Token | two |
Token ID | 734 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
bel | +0.061 |
op | +0.060 |
apr | +0.056 |
driver | +0.055 |
t | +0.052 |
Neg logit contributions | |
Sof | -0.067 |
Sasha | -0.063 |
Dawn | -0.063 |
Belle | -0.062 |
Sophia | -0.062 |
Token | rocks |
Token ID | 12586 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
op | +0.017 |
bel | +0.016 |
apr | +0.016 |
driver | +0.016 |
t | +0.015 |
Neg logit contributions | |
Sof | -0.020 |
igi | -0.020 |
Belle | -0.020 |
Dawn | -0.020 |
ora | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
apr | +0.056 |
x | +0.053 |
bel | +0.053 |
op | +0.050 |
Some | +0.048 |
Neg logit contributions | |
Sof | -0.058 |
igi | -0.055 |
ora | -0.055 |
Sasha | -0.055 |
Belle | -0.054 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Sof | +0.010 |
Belle | +0.010 |
Dawn | +0.010 |
igi | +0.009 |
Sasha | +0.009 |
Neg logit contributions | |
op | -0.008 |
apr | -0.008 |
bel | -0.008 |
driver | -0.008 |
t | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
Sof | +0.055 |
Dawn | +0.053 |
Belle | +0.053 |
igi | +0.053 |
Sasha | +0.052 |
Neg logit contributions | |
op | -0.048 |
bel | -0.048 |
apr | -0.047 |
driver | -0.045 |
t | -0.044 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
igi | +0.031 |
Sof | +0.030 |
ora | +0.029 |
Dawn | +0.029 |
Sasha | +0.029 |
Neg logit contributions | |
op | -0.029 |
x | -0.028 |
apr | -0.028 |
driver | -0.028 |
tools | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Sof | +0.202 |
igi | +0.196 |
ora | +0.195 |
Belle | +0.194 |
Joy | +0.191 |
Neg logit contributions | |
apr | -0.148 |
op | -0.141 |
bel | -0.139 |
x | -0.133 |
driver | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Sof | +0.028 |
Sasha | +0.026 |
Belle | +0.026 |
Dawn | +0.026 |
Sophia | +0.025 |
Neg logit contributions | |
op | -0.023 |
bel | -0.023 |
driver | -0.021 |
t | -0.021 |
laptop | -0.021 |
Token | big |
Token ID | 1263 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Sof | +0.010 |
Belle | +0.010 |
Dawn | +0.010 |
igi | +0.010 |
Sasha | +0.010 |
Neg logit contributions | |
apr | -0.007 |
op | -0.007 |
bel | -0.007 |
driver | -0.007 |
t | -0.007 |
Token | stick |
Token ID | 4859 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Sof | +0.006 |
Dawn | +0.006 |
Belle | +0.006 |
igi | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
bel | -0.005 |
op | -0.005 |
apr | -0.005 |
driver | -0.005 |
t | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Sof | +0.054 |
Sasha | +0.051 |
Belle | +0.051 |
ora | +0.050 |
igi | +0.050 |
Neg logit contributions | |
apr | -0.064 |
bel | -0.058 |
x | -0.057 |
op | -0.055 |
Some | -0.054 |
Token | nearby |
Token ID | 6716 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Sof | +0.046 |
igi | +0.046 |
Belle | +0.045 |
Dawn | +0.045 |
ora | +0.044 |
Neg logit contributions | |
op | -0.040 |
apr | -0.039 |
bel | -0.039 |
driver | -0.038 |
t | -0.036 |
Token | flower |
Token ID | 15061 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Sof | +0.011 |
igi | +0.011 |
Belle | +0.011 |
Dawn | +0.011 |
ora | +0.010 |
Neg logit contributions | |
op | -0.015 |
bel | -0.014 |
apr | -0.014 |
driver | -0.014 |
t | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Sof | +0.070 |
Belle | +0.069 |
igi | +0.069 |
Sasha | +0.068 |
ora | +0.067 |
Neg logit contributions | |
apr | -0.051 |
op | -0.050 |
bel | -0.049 |
driver | -0.048 |
x | -0.047 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Sof | +0.018 |
igi | +0.018 |
Dawn | +0.018 |
Belle | +0.018 |
ora | +0.017 |
Neg logit contributions | |
op | -0.018 |
apr | -0.017 |
bel | -0.017 |
driver | -0.017 |
t | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
igi | +0.046 |
Sof | +0.046 |
Dawn | +0.045 |
Belle | +0.045 |
ora | +0.044 |
Neg logit contributions | |
op | -0.039 |
apr | -0.038 |
bel | -0.038 |
driver | -0.035 |
t | -0.034 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
Sof | +0.041 |
igi | +0.041 |
Dawn | +0.039 |
Belle | +0.039 |
ora | +0.039 |
Neg logit contributions | |
op | -0.048 |
apr | -0.046 |
bel | -0.046 |
driver | -0.045 |
t | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Sof | +0.237 |
igi | +0.235 |
Dawn | +0.231 |
Belle | +0.231 |
ora | +0.229 |
Neg logit contributions | |
op | -0.099 |
apr | -0.094 |
bel | -0.093 |
driver | -0.088 |
t | -0.082 |
Token | it |
Token ID | 340 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Sof | +0.015 |
igi | +0.015 |
Belle | +0.015 |
Dawn | +0.015 |
Sasha | +0.015 |
Neg logit contributions | |
op | -0.013 |
bel | -0.012 |
apr | -0.012 |
driver | -0.012 |
t | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
apr | +0.021 |
op | +0.021 |
bel | +0.020 |
driver | +0.020 |
x | +0.019 |
Neg logit contributions | |
Sof | -0.029 |
Belle | -0.028 |
Dawn | -0.028 |
igi | -0.027 |
Sasha | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
op | +0.002 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
t | +0.001 |
Neg logit contributions | |
Sof | -0.002 |
igi | -0.002 |
Dawn | -0.002 |
Belle | -0.002 |
ora | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Sof | +0.005 |
igi | +0.005 |
Dawn | +0.005 |
Belle | +0.005 |
ora | +0.005 |
Neg logit contributions | |
op | -0.003 |
apr | -0.003 |
bel | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
op | +0.007 |
apr | +0.007 |
x | +0.006 |
machine | +0.006 |
driver | +0.006 |
Neg logit contributions | |
igi | -0.010 |
Sof | -0.009 |
Joy | -0.009 |
ora | -0.009 |
Dawn | -0.009 |
Token | came |
Token ID | 1625 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
igi | +0.046 |
Sof | +0.045 |
Dawn | +0.044 |
ora | +0.044 |
Belle | +0.043 |
Neg logit contributions | |
op | -0.036 |
bel | -0.033 |
t | -0.032 |
apr | -0.032 |
driver | -0.032 |
Token | over |
Token ID | 625 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
to | +0.003 |
op | +0.003 |
t | +0.002 |
His | +0.001 |
bel | +0.001 |
Neg logit contributions | |
oph | -0.022 |
igi | -0.022 |
Sof | -0.021 |
Dawn | -0.021 |
Sophia | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
to | +0.000 |
t | +0.000 |
Neg logit contributions | |
igi | -0.002 |
Dawn | -0.002 |
Sof | -0.002 |
Belle | -0.002 |
ora | -0.002 |
Token | scared |
Token ID | 12008 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
igi | +0.026 |
ora | +0.025 |
Sof | +0.025 |
oph | +0.025 |
Sasha | +0.024 |
Neg logit contributions | |
bel | -0.018 |
t | -0.017 |
to | -0.016 |
op | -0.016 |
apr | -0.016 |
Token | Cl |
Token ID | 1012 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
igi | +0.035 |
Sof | +0.034 |
ora | +0.033 |
Dawn | +0.033 |
Belle | +0.033 |
Neg logit contributions | |
op | -0.033 |
apr | -0.032 |
bel | -0.032 |
t | -0.031 |
driver | -0.031 |
Token | ucky |
Token ID | 5309 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Sof | +0.207 |
igi | +0.204 |
Belle | +0.200 |
Dawn | +0.197 |
Sasha | +0.196 |
Neg logit contributions | |
op | -0.140 |
apr | -0.118 |
bel | -0.116 |
t | -0.114 |
driver | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Sof | +0.109 |
igi | +0.106 |
Belle | +0.105 |
ora | +0.104 |
Dawn | +0.104 |
Neg logit contributions | |
apr | -0.069 |
op | -0.068 |
bel | -0.066 |
driver | -0.063 |
x | -0.061 |
Token | The |
Token ID | 383 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
igi | +0.006 |
ora | +0.005 |
Sof | +0.005 |
Belle | +0.005 |
waterfall | +0.005 |
Neg logit contributions | |
op | -0.003 |
His | -0.003 |
apr | -0.003 |
bel | -0.003 |
This | -0.003 |
Token | chicken |
Token ID | 9015 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
op | +0.022 |
apr | +0.021 |
bel | +0.021 |
driver | +0.020 |
t | +0.020 |
Neg logit contributions | |
Sof | -0.024 |
igi | -0.024 |
Dawn | -0.023 |
Belle | -0.023 |
ora | -0.023 |
Token | ran |
Token ID | 4966 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
igi | +0.032 |
Sof | +0.032 |
Dawn | +0.031 |
Belle | +0.031 |
ora | +0.031 |
Neg logit contributions | |
op | -0.030 |
bel | -0.028 |
apr | -0.028 |
t | -0.027 |
driver | -0.027 |
Token | even |
Token ID | 772 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Sof | +0.014 |
Dawn | +0.014 |
Belle | +0.013 |
Sasha | +0.013 |
Fif | +0.013 |
Neg logit contributions | |
apr | -0.012 |
bel | -0.012 |
op | -0.012 |
driver | -0.011 |
x | -0.011 |
Token | louder |
Token ID | 27089 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
op | +0.084 |
bel | +0.084 |
apr | +0.083 |
driver | +0.081 |
x | +0.079 |
Neg logit contributions | |
igi | -0.075 |
Sof | -0.074 |
Dawn | -0.072 |
Belle | -0.071 |
ora | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
apr | +0.040 |
op | +0.040 |
bel | +0.038 |
x | +0.037 |
driver | +0.036 |
Neg logit contributions | |
Sof | -0.049 |
Sasha | -0.046 |
igi | -0.046 |
Belle | -0.046 |
ora | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
op | +0.008 |
apr | +0.007 |
bel | +0.007 |
driver | +0.007 |
x | +0.007 |
Neg logit contributions | |
Sof | -0.012 |
igi | -0.011 |
Dawn | -0.011 |
Belle | -0.011 |
ora | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
op | +0.000 |
apr | +0.000 |
bel | +0.000 |
driver | +0.000 |
t | +0.000 |
Neg logit contributions | |
Sof | -0.000 |
igi | -0.000 |
Dawn | -0.000 |
Belle | -0.000 |
ora | -0.000 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
op | +0.004 |
apr | +0.004 |
bel | +0.004 |
driver | +0.004 |
x | +0.004 |
Neg logit contributions | |
Sof | -0.005 |
igi | -0.005 |
Dawn | -0.005 |
Belle | -0.005 |
ora | -0.005 |
Token | lla |
Token ID | 8466 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Belle | +0.145 |
Sasha | +0.144 |
Dawn | +0.143 |
Sof | +0.140 |
Patty | +0.135 |
Neg logit contributions | |
op | -0.191 |
t | -0.186 |
bel | -0.185 |
oscope | -0.174 |
apr | -0.168 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Sof | +0.035 |
igi | +0.034 |
Belle | +0.033 |
Dawn | +0.033 |
ora | +0.033 |
Neg logit contributions | |
op | -0.036 |
apr | -0.035 |
bel | -0.035 |
driver | -0.034 |
x | -0.032 |
Token | away |
Token ID | 1497 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
igi | +0.006 |
Sof | +0.006 |
Belle | +0.006 |
ora | +0.006 |
Dawn | +0.006 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
igi | +0.093 |
Sof | +0.092 |
Belle | +0.090 |
ora | +0.090 |
Dawn | +0.089 |
Neg logit contributions | |
op | -0.052 |
bel | -0.050 |
apr | -0.048 |
driver | -0.047 |
t | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
apr | +0.002 |
op | +0.002 |
bel | +0.002 |
x | +0.002 |
driver | +0.002 |
Neg logit contributions | |
igi | -0.004 |
ora | -0.003 |
Sof | -0.003 |
Belle | -0.003 |
Dawn | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Sof | +0.031 |
igi | +0.030 |
Dawn | +0.030 |
Belle | +0.030 |
ora | +0.030 |
Neg logit contributions | |
op | -0.026 |
bel | -0.025 |
apr | -0.024 |
driver | -0.024 |
t | -0.023 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
apr | +0.015 |
bel | +0.015 |
op | +0.014 |
x | +0.014 |
driver | +0.014 |
Neg logit contributions | |
Sof | -0.015 |
Sophia | -0.014 |
Sasha | -0.014 |
Dawn | -0.014 |
Belle | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
op | +0.045 |
bel | +0.043 |
apr | +0.042 |
driver | +0.041 |
t | +0.041 |
Neg logit contributions | |
Sof | -0.055 |
Belle | -0.053 |
Dawn | -0.052 |
ora | -0.052 |
igi | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
op | +0.018 |
bel | +0.018 |
apr | +0.017 |
driver | +0.017 |
x | +0.016 |
Neg logit contributions | |
Sof | -0.027 |
Belle | -0.025 |
ora | -0.025 |
Sasha | -0.025 |
Dawn | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
igi | +0.020 |
ora | +0.019 |
Sof | +0.018 |
Belle | +0.018 |
Dawn | +0.018 |
Neg logit contributions | |
bel | -0.017 |
op | -0.017 |
apr | -0.016 |
driver | -0.016 |
tools | -0.016 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
igi | +0.027 |
Sof | +0.027 |
Belle | +0.026 |
ora | +0.025 |
Sasha | +0.025 |
Neg logit contributions | |
tools | -0.022 |
x | -0.022 |
apr | -0.021 |
op | -0.021 |
repair | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Sof | +0.160 |
igi | +0.154 |
ora | +0.152 |
Belle | +0.152 |
Dawn | +0.152 |
Neg logit contributions | |
apr | -0.168 |
op | -0.166 |
bel | -0.161 |
driver | -0.157 |
x | -0.156 |
Token | very |
Token ID | 845 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Sof | +0.006 |
igi | +0.006 |
Dawn | +0.006 |
Belle | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
op | -0.005 |
apr | -0.005 |
bel | -0.005 |
driver | -0.005 |
t | -0.005 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
op | +0.013 |
bel | +0.013 |
apr | +0.012 |
t | +0.012 |
driver | +0.011 |
Neg logit contributions | |
igi | -0.020 |
Sof | -0.020 |
Belle | -0.020 |
Dawn | -0.020 |
Sasha | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
op | +0.004 |
apr | +0.004 |
bel | +0.004 |
driver | +0.003 |
x | +0.003 |
Neg logit contributions | |
Sof | -0.007 |
igi | -0.007 |
Dawn | -0.006 |
Belle | -0.006 |
Sasha | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
igi | +0.012 |
Sof | +0.012 |
Dawn | +0.012 |
ora | +0.012 |
Belle | +0.012 |
Neg logit contributions | |
op | -0.008 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
t | -0.007 |
Token | only |
Token ID | 691 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Sof | +0.052 |
igi | +0.052 |
Belle | +0.051 |
Sasha | +0.050 |
Dawn | +0.049 |
Neg logit contributions | |
op | -0.055 |
bel | -0.053 |
driver | -0.051 |
apr | -0.051 |
t | -0.049 |
Token | worms |
Token ID | 29174 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Sof | +0.007 |
igi | +0.007 |
Belle | +0.007 |
Dawn | +0.007 |
Sasha | +0.007 |
Neg logit contributions | |
op | -0.007 |
bel | -0.006 |
apr | -0.006 |
driver | -0.006 |
t | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
igi | +0.034 |
Sof | +0.034 |
Belle | +0.033 |
Sasha | +0.033 |
ora | +0.033 |
Neg logit contributions | |
bel | -0.030 |
apr | -0.030 |
op | -0.029 |
x | -0.028 |
drill | -0.026 |
Token | bugs |
Token ID | 11316 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
t | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
igi | -0.001 |
Belle | -0.001 |
Dawn | -0.001 |
ora | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
igi | +0.078 |
Belle | +0.077 |
Sof | +0.077 |
Joy | +0.075 |
ora | +0.074 |
Neg logit contributions | |
apr | -0.066 |
bel | -0.064 |
op | -0.064 |
x | -0.062 |
drill | -0.058 |
Token | berries |
Token ID | 36322 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
Sof | +0.018 |
igi | +0.018 |
Belle | +0.017 |
Dawn | +0.017 |
Sasha | +0.017 |
Neg logit contributions | |
op | -0.021 |
apr | -0.020 |
bel | -0.019 |
driver | -0.019 |
t | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
igi | +0.184 |
Sof | +0.181 |
Belle | +0.177 |
ora | +0.176 |
Sasha | +0.174 |
Neg logit contributions | |
apr | -0.141 |
op | -0.138 |
bel | -0.138 |
x | -0.133 |
driver | -0.127 |
Token | Do |
Token ID | 2141 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Sof | +0.013 |
igi | +0.013 |
Dawn | +0.013 |
ora | +0.012 |
Belle | +0.012 |
Neg logit contributions | |
op | -0.012 |
apr | -0.011 |
bel | -0.011 |
driver | -0.011 |
x | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
igi | +0.020 |
waterfall | +0.019 |
ora | +0.019 |
Dawn | +0.019 |
Sof | +0.019 |
Neg logit contributions | |
op | -0.012 |
t | -0.012 |
x | -0.012 |
apr | -0.012 |
His | -0.011 |
Token | promise |
Token ID | 6991 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Sof | +0.005 |
igi | +0.005 |
Belle | +0.005 |
ora | +0.005 |
Dawn | +0.005 |
Neg logit contributions | |
op | -0.008 |
bel | -0.007 |
apr | -0.007 |
driver | -0.007 |
x | -0.007 |
Token | ?" |
Token ID | 1701 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Sof | +0.093 |
igi | +0.092 |
Belle | +0.091 |
Dawn | +0.091 |
ora | +0.089 |
Neg logit contributions | |
op | -0.098 |
bel | -0.096 |
apr | -0.094 |
driver | -0.091 |
t | -0.087 |
Token | He |
Token ID | 679 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
bel | +0.006 |
apr | +0.006 |
op | +0.006 |
driver | +0.005 |
x | +0.005 |
Neg logit contributions | |
Sof | -0.009 |
Dawn | -0.009 |
Sasha | -0.009 |
Belle | -0.009 |
igi | -0.009 |
Token | cracked |
Token ID | 21368 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
op | +0.006 |
apr | +0.006 |
bel | +0.006 |
driver | +0.006 |
t | +0.005 |
Neg logit contributions | |
Sof | -0.005 |
igi | -0.005 |
Dawn | -0.005 |
Belle | -0.005 |
ora | -0.005 |
Token | open |
Token ID | 1280 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Sof | +0.008 |
Dawn | +0.008 |
Fif | +0.008 |
Sasha | +0.008 |
Belle | +0.007 |
Neg logit contributions | |
bel | -0.008 |
op | -0.008 |
t | -0.008 |
apr | -0.008 |
laptop | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Sof | +0.054 |
Dawn | +0.051 |
waterfall | +0.050 |
Sophia | +0.049 |
Sasha | +0.049 |
Neg logit contributions | |
op | -0.057 |
bel | -0.057 |
t | -0.056 |
apr | -0.052 |
oscope | -0.052 |
Token | orange |
Token ID | 10912 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
igi | +0.021 |
Sof | +0.020 |
Dawn | +0.020 |
Belle | +0.020 |
ora | +0.020 |
Neg logit contributions | |
op | -0.028 |
apr | -0.027 |
driver | -0.027 |
bel | -0.027 |
x | -0.027 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
Sof | +0.034 |
igi | +0.033 |
Dawn | +0.032 |
Belle | +0.032 |
ora | +0.032 |
Neg logit contributions | |
op | -0.048 |
apr | -0.047 |
bel | -0.047 |
driver | -0.045 |
x | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Sof | +0.195 |
igi | +0.188 |
Belle | +0.187 |
ora | +0.186 |
Sasha | +0.184 |
Neg logit contributions | |
apr | -0.131 |
bel | -0.129 |
op | -0.126 |
x | -0.117 |
headphones | -0.114 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Sof | +0.018 |
igi | +0.018 |
Dawn | +0.018 |
Belle | +0.017 |
ora | +0.017 |
Neg logit contributions | |
op | -0.018 |
apr | -0.017 |
bel | -0.017 |
driver | -0.016 |
t | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
Sof | +0.079 |
igi | +0.078 |
Dawn | +0.076 |
Belle | +0.076 |
ora | +0.075 |
Neg logit contributions | |
op | -0.087 |
apr | -0.085 |
bel | -0.084 |
driver | -0.082 |
t | -0.079 |
Token | delicious |
Token ID | 12625 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
igi | +0.003 |
Sof | +0.003 |
Belle | +0.003 |
Dawn | +0.002 |
ora | +0.002 |
Neg logit contributions | |
op | -0.003 |
apr | -0.003 |
bel | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | food |
Token ID | 2057 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
igi | +0.099 |
Sof | +0.095 |
Belle | +0.094 |
Dawn | +0.092 |
Joy | +0.092 |
Neg logit contributions | |
op | -0.101 |
apr | -0.100 |
tools | -0.097 |
x | -0.097 |
driver | -0.096 |
Token | ! |
Token ID | 0 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
t | +0.001 |
Neg logit contributions | |
igi | -0.001 |
ora | -0.001 |
Sof | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
op | +0.015 |
apr | +0.014 |
bel | +0.014 |
driver | +0.013 |
t | +0.013 |
Neg logit contributions | |
igi | -0.026 |
Sof | -0.025 |
ora | -0.025 |
Dawn | -0.025 |
Belle | -0.025 |
Token | animal |
Token ID | 5044 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
op | +0.019 |
apr | +0.018 |
bel | +0.018 |
driver | +0.017 |
t | +0.017 |
Neg logit contributions | |
Sof | -0.018 |
igi | -0.018 |
Dawn | -0.017 |
Belle | -0.017 |
ora | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Sof | +0.063 |
Dawn | +0.061 |
Belle | +0.061 |
igi | +0.060 |
ora | +0.059 |
Neg logit contributions | |
apr | -0.074 |
op | -0.074 |
driver | -0.071 |
bel | -0.071 |
x | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
igi | +0.019 |
ora | +0.019 |
Sof | +0.019 |
Dawn | +0.018 |
Belle | +0.018 |
Neg logit contributions | |
bel | -0.016 |
apr | -0.016 |
op | -0.016 |
driver | -0.015 |
tools | -0.015 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
igi | +0.021 |
Sof | +0.021 |
Dawn | +0.020 |
ora | +0.020 |
Belle | +0.020 |
Neg logit contributions | |
op | -0.023 |
apr | -0.022 |
bel | -0.022 |
x | -0.021 |
driver | -0.021 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Sof | +0.133 |
Belle | +0.129 |
igi | +0.128 |
Dawn | +0.127 |
ora | +0.125 |
Neg logit contributions | |
apr | -0.191 |
op | -0.186 |
x | -0.180 |
bel | -0.180 |
driver | -0.178 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Sof | +0.049 |
igi | +0.048 |
Dawn | +0.047 |
Belle | +0.047 |
ora | +0.046 |
Neg logit contributions | |
op | -0.064 |
apr | -0.062 |
bel | -0.062 |
driver | -0.060 |
t | -0.058 |
Token | ever |
Token ID | 1683 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Sof | +0.071 |
igi | +0.069 |
Belle | +0.068 |
Dawn | +0.068 |
ora | +0.068 |
Neg logit contributions | |
op | -0.062 |
apr | -0.061 |
bel | -0.059 |
driver | -0.058 |
x | -0.056 |
Token | after |
Token ID | 706 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
to | +0.013 |
t | +0.013 |
bel | +0.012 |
apr | +0.011 |
op | +0.011 |
Neg logit contributions | |
igi | -0.031 |
Dawn | -0.029 |
Sof | -0.028 |
Iris | -0.028 |
Fif | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
igi | +0.016 |
Sof | +0.016 |
Belle | +0.016 |
Dawn | +0.015 |
ora | +0.015 |
Neg logit contributions | |
op | -0.008 |
bel | -0.008 |
apr | -0.008 |
driver | -0.007 |
t | -0.007 |
Token | hands |
Token ID | 2832 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
op | +0.027 |
apr | +0.025 |
bel | +0.025 |
driver | +0.024 |
t | +0.023 |
Neg logit contributions | |
Sof | -0.064 |
igi | -0.063 |
Belle | -0.063 |
Dawn | -0.062 |
ora | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
apr | +0.051 |
bel | +0.050 |
op | +0.050 |
driver | +0.048 |
x | +0.048 |
Neg logit contributions | |
Sof | -0.054 |
Belle | -0.051 |
ora | -0.050 |
Sophia | -0.049 |
Joy | -0.049 |
Token | laugh |
Token ID | 6487 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
bel | +0.020 |
apr | +0.019 |
op | +0.018 |
tools | +0.018 |
driver | +0.018 |
Neg logit contributions | |
igi | -0.027 |
oph | -0.025 |
Dawn | -0.024 |
Sof | -0.024 |
ora | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Sof | +0.015 |
Belle | +0.014 |
igi | +0.014 |
Dawn | +0.014 |
ora | +0.014 |
Neg logit contributions | |
op | -0.009 |
apr | -0.008 |
bel | -0.008 |
driver | -0.008 |
x | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
igi | +0.003 |
Sof | +0.003 |
ora | +0.003 |
Dawn | +0.003 |
Joy | +0.003 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
bel | -0.002 |
Some | -0.002 |
His | -0.002 |
Token | tou |
Token ID | 2819 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
tools | +0.028 |
repair | +0.028 |
bel | +0.028 |
therm | +0.028 |
x | +0.028 |
Neg logit contributions | |
die | -0.025 |
oph | -0.024 |
Sof | -0.024 |
Sasha | -0.023 |
Joy | -0.023 |
Token | can |
Token ID | 5171 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
Sof | +0.196 |
Dawn | +0.192 |
Sasha | +0.192 |
igi | +0.188 |
Belle | +0.187 |
Neg logit contributions | |
op | -0.128 |
bel | -0.128 |
t | -0.124 |
driver | -0.120 |
apr | -0.106 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Sof | +0.037 |
igi | +0.037 |
Belle | +0.036 |
ora | +0.035 |
Dawn | +0.035 |
Neg logit contributions | |
apr | -0.028 |
op | -0.027 |
bel | -0.026 |
driver | -0.025 |
x | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
op | +0.036 |
apr | +0.034 |
bel | +0.034 |
x | +0.033 |
driver | +0.032 |
Neg logit contributions | |
igi | -0.047 |
Sof | -0.044 |
Dawn | -0.044 |
ora | -0.044 |
Belle | -0.043 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
igi | +0.043 |
Sof | +0.040 |
Sasha | +0.040 |
Dawn | +0.039 |
oph | +0.039 |
Neg logit contributions | |
bel | -0.019 |
x | -0.018 |
repair | -0.017 |
phone | -0.017 |
car | -0.017 |
Token | sound |
Token ID | 2128 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
op | +0.029 |
bel | +0.029 |
apr | +0.027 |
driver | +0.027 |
x | +0.027 |
Neg logit contributions | |
igi | -0.046 |
Sof | -0.045 |
Dawn | -0.044 |
ora | -0.044 |
Sasha | -0.043 |
Token | stem |
Token ID | 10717 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Sof | +0.074 |
igi | +0.073 |
Belle | +0.072 |
Dawn | +0.072 |
ora | +0.071 |
Neg logit contributions | |
op | -0.069 |
apr | -0.067 |
bel | -0.066 |
driver | -0.064 |
t | -0.062 |
Token | with |
Token ID | 351 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Sof | +0.044 |
igi | +0.044 |
Belle | +0.043 |
Sasha | +0.043 |
ora | +0.042 |
Neg logit contributions | |
apr | -0.044 |
x | -0.042 |
bel | -0.039 |
headphones | -0.039 |
laptop | -0.038 |
Token | leaves |
Token ID | 5667 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Sof | +0.004 |
Belle | +0.004 |
Sasha | +0.004 |
Dawn | +0.004 |
Fif | +0.004 |
Neg logit contributions | |
op | -0.005 |
bel | -0.004 |
driver | -0.004 |
laptop | -0.004 |
apr | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
Sof | +0.053 |
igi | +0.051 |
Belle | +0.051 |
Dawn | +0.050 |
Sasha | +0.050 |
Neg logit contributions | |
apr | -0.042 |
op | -0.040 |
x | -0.039 |
bel | -0.039 |
laptop | -0.036 |
Token | The |
Token ID | 383 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
bel | +0.002 |
apr | +0.002 |
op | +0.002 |
driver | +0.002 |
laptop | +0.002 |
Neg logit contributions | |
Sof | -0.004 |
Belle | -0.004 |
Dawn | -0.004 |
Sasha | -0.004 |
Fif | -0.004 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
op | +0.029 |
tools | +0.029 |
x | +0.028 |
bel | +0.028 |
repair | +0.028 |
Neg logit contributions | |
Sof | -0.023 |
igi | -0.023 |
ora | -0.022 |
Sasha | -0.022 |
Belle | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
Sof | +0.140 |
igi | +0.139 |
Belle | +0.136 |
ora | +0.134 |
Joy | +0.134 |
Neg logit contributions | |
apr | -0.179 |
op | -0.176 |
driver | -0.170 |
x | -0.169 |
bel | -0.169 |
Token | now |
Token ID | 783 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
op | +0.000 |
apr | +0.000 |
bel | +0.000 |
driver | +0.000 |
t | +0.000 |
Neg logit contributions | |
Sof | -0.000 |
igi | -0.000 |
Belle | -0.000 |
Dawn | -0.000 |
Sasha | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
op | +0.020 |
apr | +0.019 |
bel | +0.018 |
driver | +0.018 |
x | +0.018 |
Neg logit contributions | |
Sof | -0.021 |
igi | -0.021 |
Belle | -0.020 |
Dawn | -0.020 |
Sasha | -0.020 |
Token | lively |
Token ID | 29696 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Sof | +0.019 |
igi | +0.018 |
ora | +0.018 |
Sasha | +0.018 |
Dawn | +0.018 |
Neg logit contributions | |
op | -0.008 |
repair | -0.008 |
apr | -0.008 |
bel | -0.008 |
x | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
op | +0.004 |
apr | +0.004 |
bel | +0.004 |
driver | +0.004 |
x | +0.004 |
Neg logit contributions | |
igi | -0.005 |
Sof | -0.005 |
Dawn | -0.005 |
ora | -0.005 |
Belle | -0.005 |
Token | some |
Token ID | 617 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Sof | +0.032 |
coc | +0.030 |
Belle | +0.028 |
Sasha | +0.028 |
Sophia | +0.028 |
Neg logit contributions | |
op | -0.056 |
t | -0.052 |
bel | -0.049 |
washer | -0.048 |
oscope | -0.047 |
Token | sticks |
Token ID | 16461 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
coc | +0.002 |
bou | +0.002 |
blo | +0.002 |
pearl | +0.002 |
turtles | +0.002 |
Neg logit contributions | |
op | -0.003 |
t | -0.003 |
This | -0.002 |
bel | -0.002 |
driver | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
apr | +0.001 |
x | +0.001 |
op | +0.001 |
bel | +0.001 |
laptop | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
Belle | -0.001 |
Sasha | -0.001 |
igi | -0.001 |
Sophia | -0.001 |
Token | leaves |
Token ID | 5667 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
op | +0.002 |
t | +0.002 |
bel | +0.002 |
x | +0.002 |
This | +0.002 |
Neg logit contributions | |
Belle | -0.002 |
coc | -0.002 |
Sof | -0.002 |
Fif | -0.002 |
Sasha | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Sof | +0.076 |
igi | +0.072 |
Belle | +0.071 |
Fif | +0.070 |
Sasha | +0.070 |
Neg logit contributions | |
apr | -0.071 |
x | -0.070 |
op | -0.066 |
laptop | -0.065 |
shirt | -0.064 |
Token | berries |
Token ID | 36322 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Belle | +0.026 |
coc | +0.026 |
Sof | +0.025 |
Fif | +0.025 |
Sasha | +0.025 |
Neg logit contributions | |
op | -0.030 |
t | -0.027 |
This | -0.025 |
x | -0.025 |
bel | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
igi | +0.170 |
Sof | +0.170 |
Belle | +0.163 |
Fif | +0.162 |
Sasha | +0.159 |
Neg logit contributions | |
x | -0.147 |
apr | -0.146 |
op | -0.137 |
bel | -0.135 |
headphones | -0.133 |
Token | They |
Token ID | 1119 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Sof | +0.005 |
igi | +0.005 |
Belle | +0.005 |
Dawn | +0.005 |
Sasha | +0.004 |
Neg logit contributions | |
op | -0.004 |
bel | -0.004 |
apr | -0.004 |
driver | -0.004 |
t | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Sof | +0.037 |
igi | +0.037 |
Belle | +0.036 |
Dawn | +0.036 |
ora | +0.036 |
Neg logit contributions | |
op | -0.038 |
apr | -0.036 |
bel | -0.036 |
driver | -0.035 |
t | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
op | +0.054 |
t | +0.050 |
driver | +0.049 |
apr | +0.047 |
bel | +0.047 |
Neg logit contributions | |
Sof | -0.065 |
Belle | -0.061 |
Fif | -0.060 |
Sasha | -0.060 |
Dawn | -0.060 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
igi | +0.047 |
Sof | +0.046 |
Dawn | +0.046 |
Sasha | +0.045 |
ora | +0.044 |
Neg logit contributions | |
bel | -0.021 |
apr | -0.021 |
op | -0.020 |
x | -0.020 |
drill | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
igi | +0.004 |
ora | +0.003 |
Joy | +0.003 |
oph | +0.003 |
Dawn | +0.003 |
Neg logit contributions | |
apr | -0.001 |
tools | -0.001 |
x | -0.001 |
to | -0.001 |
fixing | -0.001 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
tools | +0.018 |
x | +0.018 |
op | +0.018 |
apr | +0.017 |
t | +0.017 |
Neg logit contributions | |
igi | -0.015 |
Sof | -0.015 |
Belle | -0.014 |
Sasha | -0.014 |
oph | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Sof | +0.079 |
igi | +0.076 |
Belle | +0.074 |
Sasha | +0.074 |
Joy | +0.073 |
Neg logit contributions | |
apr | -0.056 |
bel | -0.055 |
op | -0.051 |
driver | -0.050 |
x | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
bel | +0.012 |
apr | +0.011 |
tools | +0.011 |
driver | +0.011 |
op | +0.011 |
Neg logit contributions | |
igi | -0.021 |
ora | -0.021 |
Dawn | -0.020 |
oph | -0.020 |
Joy | -0.020 |
Token | green |
Token ID | 4077 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
igi | +0.004 |
Sof | +0.004 |
ora | +0.004 |
Belle | +0.004 |
Sasha | +0.004 |
Neg logit contributions | |
op | -0.005 |
apr | -0.005 |
bel | -0.005 |
tools | -0.005 |
x | -0.005 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
igi | +0.000 |
Sof | +0.000 |
Belle | +0.000 |
Dawn | +0.000 |
Joy | +0.000 |
Neg logit contributions | |
op | -0.000 |
driver | -0.000 |
bel | -0.000 |
tools | -0.000 |
apr | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Sof | +0.202 |
igi | +0.199 |
Belle | +0.195 |
ora | +0.194 |
Dawn | +0.193 |
Neg logit contributions | |
op | -0.119 |
apr | -0.119 |
bel | -0.115 |
driver | -0.108 |
x | -0.106 |
Token | They |
Token ID | 1119 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Sof | +0.009 |
Belle | +0.009 |
Dawn | +0.009 |
igi | +0.009 |
Sasha | +0.009 |
Neg logit contributions | |
op | -0.008 |
bel | -0.008 |
apr | -0.008 |
driver | -0.008 |
x | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
igi | +0.050 |
Sasha | +0.046 |
Belle | +0.046 |
Dawn | +0.046 |
ora | +0.045 |
Neg logit contributions | |
bel | -0.032 |
op | -0.032 |
apr | -0.032 |
t | -0.031 |
driver | -0.029 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
bel | +0.001 |
tools | +0.001 |
fixing | +0.001 |
apr | +0.001 |
to | +0.001 |
Neg logit contributions | |
oph | -0.001 |
ora | -0.001 |
igi | -0.001 |
Dawn | -0.001 |
Sof | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
op | +0.025 |
bel | +0.025 |
to | +0.022 |
apr | +0.022 |
t | +0.021 |
Neg logit contributions | |
igi | -0.081 |
Dawn | -0.078 |
ora | -0.077 |
Sof | -0.077 |
Belle | -0.077 |
Token | go |
Token ID | 467 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
Sof | +0.017 |
igi | +0.016 |
Dawn | +0.016 |
Belle | +0.016 |
ora | +0.016 |
Neg logit contributions | |
op | -0.014 |
apr | -0.014 |
bel | -0.014 |
driver | -0.013 |
t | -0.013 |
Token | dancing |
Token ID | 15360 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Sof | +0.003 |
igi | +0.003 |
Dawn | +0.003 |
Belle | +0.003 |
ora | +0.003 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
bel | -0.002 |
driver | -0.002 |
t | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
op | +0.063 |
apr | +0.059 |
driver | +0.058 |
bel | +0.058 |
x | +0.056 |
Neg logit contributions | |
Sof | -0.070 |
Belle | -0.068 |
ora | -0.068 |
Dawn | -0.067 |
igi | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
op | +0.007 |
bel | +0.007 |
apr | +0.007 |
driver | +0.006 |
x | +0.006 |
Neg logit contributions | |
Sof | -0.007 |
Belle | -0.007 |
Dawn | -0.007 |
Sasha | -0.007 |
Sophia | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
op | +0.009 |
apr | +0.009 |
bel | +0.009 |
driver | +0.008 |
t | +0.008 |
Neg logit contributions | |
igi | -0.015 |
Sof | -0.015 |
Belle | -0.015 |
Dawn | -0.015 |
ora | -0.015 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
op | +0.012 |
apr | +0.012 |
bel | +0.012 |
driver | +0.011 |
t | +0.011 |
Neg logit contributions | |
Sof | -0.012 |
igi | -0.012 |
Belle | -0.011 |
Dawn | -0.011 |
ora | -0.011 |
Token | lla |
Token ID | 8466 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Dawn | +0.141 |
Belle | +0.135 |
Sof | +0.135 |
Sasha | +0.134 |
Nora | +0.128 |
Neg logit contributions | |
op | -0.190 |
t | -0.181 |
bel | -0.181 |
apr | -0.177 |
oscope | -0.174 |
Token | gul |
Token ID | 47161 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
Sof | +0.030 |
igi | +0.029 |
Dawn | +0.029 |
Belle | +0.029 |
ora | +0.029 |
Neg logit contributions | |
op | -0.033 |
apr | -0.032 |
bel | -0.032 |
driver | -0.031 |
x | -0.030 |
Token | ped |
Token ID | 9124 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Sof | +0.028 |
igi | +0.028 |
Dawn | +0.027 |
Belle | +0.027 |
ora | +0.027 |
Neg logit contributions | |
op | -0.028 |
apr | -0.027 |
bel | -0.026 |
driver | -0.026 |
x | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Sof | +0.048 |
Dawn | +0.048 |
Belle | +0.047 |
Sasha | +0.046 |
Iris | +0.046 |
Neg logit contributions | |
op | -0.044 |
bel | -0.044 |
apr | -0.044 |
driver | -0.041 |
t | -0.040 |
Token | but |
Token ID | 475 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Sof | +0.005 |
Sasha | +0.005 |
Belle | +0.005 |
Dawn | +0.005 |
Sophia | +0.005 |
Neg logit contributions | |
op | -0.005 |
bel | -0.005 |
apr | -0.005 |
x | -0.005 |
driver | -0.005 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
igi | +0.057 |
Sof | +0.053 |
Belle | +0.053 |
Dawn | +0.052 |
Sasha | +0.052 |
Neg logit contributions | |
op | -0.046 |
bel | -0.046 |
apr | -0.045 |
His | -0.043 |
driver | -0.042 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
apr | +0.007 |
bel | +0.006 |
op | +0.006 |
tools | +0.006 |
driver | +0.006 |
Neg logit contributions | |
igi | -0.011 |
ora | -0.011 |
Belle | -0.010 |
Sof | -0.010 |
oph | -0.010 |
Token | together |
Token ID | 1978 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
op | +0.047 |
apr | +0.046 |
bel | +0.045 |
driver | +0.044 |
t | +0.041 |
Neg logit contributions | |
Sof | -0.067 |
igi | -0.067 |
Dawn | -0.065 |
Belle | -0.065 |
ora | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
op | +0.024 |
bel | +0.023 |
apr | +0.023 |
driver | +0.022 |
x | +0.021 |
Neg logit contributions | |
Sof | -0.037 |
igi | -0.036 |
Belle | -0.036 |
Dawn | -0.036 |
ora | -0.036 |
Token | The |
Token ID | 383 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
igi | +0.006 |
Sof | +0.006 |
Dawn | +0.006 |
ora | +0.006 |
Belle | +0.006 |
Neg logit contributions | |
op | -0.004 |
apr | -0.004 |
bel | -0.004 |
driver | -0.004 |
t | -0.004 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
op | +0.019 |
x | +0.018 |
tools | +0.018 |
apr | +0.018 |
bel | +0.018 |
Neg logit contributions | |
Sof | -0.017 |
igi | -0.017 |
Belle | -0.016 |
Dawn | -0.016 |
Sasha | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Sof | +0.159 |
igi | +0.155 |
Belle | +0.153 |
Dawn | +0.152 |
ora | +0.152 |
Neg logit contributions | |
op | -0.161 |
apr | -0.160 |
bel | -0.156 |
driver | -0.152 |
x | -0.148 |
Token | so |
Token ID | 523 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Sof | +0.004 |
igi | +0.004 |
Dawn | +0.004 |
Belle | +0.004 |
ora | +0.004 |
Neg logit contributions | |
op | -0.004 |
apr | -0.003 |
bel | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
op | +0.004 |
apr | +0.004 |
bel | +0.004 |
driver | +0.004 |
t | +0.003 |
Neg logit contributions | |
Sof | -0.004 |
igi | -0.004 |
Dawn | -0.004 |
Belle | -0.004 |
ora | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
op | +0.014 |
bel | +0.013 |
apr | +0.012 |
driver | +0.012 |
t | +0.012 |
Neg logit contributions | |
igi | -0.031 |
Sof | -0.031 |
ora | -0.030 |
Belle | -0.030 |
Dawn | -0.030 |
Token | proud |
Token ID | 6613 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
bel | +0.007 |
op | +0.007 |
t | +0.007 |
His | +0.007 |
apr | +0.007 |
Neg logit contributions | |
igi | -0.010 |
ora | -0.009 |
Sof | -0.009 |
Joy | -0.009 |
Belle | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Sof | +0.016 |
igi | +0.016 |
ora | +0.015 |
Belle | +0.015 |
Dawn | +0.015 |
Neg logit contributions | |
op | -0.008 |
apr | -0.008 |
bel | -0.007 |
driver | -0.007 |
x | -0.007 |
Token | slides |
Token ID | 19392 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
t | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
igi | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
ora | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
igi | +0.040 |
Sof | +0.040 |
Dawn | +0.040 |
Belle | +0.040 |
ora | +0.039 |
Neg logit contributions | |
op | -0.018 |
bel | -0.017 |
apr | -0.016 |
driver | -0.016 |
t | -0.015 |
Token | swings |
Token ID | 26728 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
igi | +0.018 |
oph | +0.016 |
Dawn | +0.016 |
ora | +0.016 |
Belle | +0.016 |
Neg logit contributions | |
bel | -0.012 |
tools | -0.012 |
apr | -0.011 |
Some | -0.011 |
headphones | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
igi | +0.106 |
Belle | +0.103 |
Dawn | +0.103 |
ora | +0.102 |
oph | +0.102 |
Neg logit contributions | |
op | -0.037 |
bel | -0.037 |
driver | -0.035 |
apr | -0.034 |
t | -0.032 |
Token | l |
Token ID | 300 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
igi | +0.046 |
Dawn | +0.040 |
iri | +0.040 |
oph | +0.040 |
Belle | +0.039 |
Neg logit contributions | |
bel | -0.037 |
apr | -0.036 |
Some | -0.035 |
tools | -0.035 |
driver | -0.034 |
Token | adders |
Token ID | 45940 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
igi | +0.243 |
oph | +0.235 |
die | +0.233 |
Belle | +0.228 |
Dawn | +0.227 |
Neg logit contributions | |
op | -0.090 |
driver | -0.075 |
itt | -0.070 |
Some | -0.068 |
bel | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
x | +0.001 |
Neg logit contributions | |
Sof | -0.002 |
igi | -0.002 |
Dawn | -0.002 |
ora | -0.002 |
Belle | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
igi | +0.007 |
Dawn | +0.007 |
Belle | +0.007 |
Sof | +0.007 |
ora | +0.007 |
Neg logit contributions | |
op | -0.006 |
apr | -0.006 |
bel | -0.006 |
driver | -0.006 |
t | -0.005 |
Token | run |
Token ID | 1057 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
igi | +0.045 |
Dawn | +0.040 |
Sof | +0.040 |
oph | +0.039 |
Belle | +0.039 |
Neg logit contributions | |
op | -0.033 |
apr | -0.032 |
driver | -0.031 |
bel | -0.031 |
tools | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
igi | +0.018 |
Sof | +0.018 |
Belle | +0.018 |
Dawn | +0.018 |
ora | +0.018 |
Neg logit contributions | |
op | -0.005 |
bel | -0.005 |
apr | -0.005 |
driver | -0.005 |
t | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
apr | +0.025 |
x | +0.025 |
op | +0.024 |
drill | +0.023 |
laptop | +0.022 |
Neg logit contributions | |
Sof | -0.031 |
igi | -0.031 |
ora | -0.030 |
Belle | -0.030 |
Dawn | -0.030 |
Token | leaves |
Token ID | 5667 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Sof | +0.021 |
Belle | +0.020 |
igi | +0.019 |
Fif | +0.019 |
Dawn | +0.019 |
Neg logit contributions | |
op | -0.030 |
driver | -0.027 |
x | -0.027 |
t | -0.027 |
bel | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
Sof | +0.086 |
igi | +0.084 |
Belle | +0.083 |
Dawn | +0.081 |
ora | +0.081 |
Neg logit contributions | |
apr | -0.078 |
x | -0.075 |
op | -0.074 |
bel | -0.072 |
headphones | -0.069 |
Token | feathers |
Token ID | 27400 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Belle | +0.039 |
Sof | +0.039 |
igi | +0.038 |
Sasha | +0.037 |
Fif | +0.037 |
Neg logit contributions | |
op | -0.035 |
x | -0.031 |
apr | -0.030 |
bel | -0.030 |
driver | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Sof | +0.057 |
igi | +0.056 |
Belle | +0.056 |
ora | +0.054 |
Fif | +0.054 |
Neg logit contributions | |
apr | -0.054 |
x | -0.051 |
bel | -0.051 |
op | -0.050 |
laptop | -0.048 |
Token | berries |
Token ID | 36322 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Belle | +0.039 |
Sof | +0.039 |
Fif | +0.037 |
Dawn | +0.037 |
Sasha | +0.036 |
Neg logit contributions | |
op | -0.046 |
apr | -0.041 |
bel | -0.041 |
driver | -0.041 |
t | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-04 |
Pos logit contributions | |
Sof | +0.187 |
igi | +0.187 |
Belle | +0.181 |
ora | +0.181 |
Dawn | +0.179 |
Neg logit contributions | |
apr | -0.129 |
op | -0.128 |
x | -0.125 |
bel | -0.124 |
driver | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
igi | +0.000 |
Sof | +0.000 |
Dawn | +0.000 |
Belle | +0.000 |
ora | +0.000 |
Neg logit contributions | |
op | -0.000 |
apr | -0.000 |
bel | -0.000 |
driver | -0.000 |
t | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
op | +0.005 |
apr | +0.004 |
bel | +0.004 |
driver | +0.004 |
x | +0.004 |
Neg logit contributions | |
Sof | -0.006 |
igi | -0.006 |
Dawn | -0.006 |
Belle | -0.006 |
ora | -0.006 |
Token | One |
Token ID | 3198 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
op | +0.014 |
apr | +0.013 |
bel | +0.013 |
driver | +0.012 |
t | +0.012 |
Neg logit contributions | |
Sof | -0.015 |
igi | -0.015 |
Dawn | -0.015 |
Belle | -0.015 |
ora | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
driver | +0.035 |
apr | +0.035 |
op | +0.034 |
bel | +0.034 |
x | +0.032 |
Neg logit contributions | |
Sof | -0.037 |
igi | -0.037 |
ora | -0.036 |
Belle | -0.036 |
Dawn | -0.036 |
Token | it |
Token ID | 340 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
op | +0.030 |
bel | +0.030 |
driver | +0.029 |
apr | +0.029 |
t | +0.028 |
Neg logit contributions | |
Sof | -0.029 |
Belle | -0.028 |
Sasha | -0.028 |
Dawn | -0.028 |
Fif | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
apr | +0.031 |
bel | +0.029 |
op | +0.028 |
Some | +0.026 |
itt | +0.026 |
Neg logit contributions | |
Sof | -0.028 |
Belle | -0.027 |
Dawn | -0.026 |
Sasha | -0.026 |
Sophia | -0.025 |
Token | even |
Token ID | 772 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Sof | +0.036 |
Belle | +0.035 |
Sasha | +0.034 |
Dawn | +0.034 |
igi | +0.033 |
Neg logit contributions | |
op | -0.036 |
bel | -0.033 |
apr | -0.033 |
driver | -0.032 |
x | -0.031 |
Token | though |
Token ID | 996 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
op | +0.022 |
apr | +0.021 |
bel | +0.020 |
driver | +0.020 |
t | +0.020 |
Neg logit contributions | |
Sof | -0.018 |
Belle | -0.018 |
igi | -0.018 |
Dawn | -0.017 |
Sasha | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
igi | +0.017 |
ora | +0.016 |
Sof | +0.016 |
Belle | +0.016 |
Dawn | +0.016 |
Neg logit contributions | |
op | -0.015 |
apr | -0.014 |
bel | -0.014 |
driver | -0.014 |
t | -0.014 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
Sof | +0.021 |
igi | +0.021 |
Belle | +0.020 |
ora | +0.020 |
Sasha | +0.020 |
Neg logit contributions | |
op | -0.025 |
tools | -0.025 |
x | -0.024 |
apr | -0.024 |
driver | -0.024 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Sof | +0.147 |
igi | +0.143 |
Dawn | +0.139 |
ora | +0.139 |
Belle | +0.139 |
Neg logit contributions | |
apr | -0.173 |
op | -0.166 |
bel | -0.164 |
driver | -0.159 |
x | -0.155 |
Token | 't |
Token ID | 470 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
apr | +0.009 |
bel | +0.008 |
tools | +0.007 |
op | +0.007 |
headphones | +0.007 |
Neg logit contributions | |
Sof | -0.011 |
Dawn | -0.011 |
Iris | -0.011 |
Fif | -0.011 |
Belle | -0.011 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Dawn | +0.043 |
Sof | +0.043 |
igi | +0.043 |
Belle | +0.042 |
ora | +0.042 |
Neg logit contributions | |
apr | -0.055 |
op | -0.052 |
bel | -0.052 |
driver | -0.050 |
laptop | -0.048 |
Token | her |
Token ID | 607 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
op | +0.056 |
apr | +0.055 |
bel | +0.054 |
driver | +0.053 |
t | +0.050 |
Neg logit contributions | |
Sof | -0.050 |
Belle | -0.048 |
igi | -0.047 |
Sasha | -0.047 |
Dawn | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
apr | +0.008 |
driver | +0.007 |
Some | +0.007 |
op | +0.007 |
bel | +0.007 |
Neg logit contributions | |
Sof | -0.008 |
coc | -0.007 |
Sasha | -0.007 |
Dawn | -0.007 |
Belle | -0.007 |
Token | nut |
Token ID | 6701 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
op | +0.036 |
apr | +0.035 |
bel | +0.035 |
driver | +0.033 |
x | +0.033 |
Neg logit contributions | |
Sof | -0.019 |
igi | -0.019 |
Belle | -0.018 |
Fif | -0.018 |
Dawn | -0.018 |
Token | at |
Token ID | 379 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
Sof | +0.115 |
igi | +0.111 |
ora | +0.109 |
Belle | +0.109 |
Fif | +0.109 |
Neg logit contributions | |
apr | -0.084 |
op | -0.079 |
x | -0.076 |
bel | -0.075 |
Some | -0.071 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
apr | +0.029 |
op | +0.028 |
x | +0.028 |
His | +0.026 |
bel | +0.026 |
Neg logit contributions | |
igi | -0.030 |
Dawn | -0.029 |
ora | -0.028 |
Sof | -0.028 |
Joy | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
apr | +0.011 |
bel | +0.010 |
op | +0.010 |
Some | +0.009 |
driver | +0.009 |
Neg logit contributions | |
Sof | -0.013 |
Belle | -0.012 |
Sasha | -0.012 |
igi | -0.012 |
Fif | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
bel | +0.005 |
apr | +0.005 |
op | +0.005 |
driver | +0.005 |
tools | +0.004 |
Neg logit contributions | |
Sof | -0.007 |
Belle | -0.007 |
Sasha | -0.007 |
Dawn | -0.007 |
Fif | -0.007 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
op | +0.035 |
tools | +0.035 |
x | +0.034 |
driver | +0.034 |
bel | +0.034 |
Neg logit contributions | |
igi | -0.031 |
oph | -0.030 |
Sof | -0.029 |
ora | -0.029 |
Dawn | -0.029 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Sof | +0.129 |
igi | +0.122 |
Belle | +0.119 |
Fif | +0.118 |
ora | +0.117 |
Neg logit contributions | |
apr | -0.193 |
op | -0.187 |
bel | -0.177 |
x | -0.177 |
driver | -0.173 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Sof | +0.037 |
igi | +0.035 |
Belle | +0.035 |
Dawn | +0.035 |
Sasha | +0.034 |
Neg logit contributions | |
op | -0.052 |
bel | -0.051 |
apr | -0.051 |
driver | -0.049 |
t | -0.048 |
Token | on |
Token ID | 319 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Sof | +0.013 |
Joy | +0.012 |
Fif | +0.012 |
coc | +0.012 |
Belle | +0.012 |
Neg logit contributions | |
apr | -0.014 |
bel | -0.013 |
Some | -0.012 |
renches | -0.012 |
op | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
bel | +0.022 |
op | +0.022 |
apr | +0.020 |
driver | +0.020 |
t | +0.020 |
Neg logit contributions | |
Sof | -0.018 |
Belle | -0.017 |
Sasha | -0.017 |
Sophia | -0.016 |
Dawn | -0.016 |
Token | head |
Token ID | 1182 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
op | +0.000 |
apr | +0.000 |
driver | +0.000 |
bel | +0.000 |
x | +0.000 |
Neg logit contributions | |
igi | -0.000 |
Sof | -0.000 |
Dawn | -0.000 |
ora | -0.000 |
Belle | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
igi | +0.003 |
Sof | +0.003 |
Dawn | +0.003 |
ora | +0.003 |
Belle | +0.003 |
Neg logit contributions | |
op | -0.003 |
apr | -0.003 |
bel | -0.003 |
x | -0.003 |
driver | -0.002 |
Token | deep |
Token ID | 2769 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
igi | +0.019 |
Dawn | +0.018 |
ora | +0.018 |
Sof | +0.017 |
Sasha | +0.017 |
Neg logit contributions | |
x | -0.011 |
repair | -0.011 |
tools | -0.011 |
tool | -0.010 |
to | -0.010 |
Token | hole |
Token ID | 7604 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
op | +0.012 |
x | +0.012 |
apr | +0.012 |
bel | +0.012 |
driver | +0.012 |
Neg logit contributions | |
igi | -0.013 |
Sof | -0.013 |
Dawn | -0.013 |
Belle | -0.012 |
Joy | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Sof | +0.060 |
Belle | +0.056 |
ora | +0.055 |
igi | +0.055 |
Sasha | +0.055 |
Neg logit contributions | |
apr | -0.070 |
op | -0.065 |
bel | -0.064 |
x | -0.061 |
headphones | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Sof | +0.037 |
Belle | +0.036 |
Dawn | +0.035 |
Fif | +0.035 |
Sasha | +0.035 |
Neg logit contributions | |
op | -0.028 |
apr | -0.027 |
bel | -0.026 |
driver | -0.025 |
laptop | -0.024 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
igi | +0.016 |
Sof | +0.016 |
ora | +0.015 |
oph | +0.015 |
Sasha | +0.015 |
Neg logit contributions | |
tools | -0.018 |
x | -0.018 |
op | -0.018 |
repair | -0.017 |
t | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Sof | +0.164 |
igi | +0.163 |
Dawn | +0.159 |
Belle | +0.159 |
ora | +0.157 |
Neg logit contributions | |
op | -0.154 |
apr | -0.148 |
bel | -0.148 |
driver | -0.143 |
t | -0.137 |
Token | gone |
Token ID | 3750 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
op | +0.006 |
bel | +0.006 |
apr | +0.006 |
driver | +0.006 |
t | +0.005 |
Neg logit contributions | |
igi | -0.006 |
Sof | -0.006 |
Belle | -0.006 |
Dawn | -0.006 |
Sasha | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
Sof | +0.024 |
igi | +0.024 |
Dawn | +0.024 |
Belle | +0.024 |
ora | +0.024 |
Neg logit contributions | |
op | -0.010 |
bel | -0.009 |
apr | -0.009 |
driver | -0.009 |
t | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
bel | +0.019 |
apr | +0.017 |
op | +0.016 |
driver | +0.015 |
headphones | +0.015 |
Neg logit contributions | |
Sof | -0.030 |
Fif | -0.029 |
Gig | -0.028 |
Belle | -0.028 |
Claw | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
op | +0.006 |
apr | +0.005 |
bel | +0.005 |
x | +0.005 |
tools | +0.005 |
Neg logit contributions | |
igi | -0.008 |
Sof | -0.008 |
Dawn | -0.008 |
Belle | -0.008 |
ora | -0.008 |
Token | many |
Token ID | 867 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
op | +0.046 |
apr | +0.044 |
bel | +0.043 |
driver | +0.041 |
t | +0.040 |
Neg logit contributions | |
Sof | -0.083 |
igi | -0.081 |
Belle | -0.080 |
Dawn | -0.080 |
Sasha | -0.079 |
Token | sandwiches |
Token ID | 29777 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
apr | +0.019 |
op | +0.019 |
tools | +0.018 |
bel | +0.017 |
driver | +0.017 |
Neg logit contributions | |
igi | -0.032 |
Sof | -0.032 |
Belle | -0.032 |
Sasha | -0.031 |
Dawn | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
igi | +0.107 |
Sof | +0.106 |
Dawn | +0.105 |
Belle | +0.104 |
ora | +0.104 |
Neg logit contributions | |
op | -0.044 |
driver | -0.041 |
apr | -0.040 |
bel | -0.040 |
t | -0.038 |
Token | fruits |
Token ID | 15921 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
apr | +0.007 |
bel | +0.007 |
tools | +0.007 |
driver | +0.006 |
Some | +0.006 |
Neg logit contributions | |
igi | -0.009 |
Dawn | -0.009 |
Sof | -0.009 |
ora | -0.009 |
Belle | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Sof | +0.092 |
igi | +0.091 |
Dawn | +0.089 |
Belle | +0.089 |
ora | +0.089 |
Neg logit contributions | |
op | -0.045 |
apr | -0.043 |
bel | -0.042 |
driver | -0.040 |
t | -0.038 |
Token | drinks |
Token ID | 11758 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
igi | +0.025 |
Dawn | +0.024 |
Sof | +0.024 |
ora | +0.023 |
Belle | +0.023 |
Neg logit contributions | |
apr | -0.022 |
bel | -0.021 |
tools | -0.020 |
op | -0.020 |
driver | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Sof | +0.206 |
igi | +0.204 |
Belle | +0.200 |
Dawn | +0.200 |
ora | +0.199 |
Neg logit contributions | |
op | -0.113 |
bel | -0.106 |
apr | -0.106 |
driver | -0.101 |
x | -0.097 |
Token | She |
Token ID | 1375 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Sof | +0.009 |
Belle | +0.009 |
Dawn | +0.009 |
igi | +0.009 |
Sasha | +0.009 |
Neg logit contributions | |
op | -0.008 |
bel | -0.008 |
apr | -0.008 |
driver | -0.008 |
t | -0.007 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
igi | +0.041 |
Dawn | +0.040 |
Belle | +0.039 |
Sof | +0.038 |
ora | +0.038 |
Neg logit contributions | |
apr | -0.034 |
op | -0.033 |
bel | -0.033 |
driver | -0.031 |
tools | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Sof | +0.046 |
igi | +0.044 |
Belle | +0.044 |
ora | +0.044 |
Dawn | +0.044 |
Neg logit contributions | |
op | -0.026 |
apr | -0.025 |
bel | -0.024 |
driver | -0.023 |
x | -0.022 |
Token | took |
Token ID | 1718 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
apr | +0.031 |
bel | +0.031 |
His | +0.029 |
tools | +0.028 |
to | +0.028 |
Neg logit contributions | |
igi | -0.051 |
ora | -0.045 |
perspective | -0.045 |
Joy | -0.044 |
Dawn | -0.044 |
Token | " |
Token ID | 366 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Sof | +0.010 |
Belle | +0.010 |
Dawn | +0.009 |
Sasha | +0.009 |
igi | +0.009 |
Neg logit contributions | |
op | -0.011 |
apr | -0.010 |
bel | -0.010 |
driver | -0.010 |
x | -0.010 |
Token | Please |
Token ID | 5492 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
op | +0.013 |
apr | +0.012 |
driver | +0.012 |
bel | +0.012 |
x | +0.012 |
Neg logit contributions | |
igi | -0.008 |
Sof | -0.008 |
ora | -0.008 |
Joy | -0.008 |
Belle | -0.008 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Sof | +0.002 |
igi | +0.002 |
Dawn | +0.002 |
Belle | +0.002 |
ora | +0.002 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
bel | -0.002 |
driver | -0.002 |
t | -0.001 |
Token | your |
Token ID | 534 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Dawn | +0.006 |
igi | +0.006 |
Sof | +0.006 |
Belle | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
bel | -0.010 |
op | -0.010 |
driver | -0.010 |
apr | -0.010 |
t | -0.010 |
Token | seat |
Token ID | 5852 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
op | +0.042 |
driver | +0.040 |
His | +0.039 |
Some | +0.039 |
t | +0.038 |
Neg logit contributions | |
waterfall | -0.031 |
coc | -0.031 |
Belle | -0.031 |
forget | -0.029 |
ora | -0.029 |
Token | bel |
Token ID | 6667 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
Some | +0.112 |
apr | +0.108 |
op | +0.098 |
itt | +0.097 |
His | +0.097 |
Neg logit contributions | |
igi | -0.099 |
Sof | -0.090 |
ora | -0.090 |
Dawn | -0.086 |
forget | -0.086 |
Token | ts |
Token ID | 912 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
op | +0.364 |
bel | +0.339 |
apr | +0.335 |
inter | +0.335 |
driver | +0.327 |
Neg logit contributions | |
Joy | -0.191 |
igi | -0.190 |
Iris | -0.183 |
Sof | -0.181 |
Lib | -0.170 |
Token | on |
Token ID | 319 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
op | +0.057 |
apr | +0.057 |
Some | +0.056 |
x | +0.055 |
driver | +0.053 |
Neg logit contributions | |
igi | -0.047 |
Sof | -0.045 |
ora | -0.044 |
Belle | -0.042 |
Sasha | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
op | +0.052 |
bel | +0.049 |
driver | +0.047 |
apr | +0.047 |
t | +0.045 |
Neg logit contributions | |
Sof | -0.027 |
waterfall | -0.026 |
Belle | -0.025 |
igi | -0.024 |
Sasha | -0.024 |
Token | We |
Token ID | 775 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
Sof | +0.005 |
Dawn | +0.005 |
Belle | +0.005 |
Fif | +0.005 |
Sasha | +0.005 |
Neg logit contributions | |
apr | -0.008 |
bel | -0.008 |
op | -0.007 |
tools | -0.007 |
driver | -0.007 |
Token | will |
Token ID | 481 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
apr | +0.001 |
bel | +0.001 |
op | +0.001 |
x | +0.001 |
driver | +0.001 |
Neg logit contributions | |
Dawn | -0.001 |
igi | -0.001 |
Belle | -0.001 |
ora | -0.001 |
Sof | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
op | +0.035 |
apr | +0.034 |
bel | +0.034 |
driver | +0.034 |
x | +0.032 |
Neg logit contributions | |
Sof | -0.035 |
igi | -0.035 |
Belle | -0.034 |
Dawn | -0.034 |
ora | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
op | +0.053 |
driver | +0.050 |
t | +0.050 |
bel | +0.047 |
apr | +0.043 |
Neg logit contributions | |
Sof | -0.093 |
Fif | -0.091 |
Gig | -0.090 |
Dawn | -0.089 |
Belle | -0.088 |
Token | play |
Token ID | 711 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
op | +0.013 |
t | +0.013 |
bel | +0.013 |
driver | +0.012 |
apr | +0.012 |
Neg logit contributions | |
Belle | -0.011 |
Sof | -0.010 |
Dawn | -0.010 |
Fif | -0.010 |
Sasha | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
op | +0.021 |
t | +0.020 |
driver | +0.019 |
bel | +0.019 |
apr | +0.018 |
Neg logit contributions | |
Sof | -0.034 |
Belle | -0.033 |
Dawn | -0.033 |
ora | -0.033 |
Iris | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
op | +0.066 |
driver | +0.065 |
t | +0.065 |
apr | +0.063 |
bel | +0.062 |
Neg logit contributions | |
Sof | -0.073 |
Dawn | -0.069 |
Belle | -0.069 |
ora | -0.068 |
Sophia | -0.067 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
apr | +0.041 |
His | +0.039 |
x | +0.038 |
op | +0.038 |
driver | +0.038 |
Neg logit contributions | |
ora | -0.086 |
Sof | -0.086 |
igi | -0.084 |
Joy | -0.084 |
Belle | -0.082 |
Token | ieve |
Token ID | 12311 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
op | +0.360 |
inter | +0.343 |
therm | +0.328 |
driver | +0.323 |
apr | +0.320 |
Neg logit contributions | |
Sof | -0.169 |
Iris | -0.162 |
Sophia | -0.162 |
Joy | -0.161 |
Kay | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
op | +0.012 |
driver | +0.011 |
apr | +0.011 |
His | +0.011 |
x | +0.011 |
Neg logit contributions | |
Sof | -0.014 |
ora | -0.014 |
Belle | -0.014 |
coc | -0.013 |
Sophia | -0.013 |
Token | Today |
Token ID | 6288 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
bel | +0.003 |
op | +0.003 |
apr | +0.003 |
driver | +0.002 |
x | +0.002 |
Neg logit contributions | |
Sof | -0.004 |
Dawn | -0.004 |
Belle | -0.003 |
ora | -0.003 |
igi | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
apr | +0.026 |
op | +0.026 |
bel | +0.025 |
driver | +0.024 |
x | +0.023 |
Neg logit contributions | |
Sof | -0.028 |
Dawn | -0.027 |
Belle | -0.027 |
ora | -0.027 |
igi | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
op | +0.010 |
apr | +0.010 |
bel | +0.010 |
driver | +0.010 |
x | +0.010 |
Neg logit contributions | |
Sof | -0.009 |
igi | -0.008 |
ora | -0.008 |
Dawn | -0.008 |
Belle | -0.008 |
Token | John |
Token ID | 1757 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
op | +0.003 |
bel | +0.003 |
apr | +0.003 |
driver | +0.002 |
x | +0.002 |
Neg logit contributions | |
Sof | -0.004 |
Sasha | -0.004 |
Belle | -0.004 |
Dawn | -0.004 |
igi | -0.004 |
Token | began |
Token ID | 2540 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
op | +0.028 |
apr | +0.027 |
bel | +0.027 |
driver | +0.026 |
x | +0.025 |
Neg logit contributions | |
Sof | -0.025 |
igi | -0.025 |
Belle | -0.024 |
Dawn | -0.024 |
ora | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Sof | +0.004 |
Belle | +0.003 |
Sasha | +0.003 |
Dawn | +0.003 |
Sophia | +0.003 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
driver | -0.002 |
t | -0.002 |
x | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
op | +0.017 |
apr | +0.016 |
bel | +0.016 |
driver | +0.015 |
x | +0.015 |
Neg logit contributions | |
igi | -0.020 |
Sof | -0.020 |
Dawn | -0.019 |
Belle | -0.019 |
ora | -0.019 |
Token | - |
Token ID | 12 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
op | +0.060 |
apr | +0.058 |
bel | +0.058 |
driver | +0.055 |
x | +0.054 |
Neg logit contributions | |
igi | -0.087 |
Sof | -0.085 |
ora | -0.083 |
Dawn | -0.083 |
Belle | -0.083 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
apr | +0.043 |
op | +0.037 |
laptop | +0.035 |
x | +0.031 |
driver | +0.031 |
Neg logit contributions | |
Sof | -0.109 |
Joy | -0.108 |
igi | -0.107 |
ora | -0.107 |
Belle | -0.106 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
op | +0.347 |
apr | +0.310 |
driver | +0.310 |
bel | +0.306 |
t | +0.304 |
Neg logit contributions | |
Sof | -0.197 |
Iris | -0.191 |
Joy | -0.191 |
igi | -0.185 |
Sophia | -0.184 |
Token | he |
Token ID | 339 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
op | +0.014 |
apr | +0.013 |
driver | +0.012 |
x | +0.012 |
bel | +0.012 |
Neg logit contributions | |
Sof | -0.016 |
Belle | -0.015 |
Dawn | -0.015 |
Sophia | -0.015 |
ora | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
op | +0.100 |
apr | +0.099 |
driver | +0.093 |
bel | +0.089 |
Some | +0.088 |
Neg logit contributions | |
Sof | -0.075 |
Belle | -0.071 |
ora | -0.070 |
Dawn | -0.068 |
igi | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
op | +0.030 |
apr | +0.029 |
driver | +0.028 |
bel | +0.027 |
x | +0.026 |
Neg logit contributions | |
Sof | -0.032 |
Belle | -0.031 |
Sasha | -0.030 |
Dawn | -0.030 |
igi | -0.030 |
Token | hero |
Token ID | 4293 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
igi | +0.007 |
Sof | +0.007 |
Dawn | +0.007 |
ora | +0.007 |
Sasha | +0.007 |
Neg logit contributions | |
op | -0.006 |
bel | -0.005 |
apr | -0.005 |
driver | -0.005 |
x | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
apr | +0.031 |
op | +0.031 |
bel | +0.031 |
driver | +0.030 |
x | +0.030 |
Neg logit contributions | |
Sof | -0.028 |
Belle | -0.028 |
ora | -0.027 |
igi | -0.027 |
Sasha | -0.027 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
op | +0.030 |
apr | +0.029 |
driver | +0.029 |
bel | +0.028 |
t | +0.027 |
Neg logit contributions | |
Sof | -0.025 |
igi | -0.024 |
Sasha | -0.024 |
Belle | -0.024 |
Dawn | -0.024 |
Token | for |
Token ID | 329 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
op | +0.042 |
apr | +0.041 |
bel | +0.039 |
driver | +0.038 |
Some | +0.038 |
Neg logit contributions | |
Sof | -0.062 |
Sasha | -0.060 |
Sophia | -0.059 |
Belle | -0.058 |
igi | -0.058 |
Token | make |
Token ID | 787 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
op | +0.030 |
apr | +0.028 |
bel | +0.028 |
driver | +0.027 |
t | +0.026 |
Neg logit contributions | |
Sof | -0.042 |
igi | -0.041 |
Dawn | -0.040 |
Belle | -0.040 |
ora | -0.040 |
Token | - |
Token ID | 12 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
op | +0.073 |
bel | +0.070 |
apr | +0.070 |
driver | +0.069 |
t | +0.066 |
Neg logit contributions | |
Sof | -0.078 |
Belle | -0.074 |
igi | -0.074 |
Dawn | -0.074 |
Sasha | -0.074 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
apr | +0.061 |
op | +0.054 |
laptop | +0.050 |
driver | +0.050 |
tools | +0.049 |
Neg logit contributions | |
igi | -0.078 |
Joy | -0.077 |
Sof | -0.077 |
ora | -0.077 |
Belle | -0.075 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
op | +0.346 |
apr | +0.314 |
driver | +0.312 |
inter | +0.312 |
therm | +0.304 |
Neg logit contributions | |
Joy | -0.187 |
Sof | -0.185 |
Sophia | -0.180 |
Iris | -0.179 |
igi | -0.173 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
op | +0.017 |
apr | +0.017 |
driver | +0.016 |
x | +0.016 |
Some | +0.016 |
Neg logit contributions | |
Sof | -0.016 |
Belle | -0.016 |
ora | -0.015 |
Sophia | -0.015 |
Sasha | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
Sof | +0.010 |
ora | +0.010 |
Belle | +0.010 |
Dawn | +0.010 |
Sophia | +0.010 |
Neg logit contributions | |
op | -0.010 |
apr | -0.009 |
driver | -0.009 |
bel | -0.009 |
x | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
igi | +0.000 |
Sof | +0.000 |
Dawn | +0.000 |
Belle | +0.000 |
ora | +0.000 |
Neg logit contributions | |
op | -0.000 |
apr | -0.000 |
bel | -0.000 |
driver | -0.000 |
t | -0.000 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
igi | +0.049 |
Sof | +0.049 |
Dawn | +0.048 |
Belle | +0.047 |
ora | +0.047 |
Neg logit contributions | |
op | -0.043 |
bel | -0.040 |
apr | -0.040 |
driver | -0.039 |
t | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
op | +0.001 |
bel | +0.001 |
apr | +0.001 |
driver | +0.001 |
x | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
Sophia | -0.001 |
Sasha | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
op | +0.029 |
apr | +0.029 |
bel | +0.028 |
driver | +0.028 |
t | +0.026 |
Neg logit contributions | |
Sof | -0.019 |
Belle | -0.018 |
ora | -0.018 |
Dawn | -0.018 |
igi | -0.018 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
op | +0.049 |
t | +0.045 |
driver | +0.042 |
tted | +0.038 |
bel | +0.037 |
Neg logit contributions | |
Sof | -0.077 |
Fif | -0.076 |
Gig | -0.075 |
coc | -0.075 |
turtles | -0.074 |
Token | make |
Token ID | 787 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
t | +0.073 |
op | +0.068 |
driver | +0.061 |
itt | +0.059 |
Some | +0.059 |
Neg logit contributions | |
waterfall | -0.071 |
hed | -0.068 |
Dawn | -0.068 |
turtles | -0.068 |
Sof | -0.068 |
Token | - |
Token ID | 12 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
op | +0.070 |
t | +0.069 |
driver | +0.067 |
apr | +0.065 |
bel | +0.062 |
Neg logit contributions | |
Sof | -0.061 |
Dawn | -0.057 |
Belle | -0.055 |
Sophia | -0.055 |
ora | -0.054 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
apr | +0.038 |
laptop | +0.031 |
op | +0.031 |
x | +0.030 |
therm | +0.030 |
Neg logit contributions | |
ora | -0.085 |
Joy | -0.084 |
igi | -0.084 |
Sof | -0.083 |
Kay | -0.082 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
op | +0.367 |
inter | +0.346 |
apr | +0.325 |
therm | +0.325 |
driver | +0.322 |
Neg logit contributions | |
Iris | -0.153 |
Joy | -0.149 |
Sof | -0.144 |
Sophia | -0.141 |
Kay | -0.140 |
Token | with |
Token ID | 351 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
op | +0.017 |
apr | +0.016 |
driver | +0.016 |
t | +0.015 |
x | +0.015 |
Neg logit contributions | |
Sof | -0.016 |
ora | -0.016 |
coc | -0.016 |
turtles | -0.016 |
waterfall | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
op | +0.000 |
t | +0.000 |
bel | +0.000 |
driver | +0.000 |
apr | +0.000 |
Neg logit contributions | |
Sof | -0.000 |
Dawn | -0.000 |
Sophia | -0.000 |
Belle | -0.000 |
Fif | -0.000 |
Token | friends |
Token ID | 2460 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
op | +0.034 |
driver | +0.034 |
t | +0.033 |
bel | +0.031 |
apr | +0.031 |
Neg logit contributions | |
coc | -0.027 |
Dawn | -0.027 |
Sof | -0.027 |
ora | -0.026 |
waterfall | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
Sof | +0.017 |
Belle | +0.017 |
turtles | +0.016 |
ora | +0.016 |
Dawn | +0.016 |
Neg logit contributions | |
apr | -0.020 |
bel | -0.020 |
op | -0.020 |
x | -0.020 |
t | -0.019 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
op | +0.024 |
apr | +0.024 |
driver | +0.024 |
bel | +0.023 |
x | +0.022 |
Neg logit contributions | |
Sof | -0.022 |
Dawn | -0.022 |
Belle | -0.022 |
igi | -0.021 |
Fif | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
op | +0.027 |
driver | +0.026 |
oscope | +0.024 |
x | +0.024 |
t | +0.023 |
Neg logit contributions | |
Sof | -0.054 |
Fif | -0.053 |
Gig | -0.052 |
coc | -0.051 |
Belle | -0.051 |
Token | play |
Token ID | 711 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Belle | +0.009 |
ora | +0.009 |
Dawn | +0.009 |
Sof | +0.008 |
Fif | +0.008 |
Neg logit contributions | |
op | -0.011 |
bel | -0.011 |
t | -0.011 |
driver | -0.011 |
apr | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
op | +0.005 |
driver | +0.005 |
t | +0.005 |
bel | +0.005 |
apr | +0.004 |
Neg logit contributions | |
Belle | -0.009 |
Sof | -0.009 |
Dawn | -0.009 |
Iris | -0.009 |
ora | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
op | +0.059 |
apr | +0.056 |
bel | +0.056 |
driver | +0.055 |
t | +0.053 |
Neg logit contributions | |
Sof | -0.070 |
igi | -0.069 |
Dawn | -0.068 |
Belle | -0.068 |
ora | -0.068 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
apr | +0.030 |
His | +0.025 |
x | +0.024 |
laptop | +0.024 |
op | +0.023 |
Neg logit contributions | |
ora | -0.087 |
igi | -0.085 |
Joy | -0.085 |
Belle | -0.084 |
Sof | -0.084 |
Token | ieve |
Token ID | 12311 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
op | +0.344 |
apr | +0.319 |
driver | +0.312 |
inter | +0.311 |
t | +0.306 |
Neg logit contributions | |
Iris | -0.172 |
Sof | -0.165 |
Joy | -0.163 |
igi | -0.162 |
ora | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
op | +0.009 |
apr | +0.009 |
driver | +0.009 |
His | +0.008 |
x | +0.008 |
Neg logit contributions | |
Sof | -0.012 |
ora | -0.012 |
Belle | -0.011 |
coc | -0.011 |
Joy | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
apr | +0.001 |
op | +0.001 |
This | +0.001 |
Some | +0.001 |
His | +0.001 |
Neg logit contributions | |
igi | -0.004 |
Sof | -0.004 |
Dawn | -0.004 |
ora | -0.004 |
Belle | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
igi | +0.001 |
Dawn | +0.001 |
Belle | +0.001 |
Sof | +0.001 |
ora | +0.001 |
Neg logit contributions | |
op | -0.000 |
t | -0.000 |
bel | -0.000 |
apr | -0.000 |
driver | -0.000 |
Token | One |
Token ID | 3198 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
op | +0.005 |
t | +0.005 |
apr | +0.005 |
bel | +0.004 |
time | +0.004 |
Neg logit contributions | |
igi | -0.008 |
Sof | -0.008 |
Dawn | -0.008 |
Sasha | -0.008 |
Fif | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
igi | +0.007 |
Sof | +0.006 |
ora | +0.006 |
Belle | +0.006 |
Dawn | +0.006 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
t | -0.003 |
driver | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
op | +0.061 |
bel | +0.059 |
apr | +0.059 |
driver | +0.056 |
t | +0.055 |
Neg logit contributions | |
igi | -0.062 |
Sof | -0.062 |
Dawn | -0.060 |
Belle | -0.060 |
ora | -0.059 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
op | +0.004 |
apr | +0.004 |
bel | +0.004 |
driver | +0.004 |
t | +0.003 |
Neg logit contributions | |
Sof | -0.004 |
igi | -0.004 |
Dawn | -0.004 |
Belle | -0.004 |
Sasha | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
op | +0.056 |
apr | +0.052 |
bel | +0.050 |
t | +0.049 |
driver | +0.049 |
Neg logit contributions | |
Sof | -0.089 |
Dawn | -0.085 |
Belle | -0.084 |
Sophia | -0.083 |
Joy | -0.083 |
Token | - |
Token ID | 12 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
op | +0.061 |
apr | +0.058 |
bel | +0.058 |
driver | +0.057 |
t | +0.055 |
Neg logit contributions | |
Sof | -0.067 |
Dawn | -0.064 |
Belle | -0.063 |
Sasha | -0.063 |
ora | -0.062 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
apr | +0.033 |
laptop | +0.027 |
x | +0.026 |
op | +0.026 |
driver | +0.025 |
Neg logit contributions | |
Sof | -0.102 |
Joy | -0.102 |
igi | -0.101 |
ora | -0.101 |
Belle | -0.099 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
op | +0.364 |
inter | +0.337 |
apr | +0.336 |
driver | +0.328 |
His | +0.318 |
Neg logit contributions | |
Iris | -0.164 |
Joy | -0.156 |
Sof | -0.145 |
ora | -0.140 |
Dawn | -0.139 |
Token | at |
Token ID | 379 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
op | +0.014 |
apr | +0.014 |
driver | +0.013 |
bel | +0.013 |
Some | +0.012 |
Neg logit contributions | |
Sof | -0.019 |
Dawn | -0.018 |
ora | -0.018 |
Belle | -0.018 |
Sophia | -0.018 |
Token | home |
Token ID | 1363 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
op | +0.029 |
apr | +0.028 |
bel | +0.028 |
driver | +0.027 |
t | +0.026 |
Neg logit contributions | |
Sof | -0.036 |
igi | -0.036 |
Dawn | -0.035 |
Belle | -0.035 |
ora | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
Sof | +0.020 |
Dawn | +0.019 |
Sophia | +0.018 |
ora | +0.018 |
Belle | +0.018 |
Neg logit contributions | |
apr | -0.016 |
op | -0.015 |
driver | -0.014 |
bel | -0.014 |
Some | -0.014 |
Token | too |
Token ID | 1165 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Sof | +0.028 |
igi | +0.027 |
Dawn | +0.027 |
Belle | +0.027 |
Sasha | +0.027 |
Neg logit contributions | |
op | -0.022 |
apr | -0.021 |
bel | -0.021 |
driver | -0.020 |
x | -0.019 |
Token | Finally |
Token ID | 9461 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
igi | +0.000 |
ora | +0.000 |
Sof | +0.000 |
Dawn | +0.000 |
Belle | +0.000 |
Neg logit contributions | |
op | -0.000 |
apr | -0.000 |
bel | -0.000 |
driver | -0.000 |
His | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
op | +0.028 |
apr | +0.026 |
bel | +0.026 |
driver | +0.025 |
t | +0.024 |
Neg logit contributions | |
igi | -0.053 |
Sof | -0.051 |
ora | -0.051 |
Dawn | -0.050 |
Belle | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Sof | +0.015 |
igi | +0.015 |
Dawn | +0.015 |
Belle | +0.015 |
Sasha | +0.014 |
Neg logit contributions | |
op | -0.016 |
apr | -0.015 |
bel | -0.015 |
driver | -0.015 |
x | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
coc | +0.006 |
Sof | +0.006 |
Belle | +0.006 |
waterfall | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
t | -0.007 |
op | -0.007 |
driver | -0.007 |
bel | -0.007 |
Some | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
op | +0.065 |
apr | +0.061 |
bel | +0.061 |
driver | +0.060 |
t | +0.057 |
Neg logit contributions | |
Sof | -0.084 |
igi | -0.082 |
Belle | -0.081 |
Dawn | -0.081 |
ora | -0.080 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
apr | +0.055 |
laptop | +0.050 |
His | +0.046 |
x | +0.046 |
op | +0.045 |
Neg logit contributions | |
Joy | -0.091 |
igi | -0.088 |
ora | -0.088 |
Sof | -0.086 |
Kay | -0.085 |
Token | ieve |
Token ID | 12311 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
op | +0.344 |
apr | +0.310 |
inter | +0.307 |
driver | +0.306 |
bel | +0.299 |
Neg logit contributions | |
Joy | -0.187 |
Sof | -0.181 |
Iris | -0.180 |
igi | -0.177 |
Belle | -0.171 |
Token | adventures |
Token ID | 17545 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
op | +0.021 |
apr | +0.021 |
driver | +0.020 |
Some | +0.020 |
bel | +0.019 |
Neg logit contributions | |
Sof | -0.023 |
Belle | -0.023 |
ora | -0.022 |
Sophia | -0.022 |
coc | -0.022 |
Token | were |
Token ID | 547 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
op | +0.058 |
apr | +0.058 |
Some | +0.053 |
driver | +0.052 |
bel | +0.052 |
Neg logit contributions | |
Sof | -0.066 |
Belle | -0.063 |
Dawn | -0.062 |
Sophia | -0.061 |
Sasha | -0.061 |
Token | recorded |
Token ID | 6264 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Sof | +0.002 |
Belle | +0.002 |
Sasha | +0.002 |
Dawn | +0.002 |
igi | +0.002 |
Neg logit contributions | |
op | -0.002 |
apr | -0.001 |
driver | -0.001 |
bel | -0.001 |
x | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
op | +0.058 |
apr | +0.055 |
driver | +0.053 |
bel | +0.052 |
t | +0.050 |
Neg logit contributions | |
Sof | -0.074 |
Belle | -0.071 |
Dawn | -0.069 |
Sasha | -0.069 |
Sophia | -0.069 |
Token | - |
Token ID | 12 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
driver | +0.020 |
op | +0.020 |
apr | +0.019 |
Some | +0.019 |
bel | +0.018 |
Neg logit contributions | |
Sof | -0.041 |
ora | -0.040 |
Dawn | -0.040 |
igi | -0.039 |
oph | -0.039 |
Token | up |
Token ID | 929 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
apr | +0.048 |
op | +0.047 |
driver | +0.046 |
drill | +0.045 |
x | +0.045 |
Neg logit contributions | |
igi | -0.065 |
Sof | -0.065 |
ora | -0.065 |
Dawn | -0.063 |
Fif | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Sof | +0.006 |
ora | +0.006 |
Belle | +0.006 |
Sophia | +0.005 |
Dawn | +0.005 |
Neg logit contributions | |
op | -0.005 |
apr | -0.005 |
driver | -0.004 |
Some | -0.004 |
drill | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Sof | +0.016 |
igi | +0.016 |
Dawn | +0.015 |
Belle | +0.015 |
ora | +0.015 |
Neg logit contributions | |
op | -0.010 |
apr | -0.010 |
bel | -0.010 |
driver | -0.010 |
t | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
op | +0.043 |
apr | +0.042 |
bel | +0.042 |
driver | +0.040 |
x | +0.038 |
Neg logit contributions | |
igi | -0.057 |
Sof | -0.057 |
Dawn | -0.056 |
Belle | -0.056 |
ora | -0.055 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
apr | +0.034 |
op | +0.033 |
x | +0.030 |
driver | +0.030 |
His | +0.029 |
Neg logit contributions | |
igi | -0.068 |
ora | -0.068 |
Sof | -0.068 |
Dawn | -0.066 |
Belle | -0.065 |
Token | ieve |
Token ID | 12311 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
op | +0.323 |
driver | +0.290 |
apr | +0.288 |
inter | +0.288 |
t | +0.284 |
Neg logit contributions | |
Iris | -0.184 |
Sof | -0.180 |
Joy | -0.177 |
igi | -0.177 |
ora | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
op | +0.001 |
driver | +0.001 |
apr | +0.001 |
x | +0.001 |
His | +0.001 |
Neg logit contributions | |
Sof | -0.002 |
ora | -0.002 |
Belle | -0.001 |
Dawn | -0.001 |
igi | -0.001 |
Token | One |
Token ID | 1881 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
bel | +0.003 |
driver | +0.003 |
t | +0.003 |
Neg logit contributions | |
Sof | -0.006 |
igi | -0.006 |
Dawn | -0.006 |
Belle | -0.006 |
ora | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
driver | +0.031 |
apr | +0.029 |
bel | +0.029 |
op | +0.028 |
renches | +0.027 |
Neg logit contributions | |
Sof | -0.019 |
ora | -0.018 |
Belle | -0.017 |
igi | -0.017 |
Sasha | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
bel | +0.048 |
apr | +0.048 |
op | +0.048 |
driver | +0.046 |
x | +0.044 |
Neg logit contributions | |
Sof | -0.062 |
Dawn | -0.060 |
Belle | -0.060 |
igi | -0.060 |
Sasha | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
op | +0.007 |
apr | +0.006 |
bel | +0.006 |
driver | +0.006 |
t | +0.006 |
Neg logit contributions | |
Sof | -0.011 |
igi | -0.011 |
Dawn | -0.011 |
Belle | -0.011 |
ora | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
op | +0.020 |
apr | +0.019 |
bel | +0.019 |
driver | +0.018 |
x | +0.018 |
Neg logit contributions | |
Sof | -0.017 |
igi | -0.016 |
Belle | -0.016 |
ora | -0.016 |
Dawn | -0.016 |
Token | race |
Token ID | 3234 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
op | +0.027 |
apr | +0.026 |
bel | +0.026 |
driver | +0.024 |
t | +0.024 |
Neg logit contributions | |
Sof | -0.026 |
Belle | -0.025 |
Dawn | -0.025 |
igi | -0.024 |
Sasha | -0.024 |
Token | make |
Token ID | 787 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Sof | +0.000 |
Dawn | +0.000 |
Belle | +0.000 |
ora | +0.000 |
Sophia | +0.000 |
Neg logit contributions | |
op | -0.000 |
apr | -0.000 |
bel | -0.000 |
x | -0.000 |
driver | -0.000 |
Token | - |
Token ID | 12 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
op | +0.055 |
apr | +0.054 |
t | +0.050 |
bel | +0.049 |
driver | +0.049 |
Neg logit contributions | |
Sof | -0.061 |
Dawn | -0.057 |
Belle | -0.057 |
Sasha | -0.056 |
Fif | -0.055 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
apr | +0.046 |
laptop | +0.041 |
x | +0.040 |
op | +0.039 |
therm | +0.037 |
Neg logit contributions | |
Joy | -0.081 |
Sof | -0.081 |
ora | -0.081 |
igi | -0.080 |
Belle | -0.079 |
Token | ieve |
Token ID | 12311 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
op | +0.327 |
apr | +0.301 |
inter | +0.298 |
therm | +0.294 |
driver | +0.281 |
Neg logit contributions | |
Sof | -0.178 |
Joy | -0.177 |
Iris | -0.174 |
Sophia | -0.168 |
Belle | -0.166 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
op | +0.009 |
apr | +0.009 |
x | +0.008 |
Some | +0.008 |
driver | +0.008 |
Neg logit contributions | |
Sof | -0.011 |
Belle | -0.010 |
waterfall | -0.010 |
ora | -0.010 |
Dawn | -0.010 |
Token | around |
Token ID | 1088 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
apr | +0.088 |
op | +0.080 |
x | +0.074 |
bel | +0.072 |
Some | +0.072 |
Neg logit contributions | |
Sof | -0.083 |
Belle | -0.079 |
ora | -0.077 |
waterfall | -0.077 |
Dawn | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
op | +0.069 |
apr | +0.064 |
bel | +0.062 |
t | +0.061 |
driver | +0.059 |
Neg logit contributions | |
Sof | -0.056 |
waterfall | -0.054 |
Belle | -0.052 |
Dawn | -0.052 |
Claw | -0.051 |
Token | track |
Token ID | 2610 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
Sof | +0.024 |
igi | +0.023 |
Belle | +0.023 |
Dawn | +0.023 |
ora | +0.023 |
Neg logit contributions | |
op | -0.025 |
bel | -0.024 |
apr | -0.024 |
driver | -0.023 |
t | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
op | +0.013 |
bel | +0.012 |
apr | +0.012 |
driver | +0.011 |
t | +0.011 |
Neg logit contributions | |
Sof | -0.023 |
Belle | -0.022 |
igi | -0.022 |
Dawn | -0.022 |
Sasha | -0.022 |
Token | world |
Token ID | 995 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
igi | +0.037 |
Sof | +0.037 |
Dawn | +0.036 |
ora | +0.035 |
Belle | +0.035 |
Neg logit contributions | |
op | -0.026 |
apr | -0.025 |
bel | -0.025 |
driver | -0.024 |
x | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
op | +0.014 |
apr | +0.014 |
driver | +0.013 |
bel | +0.013 |
tools | +0.012 |
Neg logit contributions | |
Sof | -0.021 |
igi | -0.020 |
ora | -0.020 |
Belle | -0.020 |
Dawn | -0.020 |
Token | make |
Token ID | 787 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
op | +0.040 |
apr | +0.040 |
bel | +0.039 |
driver | +0.037 |
x | +0.037 |
Neg logit contributions | |
igi | -0.053 |
Sof | -0.051 |
Dawn | -0.051 |
ora | -0.051 |
Belle | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
op | +0.055 |
apr | +0.053 |
bel | +0.052 |
driver | +0.051 |
t | +0.049 |
Neg logit contributions | |
Sof | -0.070 |
igi | -0.069 |
Belle | -0.068 |
Dawn | -0.068 |
ora | -0.067 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
apr | +0.031 |
op | +0.030 |
driver | +0.027 |
laptop | +0.025 |
x | +0.024 |
Neg logit contributions | |
Sof | -0.081 |
Joy | -0.081 |
Belle | -0.080 |
igi | -0.079 |
ora | -0.079 |
Token | ieve |
Token ID | 12311 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
op | +0.345 |
inter | +0.316 |
driver | +0.313 |
apr | +0.313 |
His | +0.301 |
Neg logit contributions | |
Joy | -0.164 |
Iris | -0.160 |
Sof | -0.158 |
igi | -0.150 |
Belle | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
driver | +0.003 |
bel | +0.003 |
t | +0.003 |
Neg logit contributions | |
Sof | -0.004 |
Belle | -0.004 |
igi | -0.004 |
ora | -0.004 |
Dawn | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
op | +0.004 |
apr | +0.003 |
bel | +0.003 |
driver | +0.003 |
t | +0.003 |
Neg logit contributions | |
igi | -0.005 |
Sof | -0.005 |
Dawn | -0.005 |
ora | -0.005 |
Belle | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
op | +0.001 |
bel | +0.001 |
apr | +0.001 |
t | +0.001 |
driver | +0.001 |
Neg logit contributions | |
igi | -0.001 |
Sof | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
ora | -0.001 |
Token | She |
Token ID | 3347 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
op | +0.008 |
bel | +0.008 |
apr | +0.007 |
t | +0.007 |
driver | +0.007 |
Neg logit contributions | |
Sof | -0.009 |
igi | -0.009 |
Dawn | -0.009 |
Belle | -0.009 |
ora | -0.009 |
Token | red |
Token ID | 2266 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
op | +0.054 |
driver | +0.050 |
t | +0.048 |
made | +0.048 |
auc | +0.047 |
Neg logit contributions | |
coc | -0.034 |
pearl | -0.034 |
deer | -0.032 |
Belle | -0.031 |
waterfall | -0.030 |
Token | cape |
Token ID | 36023 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
itt | +0.091 |
op | +0.086 |
made | +0.085 |
t | +0.085 |
tted | +0.083 |
Neg logit contributions | |
coc | -0.054 |
pearl | -0.050 |
deer | -0.048 |
waterfall | -0.048 |
maid | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
apr | +0.106 |
op | +0.104 |
Some | +0.100 |
itt | +0.098 |
x | +0.097 |
Neg logit contributions | |
Sof | -0.074 |
Belle | -0.071 |
igi | -0.068 |
Dove | -0.067 |
ora | -0.063 |
Token | make |
Token ID | 787 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Belle | +0.004 |
Sof | +0.004 |
Sasha | +0.004 |
Fif | +0.004 |
coc | +0.004 |
Neg logit contributions | |
op | -0.004 |
t | -0.004 |
apr | -0.004 |
driver | -0.003 |
bel | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
op | +0.064 |
driver | +0.059 |
apr | +0.059 |
t | +0.059 |
bel | +0.056 |
Neg logit contributions | |
Sof | -0.046 |
Belle | -0.044 |
Dawn | -0.042 |
Sasha | -0.041 |
igi | -0.041 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
apr | +0.032 |
laptop | +0.026 |
op | +0.024 |
His | +0.023 |
x | +0.023 |
Neg logit contributions | |
igi | -0.078 |
swoop | -0.075 |
ora | -0.075 |
Joy | -0.074 |
Sof | -0.074 |
Token | ieve |
Token ID | 12311 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
op | +0.347 |
inter | +0.316 |
apr | +0.310 |
driver | +0.307 |
t | +0.303 |
Neg logit contributions | |
Iris | -0.158 |
Joy | -0.151 |
igi | -0.147 |
Belle | -0.147 |
Sof | -0.146 |
Token | he |
Token ID | 339 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
op | +0.000 |
apr | +0.000 |
driver | +0.000 |
Some | +0.000 |
x | +0.000 |
Neg logit contributions | |
Sof | -0.000 |
coc | -0.000 |
Belle | -0.000 |
ora | -0.000 |
waterfall | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
op | +0.090 |
apr | +0.089 |
driver | +0.082 |
itt | +0.080 |
Some | +0.080 |
Neg logit contributions | |
forgot | -0.048 |
Sof | -0.048 |
ora | -0.046 |
Belle | -0.046 |
forget | -0.046 |
Token | super |
Token ID | 2208 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
op | +0.006 |
apr | +0.005 |
driver | +0.005 |
bel | +0.005 |
x | +0.005 |
Neg logit contributions | |
Sof | -0.008 |
Belle | -0.007 |
igi | -0.007 |
Sophia | -0.007 |
Sasha | -0.007 |
Token | powers |
Token ID | 30132 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
apr | +0.029 |
op | +0.027 |
driver | +0.027 |
mixer | +0.026 |
x | +0.026 |
Neg logit contributions | |
coc | -0.018 |
forgot | -0.017 |
ora | -0.017 |
Sof | -0.017 |
forget | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Sof | +0.007 |
Belle | +0.006 |
Sophia | +0.006 |
Dawn | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
apr | -0.007 |
op | -0.007 |
bel | -0.006 |
x | -0.006 |
Some | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
igi | +0.008 |
Sof | +0.007 |
Dawn | +0.007 |
ora | +0.007 |
Belle | +0.007 |
Neg logit contributions | |
op | -0.006 |
bel | -0.006 |
apr | -0.006 |
driver | -0.006 |
t | -0.005 |
Token | played |
Token ID | 2826 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
igi | +0.002 |
Sof | +0.002 |
Dawn | +0.002 |
Belle | +0.002 |
ora | +0.002 |
Neg logit contributions | |
op | -0.002 |
bel | -0.002 |
apr | -0.002 |
driver | -0.002 |
t | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
op | +0.011 |
apr | +0.010 |
driver | +0.009 |
t | +0.009 |
bel | +0.009 |
Neg logit contributions | |
Sof | -0.012 |
Dawn | -0.011 |
Belle | -0.011 |
Iris | -0.011 |
Joy | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
op | +0.052 |
apr | +0.050 |
bel | +0.049 |
driver | +0.049 |
t | +0.047 |
Neg logit contributions | |
Sof | -0.064 |
Belle | -0.061 |
Dawn | -0.060 |
ora | -0.060 |
igi | -0.059 |
Token | bel |
Token ID | 6667 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
apr | +0.025 |
op | +0.021 |
x | +0.020 |
laptop | +0.018 |
tools | +0.017 |
Neg logit contributions | |
igi | -0.092 |
Sof | -0.090 |
ora | -0.089 |
Joy | -0.089 |
Kay | -0.088 |
Token | ieve |
Token ID | 12311 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
op | +0.338 |
inter | +0.312 |
driver | +0.306 |
apr | +0.302 |
His | +0.297 |
Neg logit contributions | |
Iris | -0.164 |
Joy | -0.157 |
Sof | -0.148 |
ora | -0.144 |
igi | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Sof | +0.000 |
ora | +0.000 |
Belle | +0.000 |
Dawn | +0.000 |
Sophia | +0.000 |
Neg logit contributions | |
op | -0.000 |
apr | -0.000 |
driver | -0.000 |
x | -0.000 |
bel | -0.000 |
Token | Finally |
Token ID | 9461 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
igi | +0.005 |
Sof | +0.005 |
Dawn | +0.005 |
Belle | +0.005 |
ora | +0.005 |
Neg logit contributions | |
op | -0.006 |
apr | -0.006 |
bel | -0.006 |
driver | -0.006 |
t | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
op | +0.019 |
apr | +0.017 |
t | +0.016 |
His | +0.016 |
driver | +0.015 |
Neg logit contributions | |
igi | -0.054 |
ora | -0.051 |
Joy | -0.051 |
Sof | -0.050 |
Dawn | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
igi | +0.019 |
Sof | +0.019 |
Dawn | +0.018 |
Belle | +0.018 |
ora | +0.018 |
Neg logit contributions | |
op | -0.020 |
apr | -0.020 |
bel | -0.020 |
driver | -0.019 |
t | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
op | +0.000 |
apr | +0.000 |
bel | +0.000 |
driver | +0.000 |
x | +0.000 |
Neg logit contributions | |
igi | -0.000 |
Sof | -0.000 |
ora | -0.000 |
Belle | -0.000 |
Dawn | -0.000 |
Token | purple |
Token ID | 14032 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
op | +0.012 |
bel | +0.011 |
apr | +0.011 |
t | +0.010 |
driver | +0.010 |
Neg logit contributions | |
igi | -0.023 |
Sof | -0.022 |
Belle | -0.022 |
Dawn | -0.022 |
ora | -0.022 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
op | +0.030 |
apr | +0.030 |
bel | +0.030 |
driver | +0.028 |
x | +0.028 |
Neg logit contributions | |
Sof | -0.014 |
igi | -0.013 |
Dawn | -0.013 |
ora | -0.013 |
Belle | -0.013 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
apr | +0.036 |
driver | +0.035 |
op | +0.034 |
bel | +0.034 |
x | +0.033 |
Neg logit contributions | |
Sof | -0.023 |
Dawn | -0.021 |
Fif | -0.020 |
Belle | -0.020 |
Sasha | -0.019 |
Token | Jo |
Token ID | 5302 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Sof | +0.008 |
Dawn | +0.008 |
Fif | +0.008 |
Belle | +0.007 |
Sasha | +0.007 |
Neg logit contributions | |
apr | -0.014 |
bel | -0.013 |
driver | -0.013 |
op | -0.013 |
oscope | -0.013 |
Token | jo |
Token ID | 7639 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
apr | +0.138 |
bel | +0.125 |
tools | +0.123 |
op | +0.121 |
driver | +0.120 |
Neg logit contributions | |
Sof | -0.151 |
igi | -0.148 |
iki | -0.141 |
ora | -0.140 |
Sasha | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
apr | +0.207 |
bel | +0.203 |
driver | +0.195 |
op | +0.194 |
x | +0.189 |
Neg logit contributions | |
Sof | -0.225 |
Sasha | -0.207 |
Sophia | -0.207 |
Belle | -0.207 |
Dawn | -0.205 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
apr | +0.035 |
bel | +0.033 |
driver | +0.032 |
x | +0.032 |
op | +0.030 |
Neg logit contributions | |
Sof | -0.031 |
Belle | -0.029 |
Dawn | -0.029 |
Sasha | -0.029 |
Fif | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
apr | +0.018 |
bel | +0.017 |
driver | +0.017 |
laptop | +0.016 |
op | +0.016 |
Neg logit contributions | |
Sof | -0.017 |
igi | -0.016 |
Dawn | -0.016 |
Belle | -0.016 |
Joy | -0.016 |
Token | His |
Token ID | 6653 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
apr | +0.019 |
driver | +0.018 |
bel | +0.018 |
x | +0.018 |
op | +0.018 |
Neg logit contributions | |
Sof | -0.015 |
ora | -0.015 |
igi | -0.015 |
Joy | -0.015 |
Dawn | -0.015 |
Token | mum |
Token ID | 25682 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
op | +0.043 |
bel | +0.042 |
apr | +0.042 |
driver | +0.041 |
t | +0.040 |
Neg logit contributions | |
Sof | -0.038 |
igi | -0.037 |
Belle | -0.037 |
Dawn | -0.037 |
ora | -0.037 |
Token | suggested |
Token ID | 5220 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
apr | +0.039 |
bel | +0.039 |
driver | +0.038 |
op | +0.037 |
x | +0.036 |
Neg logit contributions | |
Sof | -0.026 |
ora | -0.025 |
Sasha | -0.025 |
Joy | -0.025 |
Belle | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Sof | +0.029 |
Sasha | +0.027 |
Dawn | +0.027 |
Sophia | +0.027 |
Fif | +0.026 |
Neg logit contributions | |
apr | -0.038 |
op | -0.038 |
bel | -0.037 |
oscope | -0.037 |
driver | -0.036 |
Token | just |
Token ID | 655 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
apr | +0.037 |
op | +0.036 |
bel | +0.035 |
itt | +0.033 |
iren | +0.033 |
Neg logit contributions | |
Sof | -0.027 |
forget | -0.027 |
Dawn | -0.026 |
Belle | -0.026 |
Joy | -0.026 |
Token | use |
Token ID | 779 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Sof | +0.004 |
Belle | +0.004 |
Dawn | +0.004 |
Fif | +0.004 |
Sasha | +0.004 |
Neg logit contributions | |
op | -0.005 |
apr | -0.005 |
bel | -0.005 |
t | -0.005 |
driver | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
bel | +0.038 |
t | +0.036 |
op | +0.036 |
driver | +0.032 |
washer | +0.032 |
Neg logit contributions | |
Sof | -0.021 |
Sasha | -0.020 |
Dawn | -0.020 |
Belle | -0.020 |
Patty | -0.019 |
Token | imag |
Token ID | 3590 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
bel | +0.044 |
driver | +0.039 |
t | +0.039 |
washer | +0.038 |
His | +0.038 |
Neg logit contributions | |
Sasha | -0.033 |
coc | -0.033 |
Belle | -0.032 |
Patty | -0.031 |
iki | -0.031 |
Token | inations |
Token ID | 7352 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
His | +0.279 |
This | +0.270 |
Some | +0.260 |
driver | +0.257 |
bel | +0.256 |
Neg logit contributions | |
igi | -0.106 |
ora | -0.103 |
Sof | -0.090 |
iki | -0.089 |
coc | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
apr | +0.103 |
op | +0.102 |
bel | +0.098 |
Some | +0.098 |
itt | +0.098 |
Neg logit contributions | |
Sof | -0.139 |
Sasha | -0.132 |
Sophia | -0.132 |
Belle | -0.129 |
ora | -0.125 |
Token | She |
Token ID | 1375 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
Sof | +0.002 |
Belle | +0.002 |
Sasha | +0.002 |
Dawn | +0.002 |
igi | +0.002 |
Neg logit contributions | |
op | -0.002 |
bel | -0.001 |
apr | -0.001 |
driver | -0.001 |
x | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Sof | +0.023 |
igi | +0.023 |
Belle | +0.023 |
ora | +0.022 |
Dawn | +0.022 |
Neg logit contributions | |
op | -0.033 |
bel | -0.033 |
apr | -0.032 |
driver | -0.031 |
x | -0.030 |
Token | that |
Token ID | 326 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
Sof | +0.043 |
Dawn | +0.041 |
Sasha | +0.041 |
Belle | +0.041 |
Fif | +0.041 |
Neg logit contributions | |
apr | -0.061 |
op | -0.060 |
bel | -0.060 |
laptop | -0.058 |
x | -0.057 |
Token | Winston |
Token ID | 21400 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
apr | +0.009 |
op | +0.009 |
bel | +0.009 |
driver | +0.008 |
itt | +0.008 |
Neg logit contributions | |
Sof | -0.010 |
Belle | -0.010 |
Dawn | -0.009 |
Sasha | -0.009 |
Patty | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
op | +0.010 |
apr | +0.010 |
bel | +0.010 |
driver | +0.009 |
x | +0.009 |
Neg logit contributions | |
Sof | -0.009 |
igi | -0.009 |
Dawn | -0.009 |
Belle | -0.009 |
ora | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -7.84e-03 |
Pos logit contributions | |
bel | +0.009 |
op | +0.009 |
apr | +0.008 |
driver | +0.007 |
laptop | +0.007 |
Neg logit contributions | |
Sof | -0.024 |
Fif | -0.023 |
Sasha | -0.023 |
Dawn | -0.022 |
Belle | -0.022 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
op | +0.000 |
bel | +0.000 |
apr | +0.000 |
x | +0.000 |
t | +0.000 |
Neg logit contributions | |
igi | -0.000 |
Sof | -0.000 |
ora | -0.000 |
Belle | -0.000 |
oph | -0.000 |
Token | Jo |
Token ID | 5302 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
igi | +0.012 |
Sof | +0.011 |
ora | +0.011 |
oph | +0.011 |
Joy | +0.011 |
Neg logit contributions | |
op | -0.011 |
apr | -0.010 |
bel | -0.010 |
x | -0.010 |
driver | -0.010 |
Token | jo |
Token ID | 7639 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
apr | +0.149 |
tools | +0.146 |
driver | +0.140 |
renches | +0.140 |
bel | +0.135 |
Neg logit contributions | |
iki | -0.116 |
Sof | -0.115 |
bi | -0.112 |
Sasha | -0.112 |
igi | -0.111 |
Token | safe |
Token ID | 3338 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
bel | +0.219 |
op | +0.217 |
driver | +0.216 |
apr | +0.209 |
Some | +0.202 |
Neg logit contributions | |
Sof | -0.180 |
Sasha | -0.175 |
Belle | -0.173 |
Dawn | -0.172 |
coc | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Sof | +0.048 |
Dawn | +0.046 |
igi | +0.046 |
Belle | +0.046 |
Sasha | +0.045 |
Neg logit contributions | |
op | -0.037 |
apr | -0.036 |
bel | -0.035 |
driver | -0.033 |
x | -0.032 |
Token | so |
Token ID | 523 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Sof | +0.005 |
Dawn | +0.005 |
Sasha | +0.005 |
Belle | +0.005 |
Fif | +0.005 |
Neg logit contributions | |
op | -0.006 |
bel | -0.006 |
apr | -0.006 |
driver | -0.005 |
x | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Sof | +0.021 |
Dawn | +0.020 |
igi | +0.020 |
Belle | +0.020 |
Sasha | +0.019 |
Neg logit contributions | |
apr | -0.014 |
op | -0.014 |
bel | -0.013 |
driver | -0.013 |
x | -0.013 |
Token | chased |
Token ID | 26172 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
op | +0.054 |
bel | +0.052 |
apr | +0.051 |
driver | +0.051 |
t | +0.050 |
Neg logit contributions | |
Sof | -0.048 |
igi | -0.048 |
Dawn | -0.046 |
Belle | -0.046 |
ora | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
Sof | +0.017 |
Dawn | +0.017 |
igi | +0.017 |
Belle | +0.017 |
ora | +0.017 |
Neg logit contributions | |
op | -0.010 |
apr | -0.010 |
bel | -0.009 |
driver | -0.009 |
x | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
op | +0.002 |
apr | +0.002 |
bel | +0.002 |
driver | +0.002 |
t | +0.002 |
Neg logit contributions | |
igi | -0.003 |
Sof | -0.003 |
Dawn | -0.003 |
ora | -0.003 |
Belle | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
igi | +0.042 |
Sof | +0.040 |
ora | +0.039 |
Belle | +0.038 |
Iris | +0.038 |
Neg logit contributions | |
op | -0.033 |
apr | -0.030 |
t | -0.029 |
bel | -0.029 |
driver | -0.028 |
Token | used |
Token ID | 973 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
igi | +0.011 |
ora | +0.010 |
Sof | +0.010 |
Dawn | +0.010 |
Belle | +0.010 |
Neg logit contributions | |
apr | -0.008 |
op | -0.008 |
bel | -0.008 |
tools | -0.007 |
t | -0.007 |
Token | their |
Token ID | 511 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Sof | +0.029 |
Dawn | +0.028 |
Belle | +0.028 |
igi | +0.028 |
Sasha | +0.028 |
Neg logit contributions | |
op | -0.025 |
bel | -0.024 |
apr | -0.024 |
driver | -0.023 |
t | -0.022 |
Token | imag |
Token ID | 3590 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
op | +0.036 |
bel | +0.035 |
apr | +0.035 |
driver | +0.035 |
x | +0.034 |
Neg logit contributions | |
Sof | -0.021 |
igi | -0.020 |
Belle | -0.020 |
Dawn | -0.020 |
ora | -0.020 |
Token | inations |
Token ID | 7352 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
driver | +0.232 |
His | +0.230 |
bel | +0.225 |
apr | +0.224 |
x | +0.222 |
Neg logit contributions | |
ora | -0.154 |
igi | -0.154 |
Sof | -0.152 |
Sophia | -0.144 |
Dawn | -0.144 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
op | +0.086 |
apr | +0.085 |
x | +0.082 |
bel | +0.080 |
Some | +0.076 |
Neg logit contributions | |
Sof | -0.160 |
Belle | -0.154 |
Sasha | -0.154 |
Sophia | -0.153 |
Dawn | -0.151 |
Token | their |
Token ID | 511 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
op | +0.004 |
bel | +0.004 |
apr | +0.004 |
driver | +0.004 |
t | +0.004 |
Neg logit contributions | |
igi | -0.004 |
Sof | -0.004 |
ora | -0.004 |
Dawn | -0.004 |
Belle | -0.004 |
Token | net |
Token ID | 2010 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
op | +0.001 |
apr | +0.001 |
bel | +0.001 |
driver | +0.001 |
t | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
igi | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
ora | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Sof | +0.048 |
Belle | +0.047 |
Dawn | +0.047 |
igi | +0.047 |
ora | +0.046 |
Neg logit contributions | |
op | -0.042 |
apr | -0.042 |
x | -0.039 |
driver | -0.039 |
bel | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Sof | +0.028 |
Dawn | +0.027 |
igi | +0.027 |
Belle | +0.027 |
Sasha | +0.027 |
Neg logit contributions | |
apr | -0.022 |
op | -0.020 |
bel | -0.020 |
driver | -0.019 |
x | -0.018 |
Token | tried |
Token ID | 3088 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
op | +0.004 |
bel | +0.004 |
apr | +0.004 |
driver | +0.004 |
t | +0.004 |
Neg logit contributions | |
igi | -0.004 |
Sof | -0.004 |
Dawn | -0.004 |
Belle | -0.004 |
ora | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Sof | +0.103 |
igi | +0.102 |
Dawn | +0.101 |
Belle | +0.101 |
ora | +0.100 |
Neg logit contributions | |
op | -0.018 |
apr | -0.016 |
bel | -0.015 |
driver | -0.014 |
x | -0.011 |
Token | keep |
Token ID | 1394 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
op | +0.007 |
bel | +0.007 |
apr | +0.007 |
driver | +0.007 |
x | +0.007 |
Neg logit contributions | |
igi | -0.011 |
Sof | -0.011 |
Dawn | -0.011 |
ora | -0.011 |
Belle | -0.011 |
Token | Jo |
Token ID | 5302 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
igi | +0.027 |
oph | +0.027 |
ora | +0.027 |
Sof | +0.027 |
Joy | +0.026 |
Neg logit contributions | |
op | -0.023 |
x | -0.022 |
apr | -0.021 |
tools | -0.021 |
driver | -0.021 |
Token | jo |
Token ID | 7639 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
apr | +0.140 |
tools | +0.135 |
renches | +0.130 |
driver | +0.128 |
bel | +0.123 |
Neg logit contributions | |
Sof | -0.112 |
iki | -0.112 |
Sasha | -0.111 |
igi | -0.111 |
bi | -0.110 |
Token | calm |
Token ID | 9480 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
op | +0.208 |
driver | +0.206 |
apr | +0.200 |
bel | +0.198 |
Some | +0.195 |
Neg logit contributions | |
Sof | -0.183 |
Sasha | -0.179 |
Belle | -0.177 |
coc | -0.174 |
Joy | -0.171 |
Token | by |
Token ID | 416 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Sof | +0.010 |
Dawn | +0.010 |
Belle | +0.010 |
ora | +0.010 |
Sasha | +0.010 |
Neg logit contributions | |
apr | -0.008 |
op | -0.008 |
bel | -0.008 |
driver | -0.007 |
t | -0.007 |
Token | talking |
Token ID | 3375 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
op | +0.019 |
apr | +0.019 |
bel | +0.018 |
driver | +0.018 |
t | +0.017 |
Neg logit contributions | |
Sof | -0.018 |
igi | -0.018 |
Dawn | -0.018 |
Belle | -0.017 |
Sasha | -0.017 |
Token | softly |
Token ID | 26625 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
apr | +0.040 |
op | +0.039 |
bel | +0.037 |
itt | +0.035 |
driver | +0.035 |
Neg logit contributions | |
Sof | -0.048 |
Dawn | -0.045 |
Sasha | -0.045 |
Belle | -0.044 |
Sophia | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Sof | +0.001 |
Belle | +0.001 |
Sasha | +0.001 |
Dawn | +0.001 |
ora | +0.001 |
Neg logit contributions | |
apr | -0.001 |
op | -0.001 |
bel | -0.001 |
driver | -0.001 |
t | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Belle | +0.001 |
Iris | +0.001 |
Dawn | +0.001 |
Sof | +0.001 |
Sasha | +0.001 |
Neg logit contributions | |
op | -0.002 |
bel | -0.002 |
driver | -0.002 |
drill | -0.001 |
apr | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Sof | +0.004 |
igi | +0.004 |
Dawn | +0.004 |
Belle | +0.004 |
Joy | +0.004 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
x | -0.003 |
Token | With |
Token ID | 3152 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
op | +0.005 |
driver | +0.005 |
bel | +0.005 |
apr | +0.005 |
drill | +0.005 |
Neg logit contributions | |
Joy | -0.003 |
igi | -0.003 |
oph | -0.003 |
Iris | -0.003 |
Belle | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Sof | +0.043 |
Belle | +0.042 |
Dawn | +0.042 |
Sasha | +0.042 |
Sophia | +0.041 |
Neg logit contributions | |
op | -0.043 |
bel | -0.041 |
t | -0.039 |
driver | -0.039 |
oscope | -0.037 |
Token | cr |
Token ID | 1067 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
op | +0.038 |
bel | +0.037 |
driver | +0.037 |
t | +0.037 |
shirt | +0.035 |
Neg logit contributions | |
Belle | -0.042 |
Sof | -0.041 |
coc | -0.041 |
Dawn | -0.039 |
Sasha | -0.039 |
Token | ay |
Token ID | 323 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
apr | +0.112 |
laptop | +0.100 |
x | +0.097 |
machine | +0.092 |
bel | +0.090 |
Neg logit contributions | |
igi | -0.187 |
oph | -0.184 |
iki | -0.182 |
ora | -0.176 |
Dawn | -0.175 |
Token | ons |
Token ID | 684 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
bel | +0.194 |
apr | +0.171 |
belt | +0.167 |
tant | +0.165 |
laptop | +0.163 |
Neg logit contributions | |
iki | -0.186 |
Belle | -0.179 |
Sasha | -0.176 |
coc | -0.174 |
igi | -0.173 |
Token | in |
Token ID | 287 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
apr | +0.074 |
x | +0.070 |
laptop | +0.066 |
shirt | +0.065 |
op | +0.065 |
Neg logit contributions | |
Belle | -0.065 |
Sof | -0.062 |
Dawn | -0.061 |
Sasha | -0.061 |
Patty | -0.058 |
Token | hand |
Token ID | 1021 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
op | +0.028 |
bel | +0.026 |
apr | +0.025 |
driver | +0.024 |
washer | +0.024 |
Neg logit contributions | |
Sof | -0.025 |
Belle | -0.025 |
Dawn | -0.024 |
Sasha | -0.024 |
Sophia | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
apr | +0.037 |
bel | +0.036 |
x | +0.034 |
op | +0.034 |
rain | +0.034 |
Neg logit contributions | |
Sof | -0.024 |
Sasha | -0.023 |
Belle | -0.023 |
Dawn | -0.023 |
Sophia | -0.023 |
Token | Emma |
Token ID | 18966 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Belle | +0.020 |
Iris | +0.019 |
Dawn | +0.019 |
Sof | +0.019 |
Sasha | +0.018 |
Neg logit contributions | |
op | -0.033 |
bel | -0.030 |
driver | -0.030 |
apr | -0.030 |
oscope | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
apr | +0.021 |
op | +0.020 |
bel | +0.020 |
driver | +0.019 |
x | +0.018 |
Neg logit contributions | |
Sof | -0.043 |
Dawn | -0.042 |
Sophia | -0.041 |
Sasha | -0.040 |
Belle | -0.040 |
Token | him |
Token ID | 683 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
op | +0.074 |
apr | +0.072 |
bel | +0.072 |
driver | +0.069 |
t | +0.067 |
Neg logit contributions | |
igi | -0.091 |
Sof | -0.089 |
Belle | -0.087 |
ora | -0.087 |
Dawn | -0.087 |
Token | for |
Token ID | 329 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
apr | +0.082 |
bel | +0.082 |
op | +0.079 |
driver | +0.074 |
t | +0.070 |
Neg logit contributions | |
Sof | -0.077 |
Dawn | -0.072 |
Belle | -0.071 |
Sasha | -0.070 |
Sophia | -0.070 |
Token | using |
Token ID | 1262 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
op | +0.062 |
bel | +0.059 |
apr | +0.058 |
driver | +0.057 |
t | +0.057 |
Neg logit contributions | |
Sof | -0.043 |
Dawn | -0.042 |
igi | -0.041 |
Belle | -0.040 |
Sasha | -0.040 |
Token | his |
Token ID | 465 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
op | +0.010 |
bel | +0.010 |
t | +0.009 |
driver | +0.008 |
itt | +0.008 |
Neg logit contributions | |
Sof | -0.007 |
Dawn | -0.007 |
Sophia | -0.006 |
Nora | -0.006 |
Sasha | -0.006 |
Token | imag |
Token ID | 3590 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
op | +0.056 |
t | +0.051 |
itt | +0.048 |
bel | +0.048 |
driver | +0.046 |
Neg logit contributions | |
mistake | -0.040 |
waterfall | -0.040 |
Dawn | -0.039 |
turtles | -0.038 |
pearl | -0.038 |
Token | inations |
Token ID | 7352 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
His | +0.268 |
This | +0.259 |
Some | +0.257 |
driver | +0.254 |
tr | +0.253 |
Neg logit contributions | |
igi | -0.093 |
ora | -0.092 |
agree | -0.072 |
ida | -0.071 |
ulu | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
op | +0.118 |
apr | +0.116 |
x | +0.113 |
Some | +0.111 |
bel | +0.108 |
Neg logit contributions | |
Sof | -0.108 |
Sophia | -0.102 |
Belle | -0.099 |
Sasha | -0.099 |
forgetting | -0.098 |
Token | create |
Token ID | 2251 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Dawn | +0.007 |
waterfall | +0.007 |
Sof | +0.007 |
Belle | +0.007 |
ora | +0.007 |
Neg logit contributions | |
op | -0.008 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
t | -0.007 |
Token | something |
Token ID | 1223 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
op | +0.075 |
t | +0.068 |
bel | +0.067 |
driver | +0.066 |
apr | +0.065 |
Neg logit contributions | |
Sof | -0.076 |
Belle | -0.074 |
Dawn | -0.074 |
Sophia | -0.072 |
Sasha | -0.071 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Sof | +0.028 |
Dawn | +0.028 |
Belle | +0.027 |
ora | +0.027 |
waterfall | +0.026 |
Neg logit contributions | |
op | -0.028 |
apr | -0.028 |
driver | -0.027 |
oscope | -0.026 |
bel | -0.026 |
Token | y |
Token ID | 331 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
op | +0.027 |
bel | +0.027 |
apr | +0.026 |
t | +0.025 |
driver | +0.024 |
Neg logit contributions | |
igi | -0.032 |
Sof | -0.032 |
Belle | -0.031 |
Dawn | -0.031 |
ora | -0.031 |
Token | ummy |
Token ID | 13513 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Sof | +0.023 |
igi | +0.022 |
Dawn | +0.022 |
ora | +0.022 |
Belle | +0.022 |
Neg logit contributions | |
bel | -0.019 |
apr | -0.018 |
op | -0.018 |
driver | -0.017 |
x | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
Sof | +0.011 |
igi | +0.011 |
Dawn | +0.010 |
Belle | +0.010 |
ora | +0.010 |
Neg logit contributions | |
op | -0.007 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
t | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
op | +0.002 |
apr | +0.002 |
bel | +0.002 |
driver | +0.002 |
His | +0.001 |
Neg logit contributions | |
igi | -0.003 |
Sof | -0.003 |
ora | -0.003 |
Dawn | -0.003 |
Belle | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Sof | +0.029 |
igi | +0.028 |
Dawn | +0.028 |
Belle | +0.028 |
ora | +0.027 |
Neg logit contributions | |
op | -0.021 |
apr | -0.020 |
bel | -0.020 |
driver | -0.019 |
t | -0.018 |
Token | Sally |
Token ID | 25737 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
His | +0.020 |
apr | +0.020 |
op | +0.020 |
driver | +0.020 |
bel | +0.020 |
Neg logit contributions | |
igi | -0.021 |
ora | -0.020 |
Joy | -0.019 |
oph | -0.018 |
Dawn | -0.018 |
Token | were |
Token ID | 547 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
igi | +0.102 |
Sof | +0.097 |
Dawn | +0.096 |
ora | +0.094 |
Belle | +0.093 |
Neg logit contributions | |
op | -0.074 |
apr | -0.069 |
bel | -0.068 |
t | -0.064 |
His | -0.063 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
apr | +0.009 |
His | +0.009 |
op | +0.009 |
fixing | +0.009 |
to | +0.009 |
Neg logit contributions | |
ora | -0.025 |
igi | -0.024 |
oph | -0.024 |
Belle | -0.023 |
Dawn | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
op | +0.036 |
bel | +0.033 |
apr | +0.032 |
to | +0.032 |
t | +0.031 |
Neg logit contributions | |
igi | -0.096 |
ora | -0.092 |
Sof | -0.091 |
Joy | -0.091 |
Belle | -0.091 |
Token | they |
Token ID | 484 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
op | +0.005 |
apr | +0.005 |
bel | +0.005 |
t | +0.005 |
His | +0.005 |
Neg logit contributions | |
igi | -0.007 |
ora | -0.006 |
Sof | -0.006 |
Joy | -0.006 |
Belle | -0.006 |
Token | shared |
Token ID | 4888 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
bel | +0.014 |
t | +0.013 |
op | +0.013 |
apr | +0.013 |
driver | +0.012 |
Neg logit contributions | |
Sof | -0.017 |
igi | -0.017 |
Sasha | -0.016 |
ora | -0.016 |
Dawn | -0.016 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
bars | +0.079 |
bel | +0.079 |
bell | +0.078 |
t | +0.078 |
apr | +0.077 |
Neg logit contributions | |
Fif | -0.066 |
Dawn | -0.065 |
waterfall | -0.064 |
Iris | -0.063 |
Sof | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
apr | +0.082 |
headphones | +0.078 |
driver | +0.077 |
bel | +0.075 |
op | +0.074 |
Neg logit contributions | |
Sandy | -0.027 |
Sof | -0.026 |
waterfall | -0.026 |
forgetting | -0.025 |
turtles | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Sof | +0.015 |
Dawn | +0.014 |
Belle | +0.014 |
Sasha | +0.014 |
Sophia | +0.014 |
Neg logit contributions | |
op | -0.013 |
bel | -0.012 |
apr | -0.012 |
driver | -0.012 |
x | -0.011 |
Token | found |
Token ID | 1043 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
op | +0.052 |
apr | +0.051 |
bel | +0.050 |
driver | +0.049 |
t | +0.047 |
Neg logit contributions | |
Sof | -0.047 |
igi | -0.046 |
Belle | -0.045 |
Dawn | -0.045 |
ora | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
op | +0.018 |
bel | +0.017 |
apr | +0.017 |
laptop | +0.016 |
t | +0.016 |
Neg logit contributions | |
Sof | -0.023 |
Dawn | -0.023 |
Sasha | -0.022 |
Belle | -0.022 |
igi | -0.022 |
Token | sour |
Token ID | 11348 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Sof | +0.035 |
igi | +0.035 |
Belle | +0.034 |
ora | +0.034 |
Dawn | +0.034 |
Neg logit contributions | |
op | -0.017 |
bel | -0.016 |
apr | -0.016 |
x | -0.015 |
driver | -0.015 |
Token | fruit |
Token ID | 8234 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
igi | +0.121 |
Sof | +0.120 |
Belle | +0.116 |
Joy | +0.116 |
Dawn | +0.114 |
Neg logit contributions | |
op | -0.092 |
apr | -0.084 |
driver | -0.083 |
x | -0.083 |
bel | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
igi | +0.098 |
Sof | +0.098 |
Belle | +0.097 |
Dawn | +0.097 |
ora | +0.096 |
Neg logit contributions | |
op | -0.041 |
driver | -0.037 |
apr | -0.035 |
bel | -0.035 |
t | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
bel | +0.006 |
op | +0.006 |
apr | +0.006 |
driver | +0.006 |
x | +0.005 |
Neg logit contributions | |
Sof | -0.010 |
Sophia | -0.009 |
Sasha | -0.009 |
Belle | -0.009 |
Dawn | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
op | +0.007 |
apr | +0.007 |
bel | +0.006 |
driver | +0.006 |
t | +0.006 |
Neg logit contributions | |
igi | -0.008 |
Sof | -0.008 |
Belle | -0.007 |
Dawn | -0.007 |
ora | -0.007 |
Token | never |
Token ID | 1239 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Sof | +0.009 |
igi | +0.009 |
Belle | +0.009 |
Sasha | +0.009 |
Dawn | +0.009 |
Neg logit contributions | |
op | -0.010 |
bel | -0.010 |
apr | -0.009 |
driver | -0.009 |
laptop | -0.009 |
Token | stop |
Token ID | 2245 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
bel | +0.007 |
op | +0.006 |
apr | +0.006 |
driver | +0.006 |
Some | +0.006 |
Neg logit contributions | |
Dawn | -0.009 |
Sof | -0.009 |
ora | -0.008 |
igi | -0.008 |
Belle | -0.008 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Sof | +0.014 |
Dawn | +0.014 |
forgetting | +0.013 |
Sasha | +0.013 |
Belle | +0.013 |
Neg logit contributions | |
bel | -0.017 |
op | -0.017 |
t | -0.017 |
apr | -0.017 |
driver | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
op | +0.075 |
itt | +0.073 |
earned | +0.071 |
bel | +0.070 |
needed | +0.069 |
Neg logit contributions | |
Iris | -0.046 |
Sof | -0.044 |
Dawn | -0.044 |
Sophia | -0.042 |
sharing | -0.042 |
Token | so |
Token ID | 523 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Sof | +0.022 |
Dawn | +0.021 |
Belle | +0.021 |
Sasha | +0.021 |
igi | +0.021 |
Neg logit contributions | |
op | -0.021 |
bel | -0.020 |
apr | -0.020 |
driver | -0.019 |
x | -0.019 |
Token | he |
Token ID | 339 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Sof | +0.028 |
igi | +0.027 |
Dawn | +0.027 |
Belle | +0.027 |
Sasha | +0.027 |
Neg logit contributions | |
op | -0.017 |
apr | -0.016 |
bel | -0.015 |
driver | -0.015 |
x | -0.014 |
Token | ignored |
Token ID | 9514 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
op | +0.045 |
bel | +0.044 |
apr | +0.043 |
driver | +0.043 |
x | +0.041 |
Neg logit contributions | |
Sof | -0.034 |
igi | -0.033 |
Dawn | -0.033 |
ora | -0.033 |
Belle | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Sof | +0.074 |
Dawn | +0.072 |
Sasha | +0.069 |
Sophia | +0.069 |
Sandy | +0.069 |
Neg logit contributions | |
op | -0.068 |
bel | -0.065 |
t | -0.062 |
driver | -0.060 |
itt | -0.058 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
bel | +0.057 |
t | +0.055 |
This | +0.055 |
driver | +0.055 |
op | +0.055 |
Neg logit contributions | |
mistake | -0.036 |
Sof | -0.035 |
coc | -0.035 |
Dawn | -0.033 |
Fif | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
apr | +0.039 |
bel | +0.039 |
op | +0.035 |
Some | +0.034 |
driver | +0.034 |
Neg logit contributions | |
Sof | -0.040 |
Sasha | -0.039 |
Sophia | -0.037 |
Dawn | -0.037 |
forgetting | -0.036 |
Token | His |
Token ID | 2399 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Sof | +0.002 |
Dawn | +0.002 |
Sasha | +0.002 |
Sophia | +0.002 |
Fif | +0.002 |
Neg logit contributions | |
op | -0.001 |
apr | -0.001 |
bel | -0.001 |
x | -0.001 |
driver | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
bel | +0.022 |
op | +0.022 |
driver | +0.022 |
t | +0.021 |
This | +0.021 |
Neg logit contributions | |
Sof | -0.016 |
Dawn | -0.015 |
coc | -0.015 |
Fif | -0.015 |
Sophia | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
bel | +0.015 |
apr | +0.014 |
renches | +0.014 |
driver | +0.014 |
drill | +0.013 |
Neg logit contributions | |
Sof | -0.014 |
Sasha | -0.014 |
Belle | -0.014 |
Sophia | -0.013 |
ora | -0.013 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
op | +0.069 |
bel | +0.068 |
apr | +0.065 |
t | +0.065 |
driver | +0.065 |
Neg logit contributions | |
Sof | -0.040 |
Belle | -0.039 |
Sasha | -0.038 |
igi | -0.037 |
Dawn | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
bel | +0.011 |
Lots | +0.011 |
apr | +0.010 |
renches | +0.010 |
t | +0.010 |
Neg logit contributions | |
Sof | -0.015 |
Sasha | -0.015 |
Belle | -0.014 |
Sophia | -0.014 |
Fif | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
op | +0.048 |
bel | +0.046 |
t | +0.045 |
apr | +0.045 |
driver | +0.045 |
Neg logit contributions | |
Sof | -0.031 |
Belle | -0.030 |
Sasha | -0.029 |
Dawn | -0.028 |
ora | -0.028 |
Token | spray |
Token ID | 11662 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
op | +0.028 |
t | +0.027 |
driver | +0.026 |
bel | +0.025 |
This | +0.024 |
Neg logit contributions | |
Sof | -0.028 |
Dawn | -0.028 |
Belle | -0.028 |
ora | -0.028 |
Fif | -0.028 |
Token | bottles |
Token ID | 14096 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Sof | +0.019 |
Dawn | +0.019 |
ora | +0.018 |
Belle | +0.018 |
Fif | +0.018 |
Neg logit contributions | |
op | -0.020 |
t | -0.019 |
bel | -0.019 |
x | -0.019 |
apr | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Sof | +0.060 |
ora | +0.057 |
Dawn | +0.056 |
igi | +0.056 |
Belle | +0.056 |
Neg logit contributions | |
apr | -0.072 |
x | -0.071 |
bel | -0.071 |
op | -0.070 |
drill | -0.068 |
Token | She |
Token ID | 1375 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Sof | +0.003 |
Belle | +0.003 |
igi | +0.003 |
Dawn | +0.003 |
Sasha | +0.003 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | says |
Token ID | 1139 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
igi | +0.030 |
Sof | +0.029 |
Dawn | +0.029 |
Belle | +0.028 |
ora | +0.028 |
Neg logit contributions | |
op | -0.030 |
apr | -0.030 |
bel | -0.029 |
driver | -0.028 |
x | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Sof | +0.057 |
Belle | +0.055 |
Dawn | +0.055 |
Sasha | +0.054 |
igi | +0.054 |
Neg logit contributions | |
bel | -0.045 |
op | -0.045 |
apr | -0.044 |
driver | -0.041 |
x | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Sof | +0.000 |
Belle | +0.000 |
Sasha | +0.000 |
Fif | +0.000 |
igi | +0.000 |
Neg logit contributions | |
bel | -0.001 |
op | -0.001 |
apr | -0.001 |
x | -0.001 |
t | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
op | +0.026 |
bel | +0.025 |
driver | +0.024 |
washer | +0.024 |
t | +0.023 |
Neg logit contributions | |
Sof | -0.024 |
Belle | -0.022 |
Sasha | -0.022 |
Sophia | -0.022 |
Dawn | -0.022 |
Token | chair |
Token ID | 5118 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
coc | +0.023 |
Sof | +0.023 |
igi | +0.022 |
ora | +0.022 |
Sophia | +0.022 |
Neg logit contributions | |
op | -0.016 |
bel | -0.016 |
Some | -0.015 |
t | -0.015 |
driver | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
apr | +0.101 |
op | +0.097 |
controlled | +0.093 |
bel | +0.092 |
x | +0.092 |
Neg logit contributions | |
Sof | -0.097 |
Sophia | -0.087 |
Belle | -0.083 |
Sasha | -0.083 |
Joy | -0.080 |
Token | started |
Token ID | 2067 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
igi | +0.026 |
Sof | +0.025 |
Dawn | +0.025 |
ora | +0.025 |
Belle | +0.025 |
Neg logit contributions | |
op | -0.023 |
apr | -0.022 |
bel | -0.022 |
driver | -0.021 |
tools | -0.020 |
Token | rocking |
Token ID | 38059 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Sof | +0.049 |
Fif | +0.047 |
Dawn | +0.045 |
waterfall | +0.045 |
Belle | +0.044 |
Neg logit contributions | |
t | -0.030 |
op | -0.030 |
apr | -0.030 |
x | -0.029 |
driver | -0.028 |
Token | back |
Token ID | 736 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
op | +0.082 |
apr | +0.076 |
bel | +0.072 |
t | +0.072 |
x | +0.071 |
Neg logit contributions | |
Sof | -0.119 |
igi | -0.115 |
Belle | -0.113 |
Dawn | -0.112 |
ora | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Sof | +0.083 |
ora | +0.077 |
Belle | +0.076 |
Fif | +0.076 |
Sasha | +0.075 |
Neg logit contributions | |
apr | -0.065 |
t | -0.061 |
op | -0.061 |
x | -0.060 |
driver | -0.059 |
Token | forth |
Token ID | 6071 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
igi | +0.010 |
Sof | +0.009 |
Dawn | +0.009 |
ora | +0.009 |
Belle | +0.009 |
Neg logit contributions | |
op | -0.022 |
bel | -0.021 |
apr | -0.021 |
driver | -0.021 |
tools | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Sof | +0.000 |
Belle | +0.000 |
igi | +0.000 |
Dawn | +0.000 |
ora | +0.000 |
Neg logit contributions | |
apr | -0.000 |
op | -0.000 |
x | -0.000 |
bel | -0.000 |
Some | -0.000 |
Token | The |
Token ID | 383 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Sof | +0.012 |
igi | +0.012 |
Belle | +0.012 |
Dawn | +0.012 |
Sasha | +0.011 |
Neg logit contributions | |
op | -0.007 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
x | -0.007 |
Token | chair |
Token ID | 5118 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
bel | +0.004 |
op | +0.004 |
driver | +0.004 |
t | +0.003 |
This | +0.003 |
Neg logit contributions | |
coc | -0.005 |
Sof | -0.005 |
Belle | -0.005 |
ora | -0.005 |
Sophia | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Sof | +0.071 |
Belle | +0.070 |
igi | +0.069 |
ora | +0.068 |
Sasha | +0.068 |
Neg logit contributions | |
op | -0.060 |
apr | -0.058 |
bel | -0.057 |
x | -0.056 |
laptop | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
op | +0.007 |
bel | +0.006 |
apr | +0.006 |
driver | +0.006 |
t | +0.006 |
Neg logit contributions | |
Sof | -0.006 |
igi | -0.006 |
Belle | -0.006 |
Sasha | -0.006 |
Dawn | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Sof | +0.013 |
igi | +0.012 |
Dawn | +0.012 |
Belle | +0.012 |
Sasha | +0.012 |
Neg logit contributions | |
op | -0.008 |
bel | -0.008 |
apr | -0.008 |
driver | -0.007 |
x | -0.007 |
Token | even |
Token ID | 772 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
op | +0.002 |
apr | +0.002 |
bel | +0.002 |
driver | +0.002 |
t | +0.002 |
Neg logit contributions | |
Sof | -0.002 |
igi | -0.002 |
Dawn | -0.002 |
Belle | -0.002 |
ora | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
op | +0.045 |
apr | +0.043 |
bel | +0.043 |
driver | +0.042 |
t | +0.040 |
Neg logit contributions | |
Sof | -0.044 |
igi | -0.044 |
Dawn | -0.042 |
Belle | -0.042 |
ora | -0.042 |
Token | enough |
Token ID | 1576 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Sof | +0.010 |
Sasha | +0.010 |
Belle | +0.010 |
igi | +0.010 |
Dawn | +0.009 |
Neg logit contributions | |
op | -0.008 |
bel | -0.007 |
driver | -0.007 |
apr | -0.007 |
x | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
igi | +0.055 |
Sasha | +0.055 |
Sof | +0.055 |
Dawn | +0.055 |
Belle | +0.054 |
Neg logit contributions | |
op | -0.055 |
bel | -0.050 |
t | -0.048 |
driver | -0.048 |
apr | -0.048 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
op | +0.005 |
bel | +0.005 |
apr | +0.005 |
driver | +0.005 |
t | +0.004 |
Neg logit contributions | |
Sof | -0.006 |
igi | -0.006 |
Dawn | -0.006 |
Belle | -0.006 |
ora | -0.006 |
Token | new |
Token ID | 649 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
Sof | +0.050 |
Belle | +0.049 |
Dawn | +0.048 |
Sasha | +0.048 |
igi | +0.048 |
Neg logit contributions | |
op | -0.047 |
bel | -0.043 |
driver | -0.042 |
t | -0.041 |
apr | -0.040 |
Token | blankets |
Token ID | 34794 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Belle | +0.029 |
igi | +0.029 |
Sof | +0.028 |
Dawn | +0.028 |
ora | +0.028 |
Neg logit contributions | |
op | -0.034 |
t | -0.032 |
driver | -0.031 |
bel | -0.031 |
apr | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
apr | +0.023 |
op | +0.021 |
x | +0.021 |
bel | +0.021 |
Some | +0.020 |
Neg logit contributions | |
Sof | -0.025 |
igi | -0.024 |
Dawn | -0.023 |
ora | -0.023 |
Sasha | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Sof | +0.024 |
Belle | +0.023 |
Sasha | +0.023 |
Dawn | +0.023 |
igi | +0.023 |
Neg logit contributions | |
apr | -0.022 |
bel | -0.021 |
op | -0.020 |
driver | -0.020 |
x | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
Sof | +0.006 |
igi | +0.005 |
Belle | +0.005 |
Dawn | +0.005 |
ora | +0.005 |
Neg logit contributions | |
op | -0.004 |
apr | -0.004 |
bel | -0.004 |
driver | -0.004 |
x | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
bel | +0.003 |
driver | +0.003 |
x | +0.003 |
Neg logit contributions | |
Sof | -0.003 |
igi | -0.003 |
Joy | -0.003 |
Belle | -0.003 |
ora | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
Sof | +0.021 |
igi | +0.020 |
Belle | +0.020 |
ora | +0.020 |
Dawn | +0.020 |
Neg logit contributions | |
op | -0.024 |
apr | -0.024 |
bel | -0.023 |
driver | -0.023 |
x | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
op | +0.029 |
apr | +0.028 |
bel | +0.028 |
driver | +0.028 |
x | +0.026 |
Neg logit contributions | |
Sof | -0.031 |
igi | -0.030 |
Dawn | -0.030 |
Belle | -0.030 |
ora | -0.030 |
Token | done |
Token ID | 1760 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
op | +0.002 |
bel | +0.002 |
apr | +0.002 |
driver | +0.001 |
tools | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
Sophia | -0.001 |
Sasha | -0.001 |
Belle | -0.001 |
Joy | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
op | +0.015 |
apr | +0.015 |
bel | +0.015 |
oscope | +0.014 |
driver | +0.014 |
Neg logit contributions | |
Sof | -0.013 |
Sophia | -0.013 |
Dawn | -0.012 |
Sasha | -0.012 |
Belle | -0.012 |
Token | math |
Token ID | 10688 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
op | +0.020 |
bel | +0.019 |
driver | +0.019 |
apr | +0.018 |
t | +0.018 |
Neg logit contributions | |
Sof | -0.018 |
Belle | -0.017 |
Sophia | -0.017 |
Dawn | -0.017 |
Sasha | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
op | +0.030 |
apr | +0.029 |
bel | +0.029 |
driver | +0.027 |
x | +0.027 |
Neg logit contributions | |
Sof | -0.033 |
Belle | -0.031 |
Sophia | -0.031 |
Dawn | -0.031 |
Sasha | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Sof | +0.015 |
Belle | +0.015 |
Dawn | +0.014 |
igi | +0.014 |
Sasha | +0.014 |
Neg logit contributions | |
op | -0.020 |
apr | -0.019 |
bel | -0.019 |
driver | -0.019 |
t | -0.018 |
Token | started |
Token ID | 2067 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
op | +0.023 |
apr | +0.022 |
bel | +0.022 |
driver | +0.021 |
x | +0.021 |
Neg logit contributions | |
Sof | -0.019 |
igi | -0.018 |
Belle | -0.018 |
Dawn | -0.018 |
ora | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Sof | +0.007 |
Belle | +0.006 |
Dawn | +0.006 |
Sasha | +0.006 |
Iris | +0.006 |
Neg logit contributions | |
op | -0.013 |
apr | -0.012 |
bel | -0.012 |
driver | -0.012 |
x | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Sof | +0.041 |
Belle | +0.040 |
igi | +0.040 |
Sasha | +0.040 |
ora | +0.040 |
Neg logit contributions | |
bel | -0.041 |
apr | -0.040 |
op | -0.039 |
driver | -0.038 |
Some | -0.037 |
Token | Max |
Token ID | 5436 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
op | +0.017 |
apr | +0.017 |
bel | +0.016 |
driver | +0.016 |
x | +0.016 |
Neg logit contributions | |
igi | -0.024 |
Sof | -0.023 |
ora | -0.023 |
Dawn | -0.023 |
Belle | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
op | +0.002 |
bel | +0.002 |
apr | +0.001 |
driver | +0.001 |
x | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
igi | -0.001 |
Belle | -0.001 |
Dawn | -0.001 |
ora | -0.001 |
Token | good |
Token ID | 922 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sof | +0.042 |
Fif | +0.041 |
Dawn | +0.040 |
Iris | +0.040 |
Sasha | +0.040 |
Neg logit contributions | |
apr | -0.053 |
bel | -0.052 |
op | -0.051 |
x | -0.051 |
drill | -0.049 |
Token | night |
Token ID | 3847 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Sof | +0.047 |
ora | +0.047 |
igi | +0.047 |
Belle | +0.047 |
Dawn | +0.046 |
Neg logit contributions | |
apr | -0.030 |
op | -0.029 |
bel | -0.029 |
driver | -0.027 |
x | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
apr | +0.003 |
op | +0.003 |
renches | +0.003 |
x | +0.003 |
itt | +0.003 |
Neg logit contributions | |
Belle | -0.004 |
Sasha | -0.004 |
Sof | -0.004 |
Nora | -0.004 |
Sophia | -0.004 |
Token | went |
Token ID | 1816 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
igi | +0.006 |
Sof | +0.006 |
ora | +0.006 |
Dawn | +0.006 |
Belle | +0.006 |
Neg logit contributions | |
bel | -0.005 |
apr | -0.005 |
op | -0.005 |
driver | -0.004 |
t | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Sof | +0.004 |
Belle | +0.004 |
igi | +0.004 |
Fif | +0.004 |
Iris | +0.004 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
bel | -0.002 |
driver | -0.002 |
t | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
igi | +0.011 |
Sof | +0.011 |
Dawn | +0.011 |
ora | +0.011 |
Belle | +0.010 |
Neg logit contributions | |
op | -0.007 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
x | -0.006 |
Token | beds |
Token ID | 20237 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Sof | +0.043 |
igi | +0.041 |
Belle | +0.041 |
Dawn | +0.041 |
ora | +0.041 |
Neg logit contributions | |
op | -0.030 |
driver | -0.028 |
bel | -0.028 |
apr | -0.028 |
t | -0.027 |
Token | again |
Token ID | 757 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Sof | +0.095 |
igi | +0.092 |
Dawn | +0.092 |
Belle | +0.091 |
ora | +0.090 |
Neg logit contributions | |
op | -0.067 |
apr | -0.066 |
bel | -0.062 |
driver | -0.060 |
x | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Sof | +0.078 |
igi | +0.076 |
Belle | +0.076 |
Dawn | +0.075 |
Sasha | +0.074 |
Neg logit contributions | |
op | -0.053 |
apr | -0.053 |
bel | -0.051 |
driver | -0.049 |
x | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Sof | +0.006 |
Dawn | +0.006 |
Belle | +0.006 |
igi | +0.006 |
Sasha | +0.006 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
x | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
Sof | +0.006 |
igi | +0.006 |
Dawn | +0.006 |
Belle | +0.006 |
ora | +0.006 |
Neg logit contributions | |
op | -0.004 |
apr | -0.004 |
bel | -0.004 |
driver | -0.004 |
t | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
bel | +0.003 |
driver | +0.003 |
x | +0.003 |
Neg logit contributions | |
igi | -0.003 |
Sof | -0.003 |
Joy | -0.003 |
Dawn | -0.003 |
ora | -0.003 |
Token | driver |
Token ID | 4639 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
op | +0.016 |
apr | +0.015 |
bel | +0.015 |
driver | +0.014 |
t | +0.014 |
Neg logit contributions | |
igi | -0.018 |
Sof | -0.018 |
Dawn | -0.017 |
Belle | -0.017 |
Fif | -0.017 |
Token | got |
Token ID | 1392 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
apr | +0.013 |
op | +0.012 |
bel | +0.012 |
driver | +0.012 |
laptop | +0.011 |
Neg logit contributions | |
Sof | -0.010 |
igi | -0.009 |
ora | -0.009 |
Belle | -0.009 |
Dawn | -0.009 |
Token | back |
Token ID | 736 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Dawn | +0.006 |
Sof | +0.006 |
Fif | +0.005 |
Gig | +0.005 |
Claw | +0.005 |
Neg logit contributions | |
op | -0.007 |
apr | -0.007 |
driver | -0.007 |
laptop | -0.007 |
drill | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Dawn | +0.038 |
Sof | +0.038 |
Fif | +0.038 |
Gig | +0.037 |
igi | +0.037 |
Neg logit contributions | |
apr | -0.044 |
op | -0.040 |
Some | -0.038 |
driver | -0.038 |
t | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
op | +0.021 |
bel | +0.020 |
t | +0.019 |
driver | +0.018 |
apr | +0.018 |
Neg logit contributions | |
Sof | -0.017 |
Dawn | -0.016 |
Sasha | -0.016 |
Sophia | -0.015 |
waterfall | -0.015 |
Token | car |
Token ID | 1097 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
op | +0.012 |
t | +0.012 |
driver | +0.011 |
bel | +0.011 |
apr | +0.011 |
Neg logit contributions | |
waterfall | -0.014 |
Sof | -0.014 |
Dawn | -0.014 |
Iris | -0.014 |
Belle | -0.014 |
Token | message |
Token ID | 3275 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Sof | +0.020 |
igi | +0.020 |
Dawn | +0.020 |
Belle | +0.019 |
ora | +0.019 |
Neg logit contributions | |
bel | -0.021 |
op | -0.020 |
apr | -0.020 |
t | -0.019 |
driver | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Sof | +0.049 |
Belle | +0.048 |
Sasha | +0.047 |
igi | +0.046 |
Dawn | +0.046 |
Neg logit contributions | |
apr | -0.045 |
bel | -0.043 |
op | -0.042 |
Some | -0.039 |
x | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
op | +0.020 |
bel | +0.020 |
apr | +0.020 |
driver | +0.019 |
t | +0.019 |
Neg logit contributions | |
Sof | -0.015 |
Belle | -0.015 |
igi | -0.015 |
Dawn | -0.015 |
Sasha | -0.014 |
Token | paws |
Token ID | 49193 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
Belle | +0.020 |
Sof | +0.019 |
Sasha | +0.019 |
coc | +0.019 |
Dawn | +0.018 |
Neg logit contributions | |
bel | -0.017 |
driver | -0.017 |
apr | -0.017 |
op | -0.016 |
t | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Sof | +0.021 |
Sasha | +0.020 |
Dawn | +0.020 |
igi | +0.020 |
Belle | +0.020 |
Neg logit contributions | |
apr | -0.019 |
bel | -0.019 |
x | -0.017 |
op | -0.017 |
driver | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Sof | +0.006 |
Belle | +0.006 |
Dawn | +0.006 |
Sasha | +0.006 |
igi | +0.006 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
x | -0.003 |
Token | chip |
Token ID | 11594 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
op | +0.014 |
apr | +0.013 |
bel | +0.013 |
driver | +0.013 |
x | +0.013 |
Neg logit contributions | |
Sof | -0.015 |
igi | -0.015 |
Belle | -0.014 |
Dawn | -0.014 |
ora | -0.014 |
Token | m |
Token ID | 76 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Sof | +0.071 |
igi | +0.070 |
Belle | +0.068 |
Dawn | +0.068 |
ora | +0.067 |
Neg logit contributions | |
op | -0.087 |
apr | -0.083 |
bel | -0.083 |
driver | -0.081 |
t | -0.079 |
Token | unk |
Token ID | 2954 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
igi | +0.033 |
Sof | +0.032 |
ora | +0.032 |
Sasha | +0.032 |
iki | +0.031 |
Neg logit contributions | |
apr | -0.025 |
bel | -0.022 |
driver | -0.021 |
headphones | -0.020 |
x | -0.020 |
Token | got |
Token ID | 1392 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
apr | +0.003 |
bel | +0.003 |
op | +0.003 |
driver | +0.003 |
x | +0.003 |
Neg logit contributions | |
Sof | -0.002 |
Belle | -0.002 |
Joy | -0.002 |
Dawn | -0.002 |
igi | -0.002 |
Token | closer |
Token ID | 5699 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Sof | +0.007 |
Dawn | +0.007 |
Fif | +0.007 |
Belle | +0.007 |
Sasha | +0.007 |
Neg logit contributions | |
apr | -0.010 |
op | -0.009 |
driver | -0.009 |
laptop | -0.009 |
bel | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Sof | +0.011 |
igi | +0.011 |
Belle | +0.011 |
Dawn | +0.011 |
Sasha | +0.011 |
Neg logit contributions | |
op | -0.010 |
apr | -0.010 |
bel | -0.009 |
driver | -0.009 |
t | -0.009 |
Token | knew |
Token ID | 2993 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
apr | +0.049 |
op | +0.049 |
driver | +0.047 |
bel | +0.047 |
x | +0.045 |
Neg logit contributions | |
Sof | -0.036 |
Belle | -0.034 |
igi | -0.034 |
Dawn | -0.034 |
ora | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
apr | +0.018 |
op | +0.017 |
bel | +0.017 |
driver | +0.016 |
laptop | +0.015 |
Neg logit contributions | |
Sof | -0.018 |
Dawn | -0.017 |
igi | -0.017 |
Sasha | -0.017 |
Belle | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -9.49e-04 |
Pos logit contributions | |
Sof | +0.010 |
Sasha | +0.010 |
Dawn | +0.010 |
Belle | +0.010 |
Fif | +0.009 |
Neg logit contributions | |
op | -0.010 |
apr | -0.009 |
bel | -0.009 |
driver | -0.009 |
t | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
apr | +0.000 |
op | +0.000 |
bel | +0.000 |
driver | +0.000 |
laptop | +0.000 |
Neg logit contributions | |
Belle | -0.000 |
forgot | -0.000 |
Sof | -0.000 |
igi | -0.000 |
Dawn | -0.000 |
Token | winter |
Token ID | 7374 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
op | +0.014 |
bel | +0.013 |
apr | +0.013 |
driver | +0.013 |
t | +0.012 |
Neg logit contributions | |
igi | -0.012 |
Sof | -0.011 |
Sasha | -0.011 |
Belle | -0.011 |
Dawn | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
apr | +0.092 |
op | +0.090 |
bel | +0.090 |
Some | +0.089 |
driver | +0.082 |
Neg logit contributions | |
Sof | -0.083 |
Sasha | -0.081 |
igi | -0.079 |
waterfall | -0.078 |
Belle | -0.078 |
Token | Soon |
Token ID | 15894 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
bel | +0.000 |
apr | +0.000 |
op | +0.000 |
driver | +0.000 |
x | +0.000 |
Neg logit contributions | |
Sof | -0.001 |
Sasha | -0.001 |
Dawn | -0.001 |
Belle | -0.001 |
Sophia | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
op | +0.030 |
driver | +0.028 |
apr | +0.028 |
bel | +0.028 |
tools | +0.028 |
Neg logit contributions | |
igi | -0.043 |
ora | -0.042 |
Sof | -0.040 |
Dawn | -0.040 |
Joy | -0.040 |
Token | ground |
Token ID | 2323 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Dawn | +0.017 |
waterfall | +0.017 |
Sof | +0.016 |
Belle | +0.016 |
igi | +0.016 |
Neg logit contributions | |
op | -0.020 |
apr | -0.019 |
bel | -0.019 |
driver | -0.019 |
t | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
waterfall | +0.041 |
igi | +0.040 |
Sof | +0.039 |
Dawn | +0.038 |
Sasha | +0.038 |
Neg logit contributions | |
apr | -0.073 |
op | -0.069 |
x | -0.065 |
driver | -0.065 |
laptop | -0.064 |
Token | would |
Token ID | 561 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
apr | +0.099 |
bel | +0.096 |
op | +0.094 |
driver | +0.088 |
x | +0.087 |
Neg logit contributions | |
igi | -0.052 |
Sof | -0.049 |
forgot | -0.048 |
Fif | -0.048 |
Belle | -0.047 |
Token | heal |
Token ID | 12035 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
op | +0.050 |
apr | +0.050 |
bel | +0.049 |
driver | +0.045 |
washer | +0.043 |
Neg logit contributions | |
Sof | -0.040 |
Belle | -0.039 |
igi | -0.039 |
Fif | -0.039 |
Dawn | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Sof | +0.043 |
igi | +0.043 |
Belle | +0.042 |
Dawn | +0.042 |
ora | +0.042 |
Neg logit contributions | |
op | -0.030 |
apr | -0.029 |
bel | -0.028 |
driver | -0.027 |
t | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
op | +0.019 |
bel | +0.018 |
apr | +0.016 |
t | +0.016 |
driver | +0.016 |
Neg logit contributions | |
Sof | -0.018 |
Sasha | -0.017 |
Belle | -0.017 |
Dawn | -0.017 |
Sophia | -0.016 |
Token | few |
Token ID | 1178 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Joy | +0.024 |
coc | +0.024 |
Belle | +0.024 |
Sof | +0.024 |
waterfall | +0.023 |
Neg logit contributions | |
op | -0.025 |
driver | -0.024 |
bel | -0.023 |
apr | -0.023 |
t | -0.023 |
Token | days |
Token ID | 1528 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
op | +0.040 |
bel | +0.037 |
driver | +0.037 |
This | +0.037 |
t | +0.037 |
Neg logit contributions | |
coc | -0.022 |
Joy | -0.021 |
Sof | -0.021 |
Belle | -0.020 |
igi | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
apr | +0.087 |
bel | +0.081 |
op | +0.079 |
shirt | +0.079 |
x | +0.079 |
Neg logit contributions | |
Sof | -0.074 |
Sasha | -0.070 |
Belle | -0.069 |
igi | -0.068 |
forgetting | -0.068 |
Token | He |
Token ID | 679 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
Sof | +0.007 |
Belle | +0.007 |
igi | +0.007 |
Dawn | +0.007 |
Sasha | +0.007 |
Neg logit contributions | |
op | -0.006 |
apr | -0.006 |
bel | -0.006 |
driver | -0.005 |
t | -0.005 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Sof | +0.002 |
igi | +0.002 |
Belle | +0.002 |
Fif | +0.002 |
ora | +0.002 |
Neg logit contributions | |
op | -0.003 |
bel | -0.003 |
apr | -0.003 |
driver | -0.003 |
t | -0.003 |
Token | Sam |
Token ID | 3409 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
Sof | +0.040 |
igi | +0.040 |
Dawn | +0.038 |
Belle | +0.038 |
ora | +0.038 |
Neg logit contributions | |
op | -0.053 |
apr | -0.052 |
bel | -0.051 |
driver | -0.050 |
t | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
op | +0.030 |
bel | +0.028 |
renches | +0.028 |
t | +0.027 |
driver | +0.026 |
Neg logit contributions | |
Sof | -0.029 |
Sasha | -0.028 |
Belle | -0.028 |
die | -0.027 |
igi | -0.027 |
Token | cart |
Token ID | 6383 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
bel | +0.009 |
t | +0.008 |
op | +0.008 |
apr | +0.007 |
driver | +0.007 |
Neg logit contributions | |
Sof | -0.010 |
Sasha | -0.009 |
Belle | -0.009 |
Dawn | -0.009 |
Sophia | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
apr | +0.049 |
bel | +0.045 |
op | +0.041 |
headphones | +0.039 |
x | +0.039 |
Neg logit contributions | |
Sof | -0.052 |
ora | -0.047 |
igi | -0.047 |
Dawn | -0.047 |
Sophia | -0.046 |
Token | The |
Token ID | 383 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
op | +0.003 |
bel | +0.003 |
driver | +0.003 |
x | +0.003 |
apr | +0.003 |
Neg logit contributions | |
Sof | -0.005 |
Sophia | -0.005 |
Sasha | -0.005 |
Belle | -0.004 |
Joy | -0.004 |
Token | cart |
Token ID | 6383 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
op | +0.028 |
bel | +0.027 |
apr | +0.027 |
driver | +0.026 |
t | +0.026 |
Neg logit contributions | |
Sof | -0.020 |
ora | -0.020 |
Sasha | -0.020 |
Dawn | -0.020 |
Belle | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
apr | +0.027 |
op | +0.025 |
bel | +0.025 |
x | +0.024 |
driver | +0.024 |
Neg logit contributions | |
Sof | -0.018 |
Dawn | -0.017 |
ora | -0.016 |
igi | -0.016 |
Joy | -0.016 |
Token | many |
Token ID | 867 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Sof | +0.016 |
Sasha | +0.015 |
Sophia | +0.015 |
Fif | +0.015 |
Belle | +0.015 |
Neg logit contributions | |
op | -0.015 |
bel | -0.013 |
apr | -0.013 |
t | -0.012 |
laptop | -0.012 |
Token | ice |
Token ID | 4771 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
bel | +0.064 |
t | +0.061 |
op | +0.060 |
oscope | +0.058 |
driver | +0.057 |
Neg logit contributions | |
Dawn | -0.072 |
Sof | -0.071 |
turtles | -0.070 |
coc | -0.068 |
ora | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
igi | +0.008 |
ora | +0.007 |
Sof | +0.007 |
Fif | +0.007 |
bi | +0.007 |
Neg logit contributions | |
apr | -0.005 |
x | -0.005 |
Some | -0.004 |
op | -0.004 |
headphones | -0.004 |
Token | cream |
Token ID | 36277 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
laptop | +0.079 |
apr | +0.069 |
x | +0.068 |
computer | +0.068 |
TV | +0.065 |
Neg logit contributions | |
igi | -0.094 |
Gig | -0.091 |
Fif | -0.090 |
Sof | -0.088 |
ora | -0.085 |
Token | s |
Token ID | 82 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
apr | +0.011 |
bel | +0.010 |
x | +0.009 |
op | +0.009 |
headphones | +0.009 |
Neg logit contributions | |
Sof | -0.011 |
Fif | -0.011 |
igi | -0.010 |
Gig | -0.010 |
Dawn | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
Sof | +0.001 |
igi | +0.001 |
Fif | +0.001 |
bi | +0.001 |
Dawn | +0.001 |
Neg logit contributions | |
apr | -0.001 |
x | -0.001 |
bel | -0.001 |
headphones | -0.001 |
laptop | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
igi | +0.004 |
Sof | +0.004 |
Belle | +0.004 |
Dawn | +0.004 |
ora | +0.004 |
Neg logit contributions | |
op | -0.001 |
bel | -0.001 |
apr | -0.001 |
driver | -0.001 |
t | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
apr | +0.002 |
op | +0.002 |
x | +0.002 |
bel | +0.002 |
His | +0.002 |
Neg logit contributions | |
igi | -0.004 |
ora | -0.004 |
oph | -0.004 |
Sof | -0.004 |
Dawn | -0.004 |
Token | grandma |
Token ID | 49890 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
igi | +0.013 |
Sof | +0.013 |
Dawn | +0.013 |
Belle | +0.013 |
Sasha | +0.013 |
Neg logit contributions | |
apr | -0.007 |
op | -0.007 |
bel | -0.007 |
tools | -0.006 |
x | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
bel | +0.060 |
op | +0.058 |
apr | +0.057 |
driver | +0.055 |
t | +0.055 |
Neg logit contributions | |
Sof | -0.076 |
Belle | -0.073 |
Sasha | -0.072 |
igi | -0.071 |
ora | -0.071 |
Token | She |
Token ID | 1375 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
op | +0.012 |
apr | +0.012 |
driver | +0.011 |
bel | +0.011 |
t | +0.011 |
Neg logit contributions | |
Sof | -0.009 |
Belle | -0.009 |
Sasha | -0.008 |
Sophia | -0.008 |
Fif | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
igi | +0.020 |
Sof | +0.020 |
ora | +0.020 |
Dawn | +0.020 |
Belle | +0.020 |
Neg logit contributions | |
op | -0.018 |
bel | -0.018 |
apr | -0.017 |
driver | -0.017 |
x | -0.016 |
Token | them |
Token ID | 606 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
op | +0.082 |
bel | +0.078 |
t | +0.077 |
apr | +0.076 |
driver | +0.074 |
Neg logit contributions | |
Sof | -0.064 |
Belle | -0.061 |
Sasha | -0.059 |
Sophia | -0.058 |
Dawn | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
apr | +0.014 |
op | +0.014 |
bel | +0.014 |
driver | +0.013 |
t | +0.013 |
Neg logit contributions | |
Sof | -0.018 |
Dawn | -0.017 |
igi | -0.017 |
Belle | -0.017 |
ora | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
bel | +0.006 |
apr | +0.005 |
op | +0.005 |
driver | +0.005 |
tools | +0.005 |
Neg logit contributions | |
igi | -0.008 |
ora | -0.008 |
Dawn | -0.008 |
Sof | -0.008 |
oph | -0.008 |
Token | cow |
Token ID | 9875 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Sof | +0.001 |
igi | +0.001 |
Belle | +0.001 |
Dawn | +0.001 |
ora | +0.001 |
Neg logit contributions | |
op | -0.001 |
bel | -0.001 |
apr | -0.001 |
driver | -0.001 |
t | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Sof | +0.028 |
igi | +0.027 |
Belle | +0.027 |
Dawn | +0.027 |
Sasha | +0.026 |
Neg logit contributions | |
op | -0.018 |
apr | -0.018 |
bel | -0.018 |
driver | -0.017 |
t | -0.016 |
Token | clean |
Token ID | 3424 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
op | +0.013 |
driver | +0.013 |
bel | +0.013 |
Some | +0.013 |
tant | +0.012 |
Neg logit contributions | |
Belle | -0.013 |
Sasha | -0.013 |
Dawn | -0.012 |
forget | -0.012 |
Nora | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Sof | +0.019 |
Dawn | +0.019 |
Sophia | +0.018 |
Sasha | +0.018 |
ora | +0.018 |
Neg logit contributions | |
op | -0.021 |
bel | -0.021 |
t | -0.020 |
driver | -0.019 |
Some | -0.018 |
Token | room |
Token ID | 2119 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
t | +0.017 |
op | +0.015 |
driver | +0.015 |
Some | +0.014 |
bel | +0.014 |
Neg logit contributions | |
coc | -0.012 |
mistake | -0.012 |
ora | -0.011 |
Sof | -0.010 |
Dawn | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
op | +0.111 |
itt | +0.109 |
Some | +0.103 |
iren | +0.099 |
fighting | +0.096 |
Neg logit contributions | |
Sof | -0.050 |
Sophia | -0.050 |
mistake | -0.049 |
ora | -0.045 |
forgetting | -0.045 |
Token | Tim |
Token ID | 5045 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Sof | +0.006 |
Dawn | +0.005 |
Fif | +0.005 |
Gig | +0.005 |
Sasha | +0.005 |
Neg logit contributions | |
bel | -0.010 |
apr | -0.009 |
op | -0.009 |
oscope | -0.009 |
driver | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
igi | +0.013 |
Sof | +0.013 |
ora | +0.013 |
Belle | +0.013 |
Dawn | +0.013 |
Neg logit contributions | |
op | -0.018 |
bel | -0.018 |
apr | -0.018 |
driver | -0.018 |
t | -0.017 |
Token | started |
Token ID | 2067 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
bel | +0.084 |
driver | +0.081 |
Some | +0.078 |
op | +0.078 |
iren | +0.077 |
Neg logit contributions | |
ora | -0.043 |
forgot | -0.042 |
oph | -0.042 |
Sof | -0.040 |
Joy | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
forgetting | +0.015 |
agreeing | +0.013 |
Sandy | +0.013 |
Dawn | +0.013 |
Wendy | +0.013 |
Neg logit contributions | |
controlled | -0.016 |
ay | -0.016 |
oscope | -0.015 |
int | -0.015 |
ifying | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
op | +0.016 |
driver | +0.016 |
bel | +0.016 |
t | +0.016 |
itt | +0.015 |
Neg logit contributions | |
Dawn | -0.017 |
forget | -0.017 |
Belle | -0.016 |
ora | -0.016 |
coc | -0.016 |
Token | away |
Token ID | 1497 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Dawn | +0.005 |
igi | +0.004 |
Sandy | +0.004 |
Nora | +0.004 |
Sof | +0.004 |
Neg logit contributions | |
op | -0.007 |
t | -0.007 |
bel | -0.007 |
laptop | -0.006 |
fighting | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Dawn | +0.032 |
Fif | +0.031 |
Sof | +0.031 |
Sandy | +0.030 |
Iris | +0.029 |
Neg logit contributions | |
op | -0.045 |
t | -0.044 |
itt | -0.041 |
oscope | -0.040 |
bel | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
His | +0.003 |
Some | +0.003 |
driver | +0.003 |
Neg logit contributions | |
igi | -0.005 |
Dawn | -0.005 |
ora | -0.005 |
Sof | -0.005 |
Joy | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Sof | +0.013 |
igi | +0.013 |
Belle | +0.012 |
ora | +0.012 |
Dawn | +0.012 |
Neg logit contributions | |
op | -0.015 |
apr | -0.015 |
driver | -0.015 |
bel | -0.015 |
x | -0.014 |
Token | only |
Token ID | 691 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
driver | +0.022 |
op | +0.022 |
apr | +0.021 |
bel | +0.020 |
t | +0.020 |
Neg logit contributions | |
Sof | -0.024 |
Fif | -0.023 |
Dawn | -0.023 |
Belle | -0.023 |
Iris | -0.022 |
Token | three |
Token ID | 1115 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Sof | +0.005 |
Belle | +0.005 |
Dawn | +0.005 |
ora | +0.004 |
Fif | +0.004 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
driver | -0.002 |
bel | -0.002 |
t | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
driver | +0.134 |
bel | +0.132 |
op | +0.128 |
t | +0.127 |
apr | +0.127 |
Neg logit contributions | |
Sof | -0.095 |
ora | -0.090 |
igi | -0.088 |
Dawn | -0.087 |
Sasha | -0.086 |
Token | years |
Token ID | 19002 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
apr | +0.132 |
op | +0.129 |
driver | +0.123 |
laptop | +0.121 |
bel | +0.121 |
Neg logit contributions | |
Sof | -0.131 |
igi | -0.129 |
Dawn | -0.126 |
ora | -0.125 |
Joy | -0.125 |
Token | - |
Token ID | 12 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
apr | +0.101 |
driver | +0.094 |
bel | +0.094 |
op | +0.092 |
t | +0.084 |
Neg logit contributions | |
Sof | -0.253 |
ora | -0.250 |
igi | -0.248 |
Fif | -0.242 |
Dawn | -0.239 |
Token | old |
Token ID | 727 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
apr | +0.125 |
op | +0.119 |
bel | +0.117 |
driver | +0.116 |
x | +0.111 |
Neg logit contributions | |
Sof | -0.135 |
igi | -0.131 |
ora | -0.128 |
Dawn | -0.127 |
Belle | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
op | +0.017 |
bel | +0.015 |
apr | +0.015 |
driver | +0.015 |
tools | +0.014 |
Neg logit contributions | |
igi | -0.046 |
Dawn | -0.044 |
Sof | -0.044 |
waterfall | -0.043 |
Belle | -0.043 |
Token | but |
Token ID | 475 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
op | +0.016 |
bel | +0.015 |
apr | +0.015 |
driver | +0.015 |
washer | +0.014 |
Neg logit contributions | |
Sof | -0.014 |
Sasha | -0.013 |
Belle | -0.013 |
Fif | -0.013 |
Dawn | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
op | +0.016 |
His | +0.016 |
t | +0.016 |
apr | +0.016 |
x | +0.015 |
Neg logit contributions | |
igi | -0.024 |
ora | -0.023 |
waterfall | -0.022 |
Dawn | -0.022 |
Joy | -0.022 |
Token | Anna |
Token ID | 11735 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
op | +0.015 |
bel | +0.015 |
apr | +0.015 |
driver | +0.015 |
tools | +0.014 |
Neg logit contributions | |
Sof | -0.012 |
Belle | -0.012 |
Joy | -0.011 |
Sasha | -0.011 |
Sophia | -0.011 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Sof | +0.010 |
Belle | +0.009 |
ora | +0.009 |
igi | +0.009 |
Dawn | +0.009 |
Neg logit contributions | |
op | -0.012 |
bel | -0.011 |
apr | -0.011 |
driver | -0.011 |
x | -0.011 |
Token | those |
Token ID | 883 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
bel | +0.023 |
op | +0.022 |
apr | +0.021 |
driver | +0.021 |
tools | +0.019 |
Neg logit contributions | |
Sof | -0.018 |
Belle | -0.018 |
Sasha | -0.017 |
Sophia | -0.017 |
Dawn | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
op | +0.054 |
bel | +0.053 |
apr | +0.053 |
driver | +0.052 |
x | +0.050 |
Neg logit contributions | |
Sof | -0.053 |
Belle | -0.052 |
Dawn | -0.051 |
ora | -0.051 |
Sasha | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
apr | +0.018 |
op | +0.018 |
bel | +0.018 |
x | +0.017 |
driver | +0.017 |
Neg logit contributions | |
igi | -0.030 |
Sof | -0.029 |
ora | -0.029 |
Dawn | -0.029 |
Belle | -0.028 |
Token | sill |
Token ID | 49276 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
op | +0.034 |
apr | +0.034 |
bel | +0.034 |
x | +0.032 |
t | +0.032 |
Neg logit contributions | |
igi | -0.050 |
Sof | -0.047 |
Dawn | -0.047 |
ora | -0.045 |
Sasha | -0.045 |
Token | iest |
Token ID | 6386 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
apr | +0.173 |
bel | +0.166 |
x | +0.158 |
op | +0.154 |
driver | +0.152 |
Neg logit contributions | |
igi | -0.188 |
Sasha | -0.187 |
ora | -0.186 |
Sof | -0.185 |
Belle | -0.183 |
Token | names |
Token ID | 3891 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
op | +0.066 |
bel | +0.061 |
apr | +0.061 |
driver | +0.059 |
t | +0.059 |
Neg logit contributions | |
igi | -0.084 |
Sof | -0.081 |
Dawn | -0.078 |
Joy | -0.077 |
Fif | -0.077 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
apr | +0.017 |
op | +0.017 |
bel | +0.017 |
x | +0.016 |
driver | +0.016 |
Neg logit contributions | |
Sof | -0.030 |
Belle | -0.030 |
Sasha | -0.029 |
Joy | -0.029 |
Dawn | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
op | +0.008 |
apr | +0.008 |
bel | +0.008 |
driver | +0.007 |
t | +0.007 |
Neg logit contributions | |
Sof | -0.011 |
igi | -0.011 |
Dawn | -0.011 |
Belle | -0.011 |
ora | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
op | +0.003 |
apr | +0.003 |
bel | +0.003 |
driver | +0.003 |
This | +0.002 |
Neg logit contributions | |
igi | -0.005 |
Sof | -0.005 |
Dawn | -0.005 |
ora | -0.005 |
waterfall | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Sof | +0.117 |
igi | +0.116 |
Dawn | +0.114 |
Belle | +0.114 |
ora | +0.113 |
Neg logit contributions | |
op | -0.058 |
apr | -0.054 |
bel | -0.054 |
driver | -0.052 |
t | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Sof | +0.001 |
igi | +0.001 |
Dawn | +0.001 |
Belle | +0.001 |
ora | +0.001 |
Neg logit contributions | |
op | -0.000 |
bel | -0.000 |
apr | -0.000 |
driver | -0.000 |
t | -0.000 |
Token | These |
Token ID | 4711 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
op | +0.018 |
apr | +0.017 |
driver | +0.017 |
bel | +0.017 |
tools | +0.016 |
Neg logit contributions | |
Sof | -0.017 |
Dawn | -0.017 |
igi | -0.016 |
ora | -0.016 |
Joy | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
op | +0.047 |
bel | +0.045 |
apr | +0.044 |
x | +0.042 |
driver | +0.042 |
Neg logit contributions | |
turtles | -0.036 |
ora | -0.036 |
Sof | -0.035 |
Belle | -0.035 |
Dawn | -0.034 |
Token | my |
Token ID | 616 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
op | +0.002 |
apr | +0.002 |
bel | +0.002 |
driver | +0.002 |
t | +0.002 |
Neg logit contributions | |
igi | -0.001 |
Sof | -0.001 |
ora | -0.001 |
Belle | -0.001 |
Dawn | -0.001 |
Token | ships |
Token ID | 7937 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
op | +0.007 |
bel | +0.006 |
apr | +0.006 |
driver | +0.006 |
t | +0.006 |
Neg logit contributions | |
waterfall | -0.007 |
Sof | -0.007 |
Dawn | -0.007 |
ora | -0.007 |
turtles | -0.007 |
Token | ," |
Token ID | 553 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
apr | +0.199 |
op | +0.198 |
bel | +0.184 |
Some | +0.182 |
x | +0.180 |
Neg logit contributions | |
Sof | -0.134 |
forget | -0.133 |
ora | -0.132 |
Claw | -0.131 |
coc | -0.131 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
op | +0.020 |
bel | +0.019 |
apr | +0.019 |
driver | +0.019 |
t | +0.018 |
Neg logit contributions | |
Sof | -0.017 |
Dawn | -0.016 |
igi | -0.016 |
Belle | -0.016 |
Sasha | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
op | +0.038 |
apr | +0.036 |
bel | +0.035 |
driver | +0.035 |
His | +0.034 |
Neg logit contributions | |
Dawn | -0.047 |
Sof | -0.047 |
igi | -0.047 |
Belle | -0.047 |
waterfall | -0.046 |
Token | said |
Token ID | 531 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
op | +0.150 |
bel | +0.149 |
apr | +0.148 |
driver | +0.145 |
x | +0.138 |
Neg logit contributions | |
Sof | -0.088 |
Belle | -0.084 |
Dawn | -0.084 |
igi | -0.083 |
ora | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Sof | +0.006 |
agreeing | +0.006 |
Sophia | +0.006 |
forgetting | +0.006 |
Dawn | +0.006 |
Neg logit contributions | |
apr | -0.012 |
headphones | -0.011 |
itt | -0.011 |
op | -0.010 |
renches | -0.010 |
Token | always |
Token ID | 1464 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
op | +0.012 |
bel | +0.012 |
apr | +0.012 |
driver | +0.012 |
t | +0.011 |
Neg logit contributions | |
Sof | -0.009 |
igi | -0.009 |
Belle | -0.009 |
Dawn | -0.009 |
ora | -0.009 |
Token | slept |
Token ID | 21256 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
igi | +0.016 |
Sof | +0.016 |
Dawn | +0.016 |
ora | +0.016 |
Joy | +0.016 |
Neg logit contributions | |
op | -0.016 |
apr | -0.015 |
bel | -0.015 |
driver | -0.014 |
t | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
op | +0.035 |
apr | +0.033 |
driver | +0.032 |
Some | +0.031 |
bel | +0.030 |
Neg logit contributions | |
igi | -0.037 |
Sof | -0.035 |
ora | -0.034 |
Dawn | -0.034 |
Belle | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
op | +0.001 |
t | +0.001 |
bel | +0.001 |
driver | +0.001 |
inter | +0.001 |
Neg logit contributions | |
Sof | -0.001 |
coc | -0.001 |
Fif | -0.001 |
Sasha | -0.001 |
Gig | -0.001 |
Token | night |
Token ID | 1755 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
apr | +0.001 |
driver | +0.001 |
op | +0.001 |
bel | +0.001 |
This | +0.001 |
Neg logit contributions | |
coc | -0.002 |
waterfall | -0.002 |
Fif | -0.001 |
Belle | -0.001 |
Dawn | -0.001 |
Token | light |
Token ID | 2971 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
apr | +0.119 |
driver | +0.116 |
Some | +0.110 |
bel | +0.106 |
op | +0.105 |
Neg logit contributions | |
forgetting | -0.072 |
waterfall | -0.071 |
blo | -0.070 |
coc | -0.069 |
forget | -0.066 |
Token | on |
Token ID | 319 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
op | +0.193 |
apr | +0.189 |
x | +0.176 |
Some | +0.176 |
itt | +0.175 |
Neg logit contributions | |
Belle | -0.152 |
igi | -0.152 |
Sof | -0.151 |
waterfall | -0.148 |
forgetting | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
op | +0.034 |
driver | +0.032 |
bel | +0.031 |
itt | +0.029 |
t | +0.028 |
Neg logit contributions | |
Sof | -0.018 |
waterfall | -0.017 |
Fif | -0.016 |
coc | -0.016 |
Gig | -0.014 |
Token | One |
Token ID | 1881 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
op | +0.007 |
bel | +0.007 |
apr | +0.007 |
driver | +0.007 |
t | +0.006 |
Neg logit contributions | |
Sof | -0.010 |
igi | -0.010 |
Dawn | -0.010 |
Belle | -0.010 |
Sasha | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
driver | +0.040 |
apr | +0.039 |
bel | +0.039 |
op | +0.037 |
renches | +0.034 |
Neg logit contributions | |
Sof | -0.026 |
igi | -0.025 |
Sasha | -0.024 |
Belle | -0.024 |
ora | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
apr | +0.051 |
bel | +0.050 |
op | +0.048 |
driver | +0.047 |
x | +0.046 |
Neg logit contributions | |
Sof | -0.054 |
Dawn | -0.053 |
Fif | -0.052 |
igi | -0.052 |
Sasha | -0.051 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Sof | +0.014 |
igi | +0.014 |
Dawn | +0.014 |
Belle | +0.014 |
ora | +0.014 |
Neg logit contributions | |
op | -0.013 |
apr | -0.012 |
bel | -0.012 |
driver | -0.012 |
t | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
op | +0.041 |
driver | +0.039 |
t | +0.038 |
bel | +0.035 |
oscope | +0.032 |
Neg logit contributions | |
Fif | -0.089 |
Sof | -0.089 |
Gig | -0.088 |
coc | -0.086 |
Belle | -0.085 |
Token | play |
Token ID | 711 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
t | +0.004 |
op | +0.004 |
driver | +0.004 |
bel | +0.004 |
tant | +0.004 |
Neg logit contributions | |
Belle | -0.002 |
Fif | -0.002 |
Sof | -0.002 |
coc | -0.002 |
Sasha | -0.002 |
Token | hide |
Token ID | 7808 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
t | +0.014 |
op | +0.014 |
driver | +0.014 |
bel | +0.014 |
Some | +0.012 |
Neg logit contributions | |
Fif | -0.025 |
Sof | -0.025 |
Belle | -0.024 |
Iris | -0.024 |
Joy | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Sof | +0.018 |
igi | +0.018 |
ora | +0.017 |
Belle | +0.017 |
Dawn | +0.017 |
Neg logit contributions | |
op | -0.008 |
apr | -0.007 |
bel | -0.007 |
driver | -0.007 |
t | -0.007 |
Token | and |
Token ID | 392 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
apr | +0.078 |
op | +0.074 |
driver | +0.073 |
x | +0.072 |
drill | +0.070 |
Neg logit contributions | |
igi | -0.101 |
Sof | -0.099 |
ora | -0.099 |
Joy | -0.095 |
Fif | -0.094 |
Token | - |
Token ID | 12 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
op | +0.078 |
apr | +0.076 |
bel | +0.073 |
driver | +0.072 |
x | +0.064 |
Neg logit contributions | |
Sof | -0.274 |
igi | -0.273 |
ora | -0.269 |
Dawn | -0.268 |
Belle | -0.268 |
Token | seek |
Token ID | 36163 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
apr | +0.069 |
op | +0.067 |
x | +0.066 |
driver | +0.064 |
tools | +0.063 |
Neg logit contributions | |
igi | -0.060 |
Sof | -0.060 |
ora | -0.058 |
Fif | -0.057 |
Joy | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
Sof | +0.013 |
ora | +0.012 |
Joy | +0.012 |
Sophia | +0.012 |
Belle | +0.012 |
Neg logit contributions | |
op | -0.010 |
driver | -0.010 |
apr | -0.009 |
x | -0.009 |
inter | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
igi | +0.003 |
Sof | +0.003 |
Dawn | +0.003 |
ora | +0.002 |
Belle | +0.002 |
Neg logit contributions | |
op | -0.002 |
apr | -0.002 |
bel | -0.002 |
driver | -0.002 |
x | -0.002 |
Token | friends |
Token ID | 2460 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
op | +0.015 |
apr | +0.015 |
bel | +0.014 |
driver | +0.014 |
t | +0.014 |
Neg logit contributions | |
Sof | -0.010 |
igi | -0.010 |
Dawn | -0.009 |
Belle | -0.009 |
ora | -0.009 |