior | +0.018 |
mushroom | +0.017 |
stone | +0.017 |
Neg logit contributions | |
fault | -0.023 |
common | -0.021 |
aj | -0.020 |
shampoo | -0.019 |
Qu | -0.019 |
Token | near |
Token ID | 1474 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
shampoo | +0.044 |
fault | +0.043 |
vinegar | +0.043 |
L | +0.042 |
bruises | +0.040 |
Neg logit contributions | |
emaker | -0.043 |
warrior | -0.043 |
pole | -0.043 |
ickets | -0.041 |
umbo | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
aj | +0.045 |
fault | +0.043 |
disl | +0.040 |
rou | +0.039 |
ucker | +0.038 |
Neg logit contributions | |
down | -0.019 |
Charlie | -0.017 |
out | -0.017 |
through | -0.016 |
around | -0.016 |
Token | bench |
Token ID | 7624 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
pole | +0.001 |
warrior | +0.001 |
emaker | +0.001 |
stone | +0.001 |
ickets | +0.001 |
Neg logit contributions | |
fault | -0.003 |
shampoo | -0.003 |
common | -0.003 |
bruises | -0.003 |
vinegar | -0.003 |
Token | nobody |
Token ID | 8168 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
pole | +0.034 |
emaker | +0.033 |
lf | +0.032 |
King | +0.032 |
warrior | +0.031 |
Neg logit contributions | |
fault | -0.041 |
vinegar | -0.040 |
common | -0.040 |
shampoo | -0.037 |
aj | -0.036 |
Token | answered |
Token ID | 9373 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
shampoo | +0.052 |
fault | +0.052 |
vinegar | +0.050 |
common | +0.049 |
bruises | +0.048 |
Neg logit contributions | |
emaker | -0.059 |
pole | -0.059 |
warrior | -0.057 |
ickets | -0.055 |
stone | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
pole | +0.031 |
emaker | +0.030 |
ados | +0.028 |
down | +0.028 |
fully | +0.028 |
Neg logit contributions | |
fault | -0.056 |
vinegar | -0.054 |
common | -0.054 |
shampoo | -0.052 |
bruises | -0.051 |
Token | She |
Token ID | 1375 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
pole | +0.016 |
warrior | +0.015 |
emaker | +0.015 |
ados | +0.015 |
ickets | +0.014 |
Neg logit contributions | |
fault | -0.016 |
shampoo | -0.016 |
vinegar | -0.016 |
common | -0.016 |
bruises | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
pole | +0.046 |
warrior | +0.046 |
eagle | +0.045 |
stone | +0.044 |
owl | +0.043 |
Neg logit contributions | |
fault | -0.058 |
common | -0.051 |
vinegar | -0.051 |
shampoo | -0.048 |
ours | -0.047 |
Token | all |
Token ID | 477 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
common | +0.021 |
fault | +0.021 |
vinegar | +0.021 |
shampoo | +0.021 |
aj | +0.020 |
Neg logit contributions | |
pole | -0.020 |
warrior | -0.018 |
emaker | -0.018 |
King | -0.017 |
Charlie | -0.017 |
Token | alone |
Token ID | 3436 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
pole | +0.044 |
emaker | +0.034 |
warrior | +0.030 |
around | +0.028 |
stone | +0.028 |
Neg logit contributions | |
common | -0.226 |
shampoo | -0.225 |
fault | -0.224 |
aj | -0.223 |
vinegar | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
pole | +0.002 |
warrior | +0.002 |
emaker | +0.002 |
ados | +0.002 |
stone | +0.002 |
Neg logit contributions | |
shampoo | -0.004 |
fault | -0.004 |
vinegar | -0.004 |
common | -0.004 |
L | -0.003 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
pole | +0.004 |
emaker | +0.004 |
ados | +0.004 |
warrior | +0.004 |
ickets | +0.004 |
Neg logit contributions | |
vinegar | -0.006 |
shampoo | -0.006 |
fault | -0.006 |
common | -0.006 |
bruises | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
shampoo | +0.062 |
fault | +0.060 |
L | +0.059 |
vinegar | +0.058 |
common | +0.058 |
Neg logit contributions | |
pole | -0.048 |
emaker | -0.045 |
warrior | -0.045 |
ickets | -0.044 |
ados | -0.042 |
Token | it |
Token ID | 340 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
King | +0.030 |
down | +0.029 |
ados | +0.029 |
emaker | +0.029 |
Charlie | +0.029 |
Neg logit contributions | |
fault | -0.045 |
common | -0.042 |
vinegar | -0.041 |
aj | -0.040 |
ours | -0.039 |