Token | could |
Token ID | 714 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
azes | +0.047 |
writing | +0.041 |
isdom | +0.041 |
patiently | +0.041 |
pit | +0.040 |
Neg logit contributions | |
sc | -0.026 |
ch | -0.026 |
Br | -0.025 |
B | -0.025 |
subs | -0.025 |
Token | be |
Token ID | 307 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
B | +0.009 |
subs | +0.008 |
ch | +0.008 |
ched | +0.008 |
sc | +0.008 |
Neg logit contributions | |
azes | -0.015 |
ires | -0.013 |
pit | -0.013 |
fridge | -0.013 |
oven | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
azes | +0.028 |
pit | +0.024 |
mmm | +0.023 |
ires | +0.023 |
isdom | +0.023 |
Neg logit contributions | |
ch | -0.021 |
B | -0.021 |
sc | -0.021 |
subs | -0.020 |
ched | -0.019 |
Token | never |
Token ID | 1239 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ch | +0.014 |
sc | +0.014 |
B | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.021 |
pit | -0.018 |
mmm | -0.017 |
ement | -0.017 |
ires | -0.017 |
Token | mis |
Token ID | 2984 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
sc | +0.036 |
B | +0.035 |
ch | +0.034 |
text | +0.032 |
Fl | +0.031 |
Neg logit contributions | |
azes | -0.048 |
writing | -0.041 |
isdom | -0.039 |
pit | -0.039 |
castle | -0.039 |
Token | beh |
Token ID | 20709 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
sc | +0.079 |
ch | +0.078 |
subs | +0.075 |
B | +0.074 |
fl | +0.072 |
Neg logit contributions | |
azes | -0.143 |
isdom | -0.121 |
ires | -0.118 |
eria | -0.117 |
pit | -0.117 |
Token | aved |
Token ID | 9586 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
ch | +0.134 |
B | +0.133 |
sc | +0.133 |
subs | +0.128 |
bo | +0.120 |
Neg logit contributions | |
azes | -0.179 |
pit | -0.151 |
isdom | -0.148 |
mmm | -0.147 |
ires | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
ch | +0.011 |
sc | +0.011 |
B | +0.011 |
subs | +0.011 |
bo | +0.010 |
Neg logit contributions | |
azes | -0.016 |
pit | -0.014 |
ement | -0.013 |
isdom | -0.013 |
ires | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
sc | +0.002 |
ch | +0.002 |
B | +0.002 |
subs | +0.002 |
ched | +0.002 |
Neg logit contributions | |
azes | -0.004 |
pit | -0.003 |
isdom | -0.003 |
mmm | -0.003 |
ires | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
subs | +0.024 |
ch | +0.024 |
sc | +0.024 |
B | +0.023 |
scrap | +0.023 |
Neg logit contributions | |
azes | -0.031 |
pit | -0.026 |
ement | -0.026 |
fridge | -0.025 |
refrigerator | -0.025 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
ch | +0.021 |
B | +0.021 |
sc | +0.021 |
subs | +0.020 |
bo | +0.019 |
Neg logit contributions | |
azes | -0.028 |
pit | -0.023 |
mmm | -0.023 |
isdom | -0.023 |
oven | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
B | +0.038 |
ch | +0.038 |
sc | +0.038 |
subs | +0.036 |
ched | +0.034 |
Neg logit contributions | |
azes | -0.062 |
pit | -0.053 |
oven | -0.052 |
isdom | -0.052 |
mmm | -0.052 |
Token | ch |
Token ID | 354 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
sc | +0.012 |
ch | +0.012 |
subs | +0.012 |
B | +0.011 |
text | +0.011 |
Neg logit contributions | |
azes | -0.023 |
mmm | -0.021 |
pit | -0.021 |
ocolate | -0.021 |
ement | -0.020 |
Token | oo |
Token ID | 2238 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
subs | +0.088 |
B | +0.087 |
sc | +0.084 |
Free | +0.082 |
scrap | +0.082 |
Neg logit contributions | |
azes | -0.082 |
ocolate | -0.068 |
mmm | -0.067 |
pit | -0.065 |
oven | -0.065 |
Token | cho |
Token ID | 1727 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
B | +0.075 |
sc | +0.074 |
subs | +0.073 |
Free | +0.068 |
scrap | +0.067 |
Neg logit contributions | |
azes | -0.084 |
mmm | -0.075 |
oven | -0.074 |
patiently | -0.072 |
ocolate | -0.072 |
Token | o |
Token ID | 78 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
subs | +0.155 |
scrap | +0.148 |
B | +0.147 |
Free | +0.140 |
sc | +0.140 |
Neg logit contributions | |
azes | -0.129 |
ocolate | -0.113 |
ruits | -0.105 |
mmm | -0.103 |
sing | -0.101 |
Token | cho |
Token ID | 1727 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
B | +0.048 |
subs | +0.046 |
sc | +0.044 |
scrap | +0.043 |
Free | +0.043 |
Neg logit contributions | |
azes | -0.061 |
oven | -0.056 |
mmm | -0.055 |
ocolate | -0.055 |
ummy | -0.053 |
Token | o |
Token ID | 78 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
subs | +0.162 |
scrap | +0.157 |
B | +0.154 |
Free | +0.150 |
sc | +0.149 |
Neg logit contributions | |
azes | -0.135 |
ocolate | -0.120 |
sing | -0.109 |
ruits | -0.109 |
mmm | -0.105 |
Token | ". |
Token ID | 1911 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
B | +0.054 |
subs | +0.052 |
Free | +0.049 |
scrap | +0.049 |
sc | +0.049 |
Neg logit contributions | |
azes | -0.063 |
oven | -0.058 |
ocolate | -0.056 |
sing | -0.056 |
mmm | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
azes | +0.015 |
pit | +0.013 |
isdom | +0.013 |
ires | +0.013 |
ement | +0.012 |
Neg logit contributions | |
ch | -0.009 |
B | -0.009 |
sc | -0.009 |
subs | -0.009 |
bo | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-03 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.003 |
subs | +0.003 |
ched | +0.003 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
mmm | -0.005 |
isdom | -0.005 |
ires | -0.005 |
Token | They |
Token ID | 2990 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
azes | +0.006 |
pit | +0.005 |
isdom | +0.005 |
ires | +0.005 |
mmm | +0.005 |
Neg logit contributions | |
ch | -0.003 |
B | -0.003 |
sc | -0.003 |
subs | -0.003 |
bo | -0.003 |
Token | be |
Token ID | 307 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
subs | +0.003 |
sc | +0.003 |
bo | +0.003 |
ch | +0.003 |
B | +0.003 |
Neg logit contributions | |
azes | -0.005 |
ires | -0.005 |
pit | -0.005 |
ummy | -0.004 |
ement | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
azes | +0.021 |
pit | +0.018 |
mmm | +0.017 |
isdom | +0.017 |
ires | +0.017 |
Neg logit contributions | |
ch | -0.020 |
sc | -0.020 |
B | -0.020 |
subs | -0.019 |
bo | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
azes | +0.017 |
mmm | +0.015 |
ocolate | +0.015 |
ruits | +0.015 |
isdom | +0.015 |
Neg logit contributions | |
B | -0.006 |
subs | -0.006 |
ch | -0.006 |
fl | -0.006 |
sc | -0.006 |
Token | well |
Token ID | 880 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ch | +0.020 |
B | +0.020 |
sc | +0.020 |
subs | +0.019 |
bo | +0.018 |
Neg logit contributions | |
azes | -0.021 |
pit | -0.017 |
isdom | -0.017 |
mmm | -0.017 |
writing | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
sc | +0.038 |
ch | +0.038 |
B | +0.038 |
subs | +0.036 |
ched | +0.034 |
Neg logit contributions | |
azes | -0.065 |
pit | -0.055 |
mmm | -0.054 |
isdom | -0.054 |
ires | -0.054 |
Token | beh |
Token ID | 20709 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
subs | +0.047 |
sc | +0.046 |
ch | +0.046 |
text | +0.046 |
B | +0.045 |
Neg logit contributions | |
azes | -0.082 |
isdom | -0.072 |
mmm | -0.070 |
ires | -0.069 |
castle | -0.069 |
Token | aved |
Token ID | 9586 |
Feature activation | +8.28e-03 |
Pos logit contributions | |
ch | +0.109 |
sc | +0.109 |
B | +0.108 |
subs | +0.104 |
bo | +0.097 |
Neg logit contributions | |
azes | -0.176 |
pit | -0.150 |
isdom | -0.147 |
mmm | -0.147 |
ires | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-04 |
Pos logit contributions | |
ch | +0.011 |
B | +0.011 |
sc | +0.011 |
subs | +0.011 |
bo | +0.010 |
Neg logit contributions | |
azes | -0.016 |
pit | -0.014 |
ement | -0.014 |
isdom | -0.014 |
oven | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
azes | +0.001 |
pit | +0.000 |
ires | +0.000 |
ement | +0.000 |
isdom | +0.000 |
Neg logit contributions | |
B | -0.000 |
ch | -0.000 |
sc | -0.000 |
subs | -0.000 |
bo | -0.000 |
Token | end |
Token ID | 886 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ch | +0.028 |
B | +0.028 |
sc | +0.027 |
subs | +0.026 |
scrap | +0.025 |
Neg logit contributions | |
azes | -0.047 |
mmm | -0.041 |
isdom | -0.040 |
pit | -0.039 |
ires | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
sc | +0.026 |
B | +0.026 |
ch | +0.025 |
subs | +0.025 |
ched | +0.023 |
Neg logit contributions | |
azes | -0.037 |
pit | -0.031 |
oven | -0.031 |
isdom | -0.031 |
ement | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
ch | +0.011 |
subs | +0.010 |
sc | +0.010 |
ched | +0.010 |
B | +0.010 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.011 |
ement | -0.011 |
eria | -0.011 |
mmm | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -5.69e-04 |
Pos logit contributions | |
azes | +0.004 |
pit | +0.003 |
fridge | +0.003 |
oven | +0.003 |
isdom | +0.003 |
Neg logit contributions | |
sc | -0.002 |
ch | -0.002 |
B | -0.002 |
subs | -0.002 |
ched | -0.002 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
azes | +0.001 |
ires | +0.001 |
pit | +0.001 |
mmm | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
ch | -0.001 |
sc | -0.001 |
B | -0.001 |
subs | -0.001 |
bo | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
ch | +0.017 |
sc | +0.017 |
B | +0.017 |
subs | +0.016 |
ched | +0.015 |
Neg logit contributions | |
azes | -0.028 |
pit | -0.024 |
isdom | -0.024 |
mmm | -0.024 |
ires | -0.023 |
Token | mis |
Token ID | 2984 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
ch | +0.008 |
B | +0.007 |
sc | +0.007 |
scrap | +0.007 |
subs | +0.007 |
Neg logit contributions | |
azes | -0.012 |
pit | -0.010 |
eria | -0.010 |
castle | -0.010 |
ires | -0.010 |
Token | beh |
Token ID | 20709 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
ch | +0.051 |
sc | +0.051 |
B | +0.051 |
subs | +0.049 |
ched | +0.045 |
Neg logit contributions | |
azes | -0.099 |
pit | -0.086 |
isdom | -0.084 |
mmm | -0.084 |
ires | -0.084 |
Token | aving |
Token ID | 2703 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
sc | +0.119 |
ch | +0.117 |
B | +0.114 |
subs | +0.109 |
ched | +0.108 |
Neg logit contributions | |
azes | -0.166 |
pit | -0.144 |
ires | -0.143 |
ement | -0.142 |
mmm | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
ch | +0.029 |
B | +0.029 |
sc | +0.029 |
subs | +0.028 |
Br | +0.026 |
Neg logit contributions | |
azes | -0.037 |
pit | -0.032 |
oven | -0.032 |
fridge | -0.032 |
ement | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +8.57e-04 |
Pos logit contributions | |
azes | +0.017 |
castle | +0.017 |
pit | +0.016 |
balcony | +0.015 |
throne | +0.015 |
Neg logit contributions | |
B | -0.007 |
sc | -0.006 |
ch | -0.006 |
bo | -0.006 |
subs | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.42e-03 |
Pos logit contributions | |
B | +0.001 |
ch | +0.001 |
sc | +0.001 |
subs | +0.001 |
ched | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.002 |
castle | -0.002 |
oven | -0.002 |
fridge | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
azes | +0.007 |
pit | +0.006 |
mmm | +0.006 |
isdom | +0.006 |
ires | +0.006 |
Neg logit contributions | |
ch | -0.004 |
sc | -0.004 |
B | -0.004 |
subs | -0.004 |
ched | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
sc | +0.006 |
ch | +0.006 |
B | +0.005 |
subs | +0.005 |
scrap | +0.005 |
Neg logit contributions | |
azes | -0.015 |
mmm | -0.013 |
isdom | -0.013 |
ires | -0.013 |
ruits | -0.013 |
Token | sky |
Token ID | 6766 |
Feature activation | +8.08e-03 |
Pos logit contributions | |
ch | +0.014 |
sc | +0.013 |
B | +0.013 |
subs | +0.013 |
bo | +0.013 |
Neg logit contributions | |
azes | -0.012 |
mmm | -0.009 |
isdom | -0.009 |
ires | -0.009 |
ement | -0.009 |
Token | before |
Token ID | 878 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
ch | +0.009 |
sc | +0.009 |
fl | +0.008 |
subs | +0.008 |
bo | +0.008 |
Neg logit contributions | |
azes | -0.018 |
isdom | -0.016 |
ocolate | -0.016 |
mmm | -0.016 |
ires | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ch | +0.027 |
B | +0.026 |
subs | +0.024 |
sc | +0.023 |
fl | +0.022 |
Neg logit contributions | |
azes | -0.055 |
pit | -0.049 |
ires | -0.048 |
ruits | -0.048 |
isdom | -0.048 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
azes | +0.031 |
pit | +0.027 |
mmm | +0.027 |
ement | +0.027 |
ires | +0.027 |
Neg logit contributions | |
ch | -0.013 |
sc | -0.013 |
subs | -0.012 |
B | -0.012 |
bo | -0.012 |
Token | fore |
Token ID | 1674 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
ch | +0.023 |
sc | +0.022 |
B | +0.022 |
subs | +0.021 |
ched | +0.020 |
Neg logit contributions | |
azes | -0.040 |
pit | -0.034 |
isdom | -0.034 |
mmm | -0.033 |
ires | -0.033 |
Token | shadow |
Token ID | 19106 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
subs | +0.125 |
text | +0.125 |
B | +0.123 |
ch | +0.119 |
fl | +0.117 |
Neg logit contributions | |
azes | -0.145 |
patiently | -0.129 |
eria | -0.120 |
pit | -0.120 |
isdom | -0.119 |
Token | ed |
Token ID | 276 |
Feature activation | -8.98e-03 |
Pos logit contributions | |
sc | +0.016 |
ch | +0.016 |
B | +0.016 |
subs | +0.015 |
scrap | +0.014 |
Neg logit contributions | |
azes | -0.043 |
ement | -0.039 |
pit | -0.038 |
ires | -0.038 |
ummy | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
azes | +0.019 |
pit | +0.016 |
mmm | +0.016 |
isdom | +0.016 |
ires | +0.016 |
Neg logit contributions | |
sc | -0.011 |
ch | -0.011 |
B | -0.011 |
subs | -0.011 |
ched | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ch | +0.031 |
sc | +0.030 |
B | +0.030 |
subs | +0.030 |
bo | +0.028 |
Neg logit contributions | |
azes | -0.037 |
pit | -0.031 |
isdom | -0.030 |
ires | -0.030 |
mmm | -0.030 |
Token | pour |
Token ID | 48681 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
azes | +0.029 |
isdom | +0.024 |
mmm | +0.024 |
pit | +0.024 |
ires | +0.024 |
Neg logit contributions | |
sc | -0.016 |
ch | -0.016 |
subs | -0.016 |
B | -0.015 |
ched | -0.014 |
Token | told |
Token ID | 1297 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
sc | +0.017 |
ch | +0.017 |
B | +0.017 |
subs | +0.015 |
text | +0.015 |
Neg logit contributions | |
azes | -0.029 |
fridge | -0.025 |
oven | -0.025 |
writing | -0.025 |
patiently | -0.025 |
Token | Max |
Token ID | 5436 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
ch | +0.010 |
B | +0.010 |
sc | +0.009 |
subs | +0.009 |
bo | +0.009 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.011 |
mmm | -0.011 |
castle | -0.011 |
ires | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
B | +0.011 |
ch | +0.011 |
sc | +0.011 |
subs | +0.010 |
ched | +0.010 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.011 |
ires | -0.010 |
mmm | -0.010 |
ement | -0.010 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
B | +0.011 |
ch | +0.010 |
subs | +0.010 |
bo | +0.010 |
sc | +0.010 |
Neg logit contributions | |
azes | -0.021 |
ires | -0.018 |
ement | -0.018 |
pit | -0.018 |
mmm | -0.017 |
Token | mis |
Token ID | 2984 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
azes | +0.025 |
eria | +0.022 |
ae | +0.022 |
mmm | +0.022 |
pit | +0.022 |
Neg logit contributions | |
ch | -0.021 |
B | -0.021 |
scrap | -0.020 |
subs | -0.020 |
bo | -0.019 |
Token | beh |
Token ID | 20709 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
subs | +0.055 |
fl | +0.053 |
ch | +0.053 |
sc | +0.051 |
scrap | +0.050 |
Neg logit contributions | |
azes | -0.109 |
eria | -0.094 |
isdom | -0.093 |
mmm | -0.091 |
idge | -0.090 |
Token | aving |
Token ID | 2703 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
sc | +0.119 |
ch | +0.118 |
B | +0.117 |
subs | +0.111 |
ched | +0.108 |
Neg logit contributions | |
azes | -0.159 |
pit | -0.136 |
ires | -0.134 |
mmm | -0.133 |
ement | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
ch | +0.020 |
sc | +0.020 |
B | +0.020 |
subs | +0.019 |
bo | +0.018 |
Neg logit contributions | |
azes | -0.030 |
pit | -0.025 |
ement | -0.025 |
oven | -0.025 |
isdom | -0.025 |
Token | But |
Token ID | 887 |
Feature activation | +3.58e-04 |
Pos logit contributions | |
B | +0.007 |
ch | +0.007 |
sc | +0.006 |
subs | +0.006 |
scrap | +0.006 |
Neg logit contributions | |
azes | -0.010 |
castle | -0.009 |
pit | -0.009 |
ement | -0.009 |
ires | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
ch | +0.001 |
sc | +0.001 |
B | +0.001 |
subs | +0.001 |
ched | +0.000 |
Neg logit contributions | |
azes | -0.001 |
pit | -0.001 |
isdom | -0.001 |
mmm | -0.001 |
ires | -0.001 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
azes | +0.021 |
mmm | +0.018 |
ires | +0.018 |
pit | +0.018 |
balcony | +0.018 |
Neg logit contributions | |
B | -0.009 |
ch | -0.009 |
subs | -0.009 |
ched | -0.009 |
bo | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ch | +0.018 |
sc | +0.018 |
B | +0.018 |
subs | +0.017 |
ched | +0.016 |
Neg logit contributions | |
azes | -0.025 |
pit | -0.021 |
isdom | -0.021 |
oven | -0.021 |
mmm | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
B | +0.034 |
ch | +0.034 |
sc | +0.033 |
subs | +0.032 |
bo | +0.031 |
Neg logit contributions | |
azes | -0.056 |
pit | -0.049 |
ement | -0.048 |
ires | -0.048 |
isdom | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.003 |
subs | +0.003 |
bo | +0.003 |
Neg logit contributions | |
azes | -0.005 |
pit | -0.004 |
mmm | -0.004 |
ires | -0.004 |
isdom | -0.004 |
Token | work |
Token ID | 670 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
ch | +0.013 |
B | +0.013 |
sc | +0.012 |
subs | +0.012 |
scrap | +0.012 |
Neg logit contributions | |
azes | -0.026 |
pit | -0.023 |
ement | -0.023 |
ires | -0.022 |
mmm | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
sc | +0.059 |
B | +0.056 |
ch | +0.056 |
subs | +0.052 |
ched | +0.050 |
Neg logit contributions | |
azes | -0.109 |
pit | -0.094 |
mmm | -0.093 |
isdom | -0.093 |
ires | -0.093 |
Token | Tears |
Token ID | 40328 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
B | +0.012 |
ch | +0.012 |
sc | +0.012 |
subs | +0.012 |
scrap | +0.011 |
Neg logit contributions | |
azes | -0.015 |
castle | -0.014 |
mmm | -0.014 |
isdom | -0.014 |
pit | -0.013 |
Token | started |
Token ID | 2067 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
fl | +0.091 |
B | +0.089 |
sc | +0.089 |
Fl | +0.087 |
ch | +0.086 |
Neg logit contributions | |
azes | -0.158 |
ement | -0.150 |
patiently | -0.146 |
oven | -0.144 |
writing | -0.143 |
Token | flowing |
Token ID | 17609 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
sc | +0.053 |
ch | +0.051 |
B | +0.051 |
subs | +0.048 |
bo | +0.047 |
Neg logit contributions | |
azes | -0.069 |
pit | -0.058 |
writing | -0.057 |
patiently | -0.057 |
oven | -0.057 |
Token | down |
Token ID | 866 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ch | +0.056 |
B | +0.055 |
sc | +0.055 |
subs | +0.053 |
text | +0.051 |
Neg logit contributions | |
azes | -0.091 |
pit | -0.080 |
ement | -0.079 |
fridge | -0.078 |
patiently | -0.078 |
Token | his |
Token ID | 465 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
azes | +0.024 |
mmm | +0.020 |
isdom | +0.020 |
pit | +0.020 |
ires | +0.020 |
Neg logit contributions | |
ch | -0.015 |
B | -0.015 |
sc | -0.015 |
subs | -0.015 |
ched | -0.014 |
Token | cheeks |
Token ID | 25839 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ch | +0.040 |
sc | +0.040 |
B | +0.040 |
subs | +0.039 |
bo | +0.038 |
Neg logit contributions | |
azes | -0.035 |
pit | -0.029 |
mmm | -0.029 |
isdom | -0.029 |
ires | -0.028 |
Token | became |
Token ID | 2627 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
sc | +0.010 |
B | +0.009 |
ch | +0.009 |
subs | +0.009 |
Free | +0.008 |
Neg logit contributions | |
azes | -0.011 |
patiently | -0.010 |
isdom | -0.010 |
oven | -0.010 |
Jamie | -0.010 |
Token | friendly |
Token ID | 8030 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
azes | +0.015 |
pit | +0.013 |
writing | +0.013 |
oven | +0.013 |
patiently | +0.013 |
Neg logit contributions | |
sc | -0.012 |
ch | -0.012 |
B | -0.011 |
subs | -0.011 |
bo | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
azes | +0.052 |
mmm | +0.045 |
isdom | +0.044 |
oven | +0.044 |
ires | +0.043 |
Neg logit contributions | |
B | -0.037 |
sc | -0.036 |
ch | -0.036 |
subs | -0.035 |
fl | -0.034 |
Token | well |
Token ID | 880 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
sc | +0.007 |
ch | +0.007 |
B | +0.007 |
subs | +0.006 |
text | +0.006 |
Neg logit contributions | |
azes | -0.008 |
writing | -0.007 |
patiently | -0.007 |
isdom | -0.006 |
mmm | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
sc | +0.034 |
ch | +0.034 |
B | +0.033 |
subs | +0.032 |
ched | +0.031 |
Neg logit contributions | |
azes | -0.049 |
pit | -0.042 |
mmm | -0.041 |
isdom | -0.041 |
fridge | -0.041 |
Token | beh |
Token ID | 20709 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
sc | +0.035 |
subs | +0.035 |
ch | +0.034 |
B | +0.034 |
text | +0.034 |
Neg logit contributions | |
azes | -0.058 |
isdom | -0.050 |
mmm | -0.049 |
ires | -0.048 |
castle | -0.048 |
Token | aved |
Token ID | 9586 |
Feature activation | +9.84e-04 |
Pos logit contributions | |
ch | +0.105 |
B | +0.105 |
sc | +0.104 |
subs | +0.100 |
bo | +0.093 |
Neg logit contributions | |
azes | -0.167 |
pit | -0.143 |
isdom | -0.140 |
mmm | -0.139 |
ement | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
ch | +0.001 |
sc | +0.001 |
B | +0.001 |
subs | +0.001 |
bo | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.002 |
ement | -0.002 |
isdom | -0.002 |
ires | -0.002 |
Token | just |
Token ID | 655 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
azes | +0.032 |
ires | +0.027 |
mmm | +0.027 |
pit | +0.026 |
ement | +0.026 |
Neg logit contributions | |
ch | -0.025 |
sc | -0.025 |
B | -0.025 |
subs | -0.024 |
ched | -0.023 |
Token | like |
Token ID | 588 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ch | +0.006 |
sc | +0.006 |
B | +0.006 |
subs | +0.006 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
ement | -0.005 |
mmm | -0.005 |
ires | -0.005 |
Token | Buddy |
Token ID | 36896 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
azes | +0.028 |
pit | +0.024 |
mmm | +0.024 |
ement | +0.024 |
ires | +0.023 |
Neg logit contributions | |
ch | -0.018 |
B | -0.018 |
sc | -0.017 |
subs | -0.017 |
ched | -0.016 |
Token | night |
Token ID | 1755 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
ch | +0.031 |
B | +0.030 |
sc | +0.030 |
subs | +0.029 |
bo | +0.026 |
Neg logit contributions | |
azes | -0.067 |
pit | -0.058 |
mmm | -0.057 |
ires | -0.057 |
isdom | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
sc | +0.098 |
B | +0.097 |
ch | +0.095 |
subs | +0.094 |
ched | +0.091 |
Neg logit contributions | |
azes | -0.077 |
pit | -0.061 |
oven | -0.060 |
fridge | -0.060 |
writing | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
azes | +0.017 |
pit | +0.015 |
isdom | +0.015 |
ement | +0.015 |
mmm | +0.015 |
Neg logit contributions | |
ch | -0.004 |
B | -0.004 |
sc | -0.004 |
subs | -0.003 |
Free | -0.003 |
Token | wild |
Token ID | 4295 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ch | +0.016 |
B | +0.016 |
sc | +0.014 |
subs | +0.014 |
Spot | +0.013 |
Neg logit contributions | |
azes | -0.038 |
mmm | -0.035 |
pit | -0.034 |
isdom | -0.034 |
ement | -0.033 |
Token | cat |
Token ID | 3797 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
ch | +0.014 |
B | +0.013 |
sc | +0.013 |
subs | +0.012 |
fl | +0.012 |
Neg logit contributions | |
azes | -0.025 |
mmm | -0.023 |
pit | -0.022 |
ement | -0.022 |
castle | -0.022 |
Token | lur |
Token ID | 20605 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
ch | +0.007 |
B | +0.007 |
sc | +0.007 |
subs | +0.006 |
bo | +0.006 |
Neg logit contributions | |
azes | -0.020 |
mmm | -0.017 |
ires | -0.017 |
ement | -0.017 |
pit | -0.017 |
Token | ked |
Token ID | 9091 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
subs | +0.108 |
B | +0.103 |
fl | +0.101 |
Br | +0.097 |
Spot | +0.097 |
Neg logit contributions | |
azes | -0.142 |
isdom | -0.124 |
patiently | -0.122 |
ues | -0.122 |
sing | -0.122 |
Token | through |
Token ID | 832 |
Feature activation | -2.58e-03 |
Pos logit contributions | |
ch | +0.022 |
sc | +0.022 |
B | +0.021 |
subs | +0.020 |
ched | +0.020 |
Neg logit contributions | |
azes | -0.036 |
mmm | -0.031 |
pit | -0.031 |
ement | -0.030 |
isdom | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
azes | +0.007 |
pit | +0.006 |
mmm | +0.006 |
castle | +0.006 |
ement | +0.006 |
Neg logit contributions | |
B | -0.002 |
ch | -0.002 |
sc | -0.002 |
subs | -0.002 |
scrap | -0.002 |
Token | woods |
Token ID | 16479 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
azes | +0.003 |
pit | +0.002 |
mmm | +0.002 |
isdom | +0.002 |
ement | +0.002 |
Neg logit contributions | |
ch | -0.003 |
B | -0.003 |
sc | -0.003 |
subs | -0.003 |
bo | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
sc | +0.005 |
ch | +0.005 |
B | +0.005 |
ny | +0.005 |
fl | +0.005 |
Neg logit contributions | |
azes | -0.011 |
mmm | -0.011 |
mmmm | -0.010 |
isdom | -0.010 |
ocolate | -0.010 |
Token | needle |
Token ID | 17598 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
sc | +0.035 |
ch | +0.035 |
B | +0.035 |
subs | +0.033 |
ched | +0.032 |
Neg logit contributions | |
azes | -0.041 |
pit | -0.035 |
oven | -0.034 |
fridge | -0.034 |
isdom | -0.034 |
Token | or |
Token ID | 393 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
B | +0.071 |
ch | +0.070 |
sc | +0.070 |
subs | +0.068 |
text | +0.064 |
Neg logit contributions | |
azes | -0.087 |
pit | -0.076 |
oven | -0.073 |
fridge | -0.073 |
castle | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
sc | +0.038 |
B | +0.038 |
ch | +0.037 |
subs | +0.037 |
ched | +0.035 |
Neg logit contributions | |
azes | -0.040 |
fridge | -0.035 |
oven | -0.035 |
writing | -0.034 |
pasta | -0.034 |
Token | st |
Token ID | 336 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
ch | +0.027 |
B | +0.027 |
sc | +0.027 |
subs | +0.026 |
scrap | +0.025 |
Neg logit contributions | |
azes | -0.040 |
ires | -0.034 |
mmm | -0.034 |
isdom | -0.033 |
ement | -0.033 |
Token | eth |
Token ID | 2788 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
B | +0.088 |
sc | +0.086 |
ch | +0.081 |
fl | +0.080 |
subs | +0.079 |
Neg logit contributions | |
azes | -0.150 |
fridge | -0.126 |
pit | -0.126 |
oven | -0.125 |
ires | -0.125 |
Token | oscope |
Token ID | 40326 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
B | +0.071 |
subs | +0.068 |
sc | +0.067 |
ch | +0.066 |
W | +0.063 |
Neg logit contributions | |
azes | -0.065 |
oven | -0.056 |
fridge | -0.056 |
writing | -0.056 |
pit | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
B | +0.122 |
sc | +0.119 |
ch | +0.117 |
subs | +0.115 |
Br | +0.110 |
Neg logit contributions | |
azes | -0.140 |
oven | -0.120 |
pit | -0.119 |
fridge | -0.118 |
writing | -0.117 |
Token | They |
Token ID | 1119 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
ch | +0.017 |
sc | +0.017 |
B | +0.017 |
subs | +0.016 |
ched | +0.015 |
Neg logit contributions | |
azes | -0.023 |
pit | -0.019 |
ires | -0.019 |
mmm | -0.019 |
isdom | -0.019 |
Token | did |
Token ID | 750 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.003 |
subs | +0.003 |
fl | +0.002 |
Neg logit contributions | |
azes | -0.004 |
pit | -0.004 |
fridge | -0.004 |
isdom | -0.004 |
oven | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
sc | +0.049 |
ch | +0.049 |
B | +0.049 |
subs | +0.048 |
bo | +0.045 |
Neg logit contributions | |
azes | -0.031 |
isdom | -0.023 |
ires | -0.023 |
mmm | -0.023 |
pit | -0.023 |
Token | want |
Token ID | 765 |
Feature activation | -4.43e-04 |
Pos logit contributions | |
sc | +0.040 |
ch | +0.040 |
B | +0.040 |
subs | +0.039 |
ched | +0.037 |
Neg logit contributions | |
azes | -0.042 |
pit | -0.034 |
isdom | -0.034 |
mmm | -0.034 |
oven | -0.033 |
Token | very |
Token ID | 845 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
azes | +0.028 |
pit | +0.024 |
mmm | +0.024 |
ement | +0.024 |
isdom | +0.024 |
Neg logit contributions | |
ch | -0.021 |
B | -0.020 |
sc | -0.020 |
subs | -0.020 |
bo | -0.019 |
Token | naughty |
Token ID | 45128 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
azes | +0.018 |
pit | +0.015 |
ement | +0.015 |
isdom | +0.015 |
mmm | +0.015 |
Neg logit contributions | |
ch | -0.012 |
B | -0.012 |
sc | -0.011 |
subs | -0.011 |
bo | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ch | +0.006 |
B | +0.006 |
sc | +0.005 |
fl | +0.005 |
subs | +0.005 |
Neg logit contributions | |
azes | -0.011 |
isdom | -0.010 |
mmm | -0.010 |
ocolate | -0.009 |
castle | -0.009 |
Token | always |
Token ID | 1464 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
sc | +0.024 |
B | +0.024 |
ch | +0.024 |
subs | +0.023 |
text | +0.022 |
Neg logit contributions | |
azes | -0.031 |
oven | -0.026 |
fridge | -0.026 |
pit | -0.026 |
isdom | -0.026 |
Token | mis |
Token ID | 2984 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
ch | +0.018 |
sc | +0.018 |
B | +0.018 |
subs | +0.017 |
ched | +0.016 |
Neg logit contributions | |
azes | -0.034 |
pit | -0.029 |
mmm | -0.029 |
isdom | -0.029 |
ires | -0.029 |
Token | beh |
Token ID | 20709 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
ch | +0.049 |
sc | +0.049 |
subs | +0.048 |
B | +0.045 |
text | +0.044 |
Neg logit contributions | |
azes | -0.117 |
isdom | -0.099 |
pit | -0.098 |
eria | -0.098 |
mmm | -0.097 |
Token | aving |
Token ID | 2703 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
sc | +0.103 |
ch | +0.102 |
B | +0.101 |
subs | +0.095 |
ched | +0.093 |
Neg logit contributions | |
azes | -0.165 |
pit | -0.143 |
ires | -0.141 |
ement | -0.141 |
mmm | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
ch | +0.030 |
sc | +0.030 |
B | +0.030 |
subs | +0.029 |
bo | +0.027 |
Neg logit contributions | |
azes | -0.042 |
pit | -0.035 |
isdom | -0.034 |
oven | -0.034 |
ires | -0.034 |
Token | One |
Token ID | 1881 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
B | +0.002 |
Fl | +0.002 |
ch | +0.002 |
| | +0.002 |
W | +0.002 |
Neg logit contributions | |
castle | -0.005 |
azes | -0.005 |
patiently | -0.005 |
ues | -0.005 |
pit | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
azes | +0.026 |
fridge | +0.022 |
oven | +0.022 |
pit | +0.022 |
refrigerator | +0.022 |
Neg logit contributions | |
sc | -0.017 |
subs | -0.016 |
B | -0.016 |
ch | -0.016 |
ched | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
sc | +0.033 |
ch | +0.033 |
B | +0.032 |
subs | +0.032 |
bo | +0.031 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.022 |
mmm | -0.021 |
oven | -0.021 |
writing | -0.021 |
Token | listen |
Token ID | 6004 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
sc | +0.022 |
B | +0.022 |
ch | +0.021 |
subs | +0.020 |
text | +0.020 |
Neg logit contributions | |
azes | -0.026 |
pit | -0.021 |
writing | -0.021 |
isdom | -0.021 |
fridge | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
ch | +0.002 |
sc | +0.002 |
B | +0.002 |
subs | +0.002 |
ched | +0.002 |
Neg logit contributions | |
azes | -0.005 |
pit | -0.005 |
mmm | -0.005 |
ement | -0.005 |
isdom | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
azes | +0.009 |
studio | +0.008 |
castle | +0.008 |
writing | +0.008 |
canvas | +0.008 |
Neg logit contributions | |
ch | -0.005 |
B | -0.005 |
ny | -0.005 |
sc | -0.005 |
Spot | -0.005 |
Token | always |
Token ID | 1464 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
azes | +0.013 |
pit | +0.011 |
mmm | +0.011 |
ires | +0.011 |
isdom | +0.011 |
Neg logit contributions | |
ch | -0.008 |
B | -0.008 |
sc | -0.008 |
subs | -0.008 |
bo | -0.007 |
Token | mis |
Token ID | 2984 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
ch | +0.018 |
B | +0.018 |
sc | +0.018 |
subs | +0.017 |
bo | +0.016 |
Neg logit contributions | |
azes | -0.037 |
ement | -0.032 |
pit | -0.032 |
ires | -0.032 |
mmm | -0.032 |
Token | beh |
Token ID | 20709 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
sc | +0.041 |
subs | +0.041 |
ch | +0.040 |
B | +0.037 |
text | +0.036 |
Neg logit contributions | |
azes | -0.114 |
isdom | -0.099 |
pit | -0.096 |
mmm | -0.096 |
eria | -0.096 |
Token | aved |
Token ID | 9586 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
sc | +0.109 |
ch | +0.109 |
B | +0.107 |
subs | +0.102 |
ched | +0.099 |
Neg logit contributions | |
azes | -0.157 |
pit | -0.134 |
ires | -0.132 |
ement | -0.132 |
mmm | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
azes | +0.013 |
mmm | +0.011 |
pit | +0.011 |
isdom | +0.011 |
ement | +0.011 |
Neg logit contributions | |
ch | -0.008 |
sc | -0.008 |
B | -0.008 |
subs | -0.008 |
ched | -0.008 |
Token | caused |
Token ID | 4073 |
Feature activation | +9.85e-04 |
Pos logit contributions | |
ch | +0.024 |
B | +0.024 |
sc | +0.024 |
subs | +0.023 |
ched | +0.022 |
Neg logit contributions | |
azes | -0.036 |
pit | -0.031 |
ement | -0.031 |
mmm | -0.030 |
ires | -0.030 |
Token | trouble |
Token ID | 5876 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
sc | +0.001 |
ch | +0.001 |
B | +0.001 |
subs | +0.001 |
ched | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.002 |
isdom | -0.002 |
ires | -0.002 |
mmm | -0.002 |
Token | wherever |
Token ID | 14530 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ch | +0.039 |
sc | +0.038 |
B | +0.038 |
subs | +0.037 |
bo | +0.035 |
Neg logit contributions | |
azes | -0.048 |
pit | -0.040 |
writing | -0.040 |
isdom | -0.039 |
oven | -0.039 |
Token | knee |
Token ID | 10329 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
sc | +0.035 |
ch | +0.034 |
B | +0.034 |
subs | +0.032 |
ched | +0.032 |
Neg logit contributions | |
azes | -0.019 |
pit | -0.014 |
fridge | -0.014 |
writing | -0.014 |
ires | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
B | +0.045 |
sc | +0.045 |
Ar | +0.045 |
text | +0.044 |
Free | +0.044 |
Neg logit contributions | |
azes | -0.027 |
fridge | -0.024 |
patiently | -0.023 |
writing | -0.023 |
oven | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
sc | +0.051 |
ch | +0.045 |
B | +0.045 |
subs | +0.043 |
Ar | +0.043 |
Neg logit contributions | |
azes | -0.066 |
fridge | -0.060 |
writing | -0.060 |
pasta | -0.057 |
desk | -0.057 |
Token | started |
Token ID | 2067 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Ar | +0.040 |
text | +0.038 |
| | +0.038 |
sc | +0.038 |
fl | +0.034 |
Neg logit contributions | |
fridge | -0.042 |
patiently | -0.041 |
writing | -0.038 |
azes | -0.038 |
desk | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
sc | +0.071 |
text | +0.070 |
Ar | +0.065 |
Fl | +0.064 |
B | +0.063 |
Neg logit contributions | |
azes | -0.057 |
writing | -0.054 |
counting | -0.050 |
reading | -0.049 |
patiently | -0.049 |
Token | bleed |
Token ID | 30182 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
sc | +0.030 |
text | +0.028 |
B | +0.026 |
subs | +0.026 |
fl | +0.026 |
Neg logit contributions | |
azes | -0.041 |
fridge | -0.040 |
oven | -0.038 |
balcony | -0.038 |
writing | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
B | +0.129 |
sc | +0.128 |
ch | +0.125 |
subs | +0.125 |
Br | +0.123 |
Neg logit contributions | |
azes | -0.117 |
patiently | -0.104 |
fridge | -0.102 |
writing | -0.102 |
oven | -0.099 |
Token | |
Token ID | 220 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
sc | +0.025 |
ch | +0.025 |
B | +0.024 |
subs | +0.024 |
ched | +0.022 |
Neg logit contributions | |
azes | -0.035 |
pit | -0.030 |
mmm | -0.030 |
fridge | -0.029 |
isdom | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ch | +0.027 |
sc | +0.027 |
B | +0.026 |
subs | +0.026 |
bo | +0.024 |
Neg logit contributions | |
azes | -0.046 |
pit | -0.039 |
ires | -0.039 |
mmm | -0.038 |
isdom | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
subs | +0.036 |
sc | +0.036 |
ch | +0.036 |
B | +0.035 |
fl | +0.033 |
Neg logit contributions | |
azes | -0.054 |
mmm | -0.045 |
ires | -0.045 |
ement | -0.044 |
pit | -0.044 |
Token | Tim |
Token ID | 14967 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
sc | +0.035 |
subs | +0.034 |
fl | +0.032 |
text | +0.032 |
ch | +0.031 |
Neg logit contributions | |
azes | -0.038 |
mmm | -0.033 |
isdom | -0.032 |
fridge | -0.032 |
ocolate | -0.031 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.004 |
fridge | +0.004 |
castle | +0.004 |
writing | +0.004 |
Neg logit contributions | |
sc | -0.003 |
B | -0.003 |
ch | -0.003 |
subs | -0.002 |
Br | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
azes | +0.088 |
mmm | +0.078 |
pit | +0.075 |
isdom | +0.075 |
ement | +0.074 |
Neg logit contributions | |
B | -0.046 |
ch | -0.046 |
scrap | -0.041 |
ched | -0.041 |
sc | -0.041 |
Token | other |
Token ID | 584 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
azes | +0.020 |
mmm | +0.018 |
isdom | +0.017 |
pit | +0.017 |
ocolate | +0.017 |
Neg logit contributions | |
ch | -0.013 |
B | -0.012 |
sc | -0.012 |
subs | -0.012 |
scrap | -0.011 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
azes | +0.030 |
mmm | +0.026 |
isdom | +0.026 |
ement | +0.025 |
ocolate | +0.025 |
Neg logit contributions | |
sc | -0.023 |
ch | -0.023 |
B | -0.023 |
subs | -0.022 |
text | -0.021 |
Token | mis |
Token ID | 2984 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
azes | +0.018 |
mmm | +0.017 |
isdom | +0.016 |
ires | +0.016 |
ae | +0.016 |
Neg logit contributions | |
sc | -0.018 |
ch | -0.018 |
B | -0.018 |
subs | -0.018 |
ched | -0.017 |
Token | beh |
Token ID | 20709 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
ch | +0.052 |
sc | +0.050 |
subs | +0.050 |
B | +0.049 |
fl | +0.047 |
Neg logit contributions | |
azes | -0.089 |
pit | -0.076 |
isdom | -0.074 |
mmm | -0.073 |
eria | -0.073 |
Token | aving |
Token ID | 2703 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ch | +0.102 |
sc | +0.102 |
B | +0.102 |
subs | +0.097 |
bo | +0.091 |
Neg logit contributions | |
azes | -0.159 |
pit | -0.135 |
isdom | -0.133 |
mmm | -0.132 |
ires | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ch | +0.017 |
B | +0.017 |
sc | +0.017 |
subs | +0.016 |
bo | +0.015 |
Neg logit contributions | |
azes | -0.023 |
pit | -0.020 |
isdom | -0.019 |
ement | -0.019 |
oven | -0.019 |
Token | running |
Token ID | 2491 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ch | +0.014 |
sc | +0.014 |
B | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.023 |
mmm | -0.019 |
ement | -0.019 |
pit | -0.019 |
ires | -0.019 |
Token | around |
Token ID | 1088 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
subs | +0.025 |
ch | +0.025 |
B | +0.024 |
text | +0.024 |
Br | +0.024 |
Neg logit contributions | |
azes | -0.033 |
pit | -0.030 |
patiently | -0.029 |
ement | -0.028 |
castle | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
azes | +0.050 |
mmm | +0.043 |
isdom | +0.043 |
pit | +0.042 |
ires | +0.042 |
Neg logit contributions | |
sc | -0.025 |
B | -0.025 |
ch | -0.024 |
subs | -0.022 |
ched | -0.021 |
Token | play |
Token ID | 711 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
ch | +0.009 |
B | +0.009 |
subs | +0.009 |
scrap | +0.009 |
sc | +0.008 |
Neg logit contributions | |
azes | -0.022 |
ires | -0.019 |
mmm | -0.019 |
pit | -0.019 |
ement | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-04 |
Pos logit contributions | |
B | +0.009 |
sc | +0.008 |
ch | +0.008 |
ched | +0.007 |
subs | +0.007 |
Neg logit contributions | |
azes | -0.018 |
isdom | -0.016 |
mmm | -0.016 |
ruits | -0.016 |
ires | -0.016 |
Token | |
Token ID | 220 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
ch | +0.001 |
sc | +0.001 |
B | +0.001 |
subs | +0.001 |
bo | +0.001 |
Neg logit contributions | |
azes | -0.001 |
pit | -0.001 |
isdom | -0.001 |
ires | -0.001 |
mmm | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -5.77e-04 |
Pos logit contributions | |
ch | +0.009 |
B | +0.009 |
sc | +0.009 |
subs | +0.009 |
ched | +0.008 |
Neg logit contributions | |
azes | -0.019 |
pit | -0.017 |
isdom | -0.017 |
oven | -0.017 |
ement | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
azes | +0.001 |
mmm | +0.001 |
ocolate | +0.001 |
ires | +0.001 |
writing | +0.001 |
Neg logit contributions | |
sc | -0.001 |
subs | -0.001 |
ch | -0.001 |
B | -0.001 |
fl | -0.001 |
Token | THE |
Token ID | 10970 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
azes | +0.012 |
mmm | +0.011 |
ocolate | +0.011 |
eria | +0.011 |
ae | +0.011 |
Neg logit contributions | |
fl | -0.010 |
sc | -0.010 |
subs | -0.009 |
ch | -0.009 |
bo | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ch | +0.095 |
sc | +0.095 |
B | +0.094 |
subs | +0.091 |
bo | +0.085 |
Neg logit contributions | |
azes | -0.165 |
pit | -0.143 |
ires | -0.141 |
isdom | -0.140 |
ement | -0.140 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
subs | +0.018 |
sc | +0.018 |
beh | +0.017 |
burn | +0.017 |
ch | +0.017 |
Neg logit contributions | |
azes | -0.018 |
fridge | -0.015 |
ement | -0.015 |
refrigerator | -0.015 |
pit | -0.015 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
sc | +0.027 |
ch | +0.027 |
B | +0.027 |
subs | +0.026 |
ched | +0.025 |
Neg logit contributions | |
azes | -0.032 |
pit | -0.027 |
ires | -0.026 |
isdom | -0.026 |
ement | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
sc | +0.054 |
subs | +0.053 |
ch | +0.053 |
B | +0.051 |
fl | +0.049 |
Neg logit contributions | |
azes | -0.058 |
writing | -0.047 |
fridge | -0.046 |
mmm | -0.046 |
pit | -0.046 |
Token | time |
Token ID | 640 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
sc | +0.035 |
ch | +0.034 |
B | +0.034 |
subs | +0.033 |
ched | +0.030 |
Neg logit contributions | |
azes | -0.082 |
pit | -0.072 |
mmm | -0.071 |
isdom | -0.071 |
oven | -0.071 |
Token | went |
Token ID | 1816 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
sc | +0.007 |
ch | +0.007 |
B | +0.007 |
subs | +0.006 |
fl | +0.006 |
Neg logit contributions | |
azes | -0.013 |
oven | -0.011 |
pit | -0.011 |
fridge | -0.011 |
patiently | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.004 |
oven | +0.004 |
fridge | +0.004 |
patiently | +0.004 |
Neg logit contributions | |
B | -0.003 |
ch | -0.003 |
sc | -0.003 |
subs | -0.003 |
text | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
ch | +0.004 |
B | +0.004 |
scrap | +0.004 |
sc | +0.004 |
subs | +0.004 |
Neg logit contributions | |
azes | -0.011 |
ement | -0.010 |
pit | -0.010 |
mmm | -0.010 |
ires | -0.010 |
Token | room |
Token ID | 2119 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
azes | +0.007 |
mmm | +0.006 |
otion | +0.006 |
isdom | +0.006 |
ocolate | +0.006 |
Neg logit contributions | |
B | -0.006 |
sc | -0.006 |
ch | -0.006 |
subs | -0.006 |
scrap | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
sc | +0.012 |
subs | +0.010 |
B | +0.010 |
went | +0.010 |
ch | +0.010 |
Neg logit contributions | |
azes | -0.030 |
mmm | -0.028 |
isdom | -0.026 |
ires | -0.026 |
mmmm | -0.026 |
Token | sul |
Token ID | 33154 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
ch | +0.006 |
sc | +0.005 |
B | +0.005 |
subs | +0.005 |
scrap | +0.005 |
Neg logit contributions | |
azes | -0.013 |
ement | -0.011 |
mmm | -0.011 |
ires | -0.011 |
pit | -0.011 |
Token | ked |
Token ID | 9091 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
B | +0.079 |
ch | +0.079 |
sc | +0.078 |
subs | +0.074 |
text | +0.068 |
Neg logit contributions | |
azes | -0.181 |
pit | -0.158 |
ires | -0.154 |
isdom | -0.154 |
fridge | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
ch | +0.024 |
sc | +0.024 |
B | +0.024 |
subs | +0.023 |
ched | +0.022 |
Neg logit contributions | |
azes | -0.041 |
pit | -0.035 |
mmm | -0.035 |
isdom | -0.035 |
ires | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
B | +0.006 |
ch | +0.006 |
sc | +0.006 |
Br | +0.005 |
subs | +0.005 |
Neg logit contributions | |
azes | -0.020 |
castle | -0.019 |
pit | -0.018 |
isdom | -0.018 |
ement | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ch | +0.025 |
sc | +0.025 |
B | +0.024 |
subs | +0.023 |
ched | +0.022 |
Neg logit contributions | |
azes | -0.047 |
pit | -0.041 |
isdom | -0.040 |
mmm | -0.040 |
ires | -0.040 |
Token | Then |
Token ID | 6423 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ch | +0.024 |
sc | +0.024 |
B | +0.024 |
subs | +0.023 |
ched | +0.022 |
Neg logit contributions | |
azes | -0.040 |
pit | -0.034 |
isdom | -0.033 |
mmm | -0.033 |
ires | -0.033 |
Token | for |
Token ID | 329 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
azes | +0.035 |
ires | +0.029 |
isdom | +0.028 |
Majesty | +0.028 |
pit | +0.028 |
Neg logit contributions | |
sc | -0.021 |
ch | -0.021 |
B | -0.020 |
subs | -0.018 |
ched | -0.018 |
Token | being |
Token ID | 852 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
azes | +0.038 |
pit | +0.035 |
ires | +0.033 |
oven | +0.032 |
fridge | +0.032 |
Neg logit contributions | |
B | -0.023 |
ch | -0.023 |
sc | -0.021 |
subs | -0.021 |
scrap | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
ch | +0.004 |
sc | +0.004 |
B | +0.004 |
subs | +0.003 |
ched | +0.003 |
Neg logit contributions | |
azes | -0.004 |
pit | -0.003 |
isdom | -0.003 |
mmm | -0.003 |
ires | -0.003 |
Token | well |
Token ID | 880 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
sc | +0.005 |
ch | +0.005 |
B | +0.005 |
subs | +0.005 |
ched | +0.005 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
ires | -0.005 |
isdom | -0.005 |
mmm | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
sc | +0.049 |
ch | +0.048 |
B | +0.048 |
subs | +0.046 |
ched | +0.044 |
Neg logit contributions | |
azes | -0.072 |
pit | -0.060 |
isdom | -0.059 |
mmm | -0.059 |
ires | -0.059 |
Token | beh |
Token ID | 20709 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
text | +0.047 |
sc | +0.047 |
subs | +0.046 |
ch | +0.044 |
B | +0.043 |
Neg logit contributions | |
azes | -0.071 |
isdom | -0.063 |
mmm | -0.061 |
patiently | -0.060 |
ae | -0.060 |
Token | aved |
Token ID | 9586 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
ch | +0.099 |
sc | +0.099 |
B | +0.099 |
subs | +0.094 |
bo | +0.088 |
Neg logit contributions | |
azes | -0.158 |
pit | -0.135 |
isdom | -0.133 |
mmm | -0.132 |
ires | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ch | +0.008 |
B | +0.008 |
sc | +0.008 |
subs | +0.007 |
bo | +0.007 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.009 |
ement | -0.008 |
oven | -0.008 |
isdom | -0.008 |
Token | Jack |
Token ID | 3619 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
ch | +0.017 |
sc | +0.017 |
B | +0.017 |
subs | +0.016 |
ched | +0.015 |
Neg logit contributions | |
azes | -0.018 |
pit | -0.014 |
ires | -0.014 |
isdom | -0.014 |
mmm | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ch | +0.004 |
sc | +0.004 |
B | +0.004 |
subs | +0.004 |
bo | +0.003 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.009 |
ires | -0.008 |
mmm | -0.008 |
isdom | -0.008 |
Token | delighted |
Token ID | 20707 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
azes | +0.035 |
pit | +0.029 |
isdom | +0.028 |
ires | +0.028 |
mmm | +0.028 |
Neg logit contributions | |
ch | -0.034 |
B | -0.033 |
sc | -0.033 |
subs | -0.032 |
bo | -0.031 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ch | +0.026 |
sc | +0.025 |
B | +0.024 |
text | +0.024 |
ched | +0.024 |
Neg logit contributions | |
azes | -0.029 |
pit | -0.028 |
fridge | -0.028 |
oven | -0.027 |
refrigerator | -0.027 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
B | +0.014 |
ch | +0.014 |
subs | +0.014 |
sc | +0.014 |
bo | +0.014 |
Neg logit contributions | |
azes | -0.033 |
pit | -0.028 |
ires | -0.028 |
mmm | -0.028 |
ocolate | -0.027 |
Token | 't |
Token ID | 470 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
sc | +0.066 |
ch | +0.064 |
B | +0.064 |
subs | +0.063 |
fl | +0.062 |
Neg logit contributions | |
azes | -0.063 |
mmm | -0.054 |
ocolate | -0.052 |
ement | -0.051 |
ires | -0.051 |
Token | understand |
Token ID | 1833 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
sc | +0.028 |
B | +0.027 |
ch | +0.027 |
text | +0.026 |
subs | +0.026 |
Neg logit contributions | |
azes | -0.024 |
isdom | -0.020 |
writing | -0.019 |
mmm | -0.019 |
patiently | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
azes | +0.015 |
pit | +0.013 |
castle | +0.013 |
balcony | +0.013 |
sing | +0.013 |
Neg logit contributions | |
ch | -0.009 |
B | -0.009 |
sc | -0.008 |
ched | -0.008 |
scrap | -0.008 |
Token | Tears |
Token ID | 40328 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
ny | +0.003 |
bo | +0.003 |
s | +0.003 |
subs | +0.003 |
B | +0.003 |
Neg logit contributions | |
azes | -0.006 |
castle | -0.006 |
ocket | -0.005 |
mmm | -0.005 |
otion | -0.005 |
Token | started |
Token ID | 2067 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
fl | +0.096 |
sc | +0.089 |
Fl | +0.089 |
ch | +0.088 |
Rex | +0.087 |
Neg logit contributions | |
ement | -0.138 |
azes | -0.137 |
patiently | -0.130 |
writing | -0.126 |
oven | -0.125 |
Token | rolling |
Token ID | 10708 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
sc | +0.046 |
ch | +0.043 |
B | +0.042 |
text | +0.041 |
bo | +0.040 |
Neg logit contributions | |
azes | -0.057 |
writing | -0.049 |
patiently | -0.049 |
fridge | -0.047 |
pit | -0.047 |
Token | down |
Token ID | 866 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ch | +0.023 |
text | +0.022 |
sc | +0.022 |
subs | +0.022 |
B | +0.022 |
Neg logit contributions | |
azes | -0.032 |
ement | -0.030 |
pit | -0.030 |
patiently | -0.029 |
refrigerator | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
azes | +0.026 |
pit | +0.022 |
ement | +0.021 |
isdom | +0.021 |
oven | +0.021 |
Neg logit contributions | |
ch | -0.016 |
sc | -0.016 |
B | -0.016 |
subs | -0.016 |
bo | -0.015 |
Token | face |
Token ID | 1986 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ch | +0.034 |
sc | +0.034 |
B | +0.033 |
subs | +0.032 |
ched | +0.031 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.021 |
ement | -0.021 |
fridge | -0.021 |
isdom | -0.020 |
Token | told |
Token ID | 1297 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
azes | +0.027 |
pit | +0.023 |
ires | +0.023 |
mmm | +0.023 |
isdom | +0.023 |
Neg logit contributions | |
ch | -0.012 |
B | -0.012 |
sc | -0.012 |
subs | -0.011 |
ched | -0.010 |
Token | him |
Token ID | 683 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ch | +0.007 |
B | +0.007 |
sc | +0.007 |
subs | +0.007 |
bo | +0.006 |
Neg logit contributions | |
azes | -0.007 |
pit | -0.005 |
ires | -0.005 |
castle | -0.005 |
ement | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
azes | +0.043 |
pit | +0.039 |
ement | +0.037 |
ires | +0.037 |
mmm | +0.037 |
Neg logit contributions | |
ch | -0.028 |
B | -0.028 |
sc | -0.027 |
subs | -0.027 |
ched | -0.026 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
B | +0.003 |
ch | +0.003 |
sc | +0.003 |
subs | +0.003 |
bo | +0.003 |
Neg logit contributions | |
azes | -0.005 |
ires | -0.005 |
ement | -0.005 |
pit | -0.005 |
oven | -0.004 |
Token | mis |
Token ID | 2984 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
azes | +0.035 |
eria | +0.032 |
pit | +0.031 |
isdom | +0.031 |
ae | +0.031 |
Neg logit contributions | |
ch | -0.029 |
B | -0.028 |
subs | -0.027 |
sc | -0.026 |
scrap | -0.026 |
Token | beh |
Token ID | 20709 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
subs | +0.054 |
fl | +0.052 |
ch | +0.050 |
scrap | +0.049 |
text | +0.048 |
Neg logit contributions | |
azes | -0.101 |
eria | -0.085 |
mmm | -0.085 |
isdom | -0.084 |
pit | -0.083 |
Token | aving |
Token ID | 2703 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
sc | +0.104 |
ch | +0.104 |
B | +0.103 |
subs | +0.099 |
ched | +0.094 |
Neg logit contributions | |
azes | -0.153 |
pit | -0.130 |
mmm | -0.127 |
ires | -0.127 |
isdom | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
ch | +0.012 |
sc | +0.012 |
B | +0.012 |
subs | +0.011 |
ched | +0.011 |
Neg logit contributions | |
azes | -0.014 |
pit | -0.011 |
isdom | -0.011 |
mmm | -0.011 |
ires | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ch | +0.012 |
sc | +0.012 |
B | +0.012 |
subs | +0.012 |
ched | +0.011 |
Neg logit contributions | |
azes | -0.016 |
pit | -0.014 |
mmm | -0.013 |
isdom | -0.013 |
ement | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ch | +0.026 |
sc | +0.026 |
B | +0.026 |
subs | +0.025 |
ched | +0.023 |
Neg logit contributions | |
azes | -0.035 |
pit | -0.030 |
isdom | -0.029 |
mmm | -0.029 |
ires | -0.029 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
azes | +0.023 |
pit | +0.019 |
patiently | +0.019 |
writing | +0.018 |
castle | +0.018 |
Neg logit contributions | |
sc | -0.027 |
ch | -0.026 |
B | -0.026 |
subs | -0.026 |
text | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
azes | +0.033 |
ires | +0.027 |
mmm | +0.027 |
pit | +0.027 |
isdom | +0.026 |
Neg logit contributions | |
ch | -0.018 |
sc | -0.018 |
B | -0.017 |
subs | -0.017 |
fl | -0.017 |
Token | |
Token ID | 220 |
Feature activation | -6.13e-04 |
Pos logit contributions | |
azes | +0.009 |
pit | +0.008 |
ement | +0.008 |
isdom | +0.008 |
castle | +0.008 |
Neg logit contributions | |
B | -0.004 |
ch | -0.004 |
sc | -0.004 |
subs | -0.004 |
bo | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
azes | +0.001 |
ement | +0.001 |
pit | +0.001 |
oven | +0.001 |
fridge | +0.001 |
Neg logit contributions | |
ch | -0.001 |
B | -0.001 |
sc | -0.001 |
subs | -0.001 |
bo | -0.001 |
Token | |
Token ID | 220 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
azes | +0.022 |
pit | +0.019 |
ires | +0.018 |
mmm | +0.018 |
isdom | +0.018 |
Neg logit contributions | |
sc | -0.013 |
ch | -0.013 |
subs | -0.013 |
B | -0.013 |
bo | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
azes | +0.012 |
ement | +0.010 |
pit | +0.010 |
isdom | +0.010 |
oven | +0.010 |
Neg logit contributions | |
ch | -0.006 |
B | -0.006 |
sc | -0.006 |
subs | -0.006 |
bo | -0.005 |
Token | THE |
Token ID | 10970 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
azes | +0.034 |
mmm | +0.030 |
pit | +0.030 |
ires | +0.030 |
ocolate | +0.029 |
Neg logit contributions | |
sc | -0.016 |
subs | -0.015 |
ch | -0.015 |
B | -0.015 |
scrap | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
B | +0.080 |
ch | +0.079 |
sc | +0.078 |
subs | +0.077 |
fl | +0.074 |
Neg logit contributions | |
azes | -0.174 |
pit | -0.155 |
ires | -0.155 |
ement | -0.153 |
isdom | -0.151 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
subs | +0.012 |
sc | +0.012 |
ch | +0.011 |
scrap | +0.011 |
burn | +0.011 |
Neg logit contributions | |
azes | -0.015 |
pit | -0.013 |
ement | -0.012 |
fridge | -0.012 |
refrigerator | -0.012 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
ch | +0.026 |
sc | +0.025 |
B | +0.025 |
subs | +0.024 |
ched | +0.023 |
Neg logit contributions | |
azes | -0.031 |
pit | -0.026 |
isdom | -0.026 |
mmm | -0.026 |
ires | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
sc | +0.053 |
subs | +0.053 |
ch | +0.052 |
B | +0.050 |
fl | +0.048 |
Neg logit contributions | |
azes | -0.055 |
writing | -0.045 |
mmm | -0.044 |
fridge | -0.044 |
pit | -0.044 |
Token | time |
Token ID | 640 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
sc | +0.036 |
ch | +0.035 |
B | +0.035 |
subs | +0.034 |
ched | +0.031 |
Neg logit contributions | |
azes | -0.086 |
pit | -0.075 |
mmm | -0.074 |
isdom | -0.074 |
oven | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
azes | +0.043 |
isdom | +0.037 |
ires | +0.036 |
eria | +0.035 |
fridge | +0.035 |
Neg logit contributions | |
ch | -0.034 |
sc | -0.033 |
subs | -0.032 |
B | -0.031 |
bo | -0.030 |
Token | fourteen |
Token ID | 29167 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
azes | +0.025 |
isdom | +0.020 |
pit | +0.019 |
ement | +0.019 |
ires | +0.019 |
Neg logit contributions | |
ch | -0.028 |
sc | -0.027 |
B | -0.027 |
subs | -0.026 |
bo | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
azes | +0.118 |
isdom | +0.101 |
eria | +0.100 |
ires | +0.099 |
sing | +0.098 |
Neg logit contributions | |
ch | -0.086 |
subs | -0.084 |
sc | -0.082 |
B | -0.082 |
fl | -0.080 |
Token | fifteen |
Token ID | 17280 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
azes | +0.034 |
isdom | +0.027 |
ement | +0.026 |
pit | +0.026 |
ires | +0.026 |
Neg logit contributions | |
ch | -0.043 |
sc | -0.041 |
B | -0.041 |
subs | -0.041 |
bo | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
azes | +0.142 |
isdom | +0.123 |
eria | +0.121 |
sing | +0.121 |
workshop | +0.119 |
Neg logit contributions | |
ch | -0.096 |
sc | -0.091 |
l | -0.088 |
subs | -0.088 |
B | -0.087 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
azes | +0.046 |
isdom | +0.036 |
pit | +0.035 |
ement | +0.035 |
ires | +0.035 |
Neg logit contributions | |
ch | -0.059 |
sc | -0.057 |
B | -0.055 |
subs | -0.055 |
bo | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
azes | +0.183 |
isdom | +0.159 |
eria | +0.158 |
sing | +0.157 |
workshop | +0.154 |
Neg logit contributions | |
ch | -0.125 |
sc | -0.122 |
B | -0.119 |
fl | -0.119 |
subs | -0.118 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
azes | +0.058 |
isdom | +0.046 |
pit | +0.045 |
ires | +0.044 |
ement | +0.044 |
Neg logit contributions | |
ch | -0.066 |
sc | -0.064 |
B | -0.062 |
subs | -0.061 |
bo | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
azes | +0.126 |
eria | +0.113 |
sing | +0.111 |
balcony | +0.111 |
isdom | +0.111 |
Neg logit contributions | |
ch | -0.084 |
fl | -0.079 |
l | -0.078 |
subs | -0.077 |
bo | -0.077 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
azes | +0.045 |
isdom | +0.035 |
pit | +0.034 |
ement | +0.034 |
ires | +0.034 |
Neg logit contributions | |
ch | -0.054 |
sc | -0.052 |
B | -0.050 |
subs | -0.050 |
bo | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
azes | +0.158 |
isdom | +0.144 |
eria | +0.144 |
workshop | +0.143 |
sing | +0.141 |
Neg logit contributions | |
l | -0.085 |
ch | -0.085 |
s | -0.082 |
fl | -0.081 |
subs | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
azes | +0.101 |
isdom | +0.086 |
pit | +0.084 |
fridge | +0.084 |
mmm | +0.084 |
Neg logit contributions | |
ch | -0.087 |
B | -0.085 |
sc | -0.085 |
subs | -0.082 |
bo | -0.077 |
Token | seven |
Token ID | 3598 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
azes | +0.054 |
isdom | +0.044 |
pit | +0.043 |
ires | +0.043 |
ement | +0.043 |
Neg logit contributions | |
ch | -0.048 |
sc | -0.048 |
B | -0.047 |
subs | -0.045 |
bo | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
azes | +0.135 |
isdom | +0.118 |
fridge | +0.116 |
pit | +0.115 |
ocolate | +0.115 |
Neg logit contributions | |
ch | -0.109 |
sc | -0.105 |
B | -0.104 |
subs | -0.102 |
text | -0.097 |
Token | There |
Token ID | 1318 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
azes | +0.007 |
isdom | +0.006 |
pit | +0.006 |
castle | +0.006 |
ement | +0.006 |
Neg logit contributions | |
sc | -0.003 |
ch | -0.003 |
B | -0.003 |
ny | -0.003 |
bo | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
s | +0.008 |
subs | +0.007 |
sc | +0.007 |
l | +0.007 |
fl | +0.007 |
Neg logit contributions | |
azes | -0.035 |
isdom | -0.033 |
mmm | -0.032 |
sing | -0.031 |
ires | -0.031 |
Token | seven |
Token ID | 3598 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
azes | +0.098 |
isdom | +0.092 |
ement | +0.088 |
mmm | +0.086 |
ires | +0.082 |
Neg logit contributions | |
ch | -0.081 |
B | -0.079 |
sc | -0.079 |
subs | -0.074 |
fl | -0.073 |
Token | ants |
Token ID | 27842 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
azes | +0.151 |
isdom | +0.131 |
ires | +0.126 |
fridge | +0.126 |
mmm | +0.125 |
Neg logit contributions | |
ch | -0.132 |
sc | -0.129 |
B | -0.127 |
subs | -0.123 |
text | -0.117 |
Token | in |
Token ID | 287 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
azes | +0.078 |
isdom | +0.075 |
mmm | +0.073 |
ae | +0.070 |
ires | +0.070 |
Neg logit contributions | |
ch | -0.032 |
sc | -0.031 |
l | -0.030 |
B | -0.029 |
s | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
azes | +0.011 |
pit | +0.009 |
oven | +0.009 |
ires | +0.009 |
mmm | +0.009 |
Neg logit contributions | |
sc | -0.005 |
ch | -0.005 |
B | -0.005 |
subs | -0.005 |
ched | -0.005 |
Token | line |
Token ID | 1627 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
azes | +0.050 |
isdom | +0.041 |
mmm | +0.041 |
ires | +0.040 |
ement | +0.040 |
Neg logit contributions | |
ch | -0.047 |
sc | -0.046 |
B | -0.046 |
subs | -0.044 |
bo | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
azes | +0.048 |
isdom | +0.046 |
mmm | +0.045 |
Majesty | +0.044 |
sing | +0.043 |
Neg logit contributions | |
sc | -0.013 |
l | -0.010 |
ny | -0.010 |
ch | -0.010 |
ched | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
ch | +0.008 |
sc | +0.008 |
B | +0.008 |
subs | +0.007 |
bo | +0.007 |
Neg logit contributions | |
azes | -0.012 |
pit | -0.010 |
ement | -0.010 |
oven | -0.010 |
isdom | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +7.02e-04 |
Pos logit contributions | |
B | +0.003 |
ch | +0.003 |
sc | +0.003 |
subs | +0.003 |
bo | +0.003 |
Neg logit contributions | |
azes | -0.004 |
isdom | -0.003 |
pit | -0.003 |
mmm | -0.003 |
ement | -0.003 |
Token | They |
Token ID | 2990 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
B | +0.001 |
sc | +0.001 |
ch | +0.001 |
subs | +0.001 |
bo | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.001 |
isdom | -0.001 |
ement | -0.001 |
oven | -0.001 |
Token | can |
Token ID | 460 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
azes | +0.031 |
ement | +0.028 |
mmm | +0.027 |
ires | +0.027 |
ummy | +0.027 |
Neg logit contributions | |
sc | -0.013 |
ch | -0.012 |
B | -0.011 |
ny | -0.011 |
ched | -0.011 |
Token | help |
Token ID | 1037 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
azes | +0.055 |
ement | +0.052 |
pit | +0.049 |
ae | +0.048 |
isdom | +0.048 |
Neg logit contributions | |
ch | -0.018 |
bo | -0.018 |
hurt | -0.016 |
B | -0.015 |
ny | -0.014 |
Token | each |
Token ID | 1123 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
ch | +0.004 |
B | +0.004 |
sc | +0.004 |
bo | +0.003 |
l | +0.003 |
Neg logit contributions | |
azes | -0.009 |
pit | -0.009 |
ement | -0.009 |
castle | -0.008 |
ocolate | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
azes | +0.186 |
pit | +0.162 |
mmm | +0.160 |
ement | +0.159 |
isdom | +0.158 |
Neg logit contributions | |
ch | -0.085 |
sc | -0.085 |
B | -0.085 |
subs | -0.079 |
bo | -0.073 |
Token | fight |
Token ID | 1907 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
sc | +0.005 |
ch | +0.005 |
B | +0.004 |
ny | +0.004 |
bo | +0.004 |
Neg logit contributions | |
azes | -0.008 |
ement | -0.007 |
mmm | -0.007 |
isdom | -0.007 |
ires | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
azes | +0.008 |
pit | +0.007 |
ement | +0.007 |
ae | +0.007 |
isdom | +0.006 |
Neg logit contributions | |
ch | -0.003 |
sc | -0.003 |
B | -0.003 |
ny | -0.003 |
s | -0.003 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
azes | +0.013 |
pit | +0.011 |
fridge | +0.011 |
oven | +0.011 |
ires | +0.011 |
Neg logit contributions | |
B | -0.010 |
ch | -0.010 |
sc | -0.010 |
subs | -0.010 |
ched | -0.009 |
Token | guys |
Token ID | 3730 |
Feature activation | -3.06e-04 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.002 |
subs | +0.002 |
bo | +0.002 |
Neg logit contributions | |
azes | -0.003 |
pit | -0.003 |
mmm | -0.003 |
ement | -0.003 |
ires | -0.003 |
Token | think |
Token ID | 892 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
sc | +0.019 |
ny | +0.019 |
ched | +0.018 |
scrap | +0.018 |
bo | +0.018 |
Neg logit contributions | |
azes | -0.034 |
ires | -0.029 |
isdom | -0.029 |
pit | -0.029 |
ement | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
azes | +0.023 |
pit | +0.023 |
castle | +0.020 |
eria | +0.020 |
Majesty | +0.020 |
Neg logit contributions | |
ch | -0.021 |
l | -0.020 |
sc | -0.019 |
s | -0.019 |
ched | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
ch | +0.005 |
B | +0.005 |
sc | +0.005 |
subs | +0.004 |
bo | +0.004 |
Neg logit contributions | |
azes | -0.008 |
pit | -0.007 |
isdom | -0.007 |
ement | -0.007 |
castle | -0.007 |
Token | look |
Token ID | 804 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
azes | +0.020 |
ement | +0.017 |
pit | +0.017 |
ummy | +0.017 |
ires | +0.017 |
Neg logit contributions | |
ny | -0.011 |
scrap | -0.011 |
sc | -0.011 |
ch | -0.011 |
ched | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
azes | +0.012 |
mmm | +0.011 |
ocolate | +0.011 |
pit | +0.011 |
castle | +0.011 |
Neg logit contributions | |
sc | -0.009 |
ch | -0.009 |
B | -0.008 |
scrap | -0.008 |
ched | -0.008 |
Token | each |
Token ID | 1123 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
azes | +0.071 |
pit | +0.060 |
mmm | +0.059 |
castle | +0.057 |
isdom | +0.057 |
Neg logit contributions | |
ch | -0.048 |
B | -0.047 |
sc | -0.046 |
scrap | -0.044 |
bo | -0.044 |
Token | other |
Token ID | 584 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
azes | +0.189 |
pit | +0.163 |
mmm | +0.162 |
isdom | +0.161 |
ement | +0.161 |
Neg logit contributions | |
sc | -0.083 |
B | -0.082 |
ch | -0.082 |
subs | -0.076 |
bo | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
sc | +0.008 |
B | +0.007 |
ch | +0.007 |
s | +0.007 |
bo | +0.007 |
Neg logit contributions | |
azes | -0.018 |
mmm | -0.016 |
isdom | -0.016 |
pit | -0.015 |
castle | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
B | +0.007 |
sc | +0.007 |
ch | +0.007 |
Free | +0.006 |
subs | +0.006 |
Neg logit contributions | |
azes | -0.016 |
pit | -0.014 |
castle | -0.014 |
isdom | -0.014 |
ement | -0.014 |
Token | have |
Token ID | 423 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
azes | +0.026 |
ummy | +0.023 |
ement | +0.023 |
ocolate | +0.023 |
pit | +0.023 |
Neg logit contributions | |
scrap | -0.012 |
went | -0.011 |
l | -0.011 |
st | -0.011 |
bo | -0.011 |
Token | an |
Token ID | 281 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
ch | +0.007 |
B | +0.007 |
scrap | +0.007 |
sc | +0.006 |
subs | +0.006 |
Neg logit contributions | |
azes | -0.011 |
ement | -0.010 |
pit | -0.010 |
mmm | -0.010 |
ires | -0.009 |
Token | tomato |
Token ID | 24240 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
azes | +0.049 |
mmm | +0.038 |
isdom | +0.038 |
ocolate | +0.037 |
eria | +0.037 |
Neg logit contributions | |
ch | -0.044 |
l | -0.042 |
B | -0.042 |
fl | -0.041 |
sc | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
azes | +0.064 |
isdom | +0.059 |
mmm | +0.057 |
Majesty | +0.056 |
idge | +0.055 |
Neg logit contributions | |
sc | -0.019 |
s | -0.018 |
l | -0.017 |
fl | -0.017 |
ch | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | -9.90e-03 |
Pos logit contributions | |
sc | +0.011 |
B | +0.011 |
ch | +0.011 |
Free | +0.010 |
subs | +0.010 |
Neg logit contributions | |
azes | -0.026 |
pit | -0.024 |
ae | -0.023 |
castle | -0.023 |
throne | -0.023 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
azes | +0.025 |
ocolate | +0.023 |
ummy | +0.023 |
ires | +0.023 |
mmm | +0.023 |
Neg logit contributions | |
scrap | -0.008 |
B | -0.008 |
hurt | -0.007 |
ched | -0.007 |
went | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
azes | +0.025 |
ocolate | +0.021 |
mmm | +0.021 |
pit | +0.021 |
ae | +0.021 |
Neg logit contributions | |
sc | -0.018 |
ch | -0.018 |
B | -0.017 |
ched | -0.017 |
scrap | -0.017 |
Token | each |
Token ID | 1123 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
azes | +0.062 |
pit | +0.055 |
mmm | +0.053 |
eria | +0.052 |
isdom | +0.052 |
Neg logit contributions | |
ch | -0.030 |
B | -0.030 |
sc | -0.029 |
scrap | -0.027 |
subs | -0.027 |
Token | other |
Token ID | 584 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
azes | +0.174 |
pit | +0.151 |
oven | +0.149 |
ires | +0.149 |
isdom | +0.148 |
Neg logit contributions | |
ch | -0.092 |
sc | -0.092 |
B | -0.091 |
subs | -0.089 |
bo | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
sc | +0.011 |
ch | +0.011 |
B | +0.010 |
subs | +0.010 |
ched | +0.010 |
Neg logit contributions | |
azes | -0.025 |
isdom | -0.022 |
mmm | -0.022 |
pit | -0.022 |
ires | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
sc | +0.010 |
B | +0.010 |
ch | +0.010 |
Free | +0.009 |
Spot | +0.008 |
Neg logit contributions | |
azes | -0.024 |
pit | -0.022 |
castle | -0.022 |
ae | -0.022 |
throne | -0.022 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
azes | +0.022 |
ocolate | +0.020 |
mmm | +0.020 |
ummy | +0.020 |
ires | +0.020 |
Neg logit contributions | |
scrap | -0.007 |
B | -0.007 |
subs | -0.006 |
ched | -0.006 |
ch | -0.006 |
Token | bad |
Token ID | 2089 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
ch | +0.007 |
B | +0.007 |
sc | +0.007 |
subs | +0.007 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.007 |
pit | -0.005 |
isdom | -0.005 |
mmm | -0.005 |
ement | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
azes | +0.021 |
writing | +0.018 |
patiently | +0.018 |
counting | +0.018 |
reading | +0.018 |
Neg logit contributions | |
sc | -0.019 |
text | -0.019 |
ch | -0.019 |
subs | -0.018 |
B | -0.018 |
Token | climb |
Token ID | 12080 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
azes | +0.006 |
pit | +0.005 |
fridge | +0.005 |
oven | +0.005 |
writing | +0.005 |
Neg logit contributions | |
sc | -0.004 |
ch | -0.004 |
B | -0.004 |
subs | -0.003 |
text | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
azes | +0.019 |
pit | +0.017 |
oven | +0.017 |
ement | +0.016 |
patiently | +0.016 |
Neg logit contributions | |
B | -0.014 |
subs | -0.014 |
sc | -0.013 |
ch | -0.013 |
text | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
sc | +0.004 |
ch | +0.004 |
B | +0.004 |
subs | +0.004 |
text | +0.003 |
Neg logit contributions | |
azes | -0.006 |
isdom | -0.005 |
pit | -0.005 |
castle | -0.005 |
ement | -0.005 |
Token | help |
Token ID | 1037 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
azes | +0.034 |
ement | +0.029 |
ires | +0.029 |
pit | +0.028 |
mmm | +0.028 |
Neg logit contributions | |
ch | -0.019 |
sc | -0.019 |
B | -0.018 |
subs | -0.018 |
bo | -0.017 |
Token | each |
Token ID | 1123 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
sc | +0.015 |
ch | +0.015 |
B | +0.015 |
subs | +0.015 |
ched | +0.014 |
Neg logit contributions | |
azes | -0.013 |
oven | -0.010 |
pit | -0.010 |
ires | -0.010 |
fridge | -0.010 |
Token | other |
Token ID | 584 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
azes | +0.150 |
oven | +0.136 |
pit | +0.133 |
fridge | +0.132 |
ires | +0.129 |
Neg logit contributions | |
sc | -0.106 |
subs | -0.103 |
ch | -0.103 |
B | -0.102 |
ched | -0.098 |
Token | when |
Token ID | 618 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ch | +0.019 |
sc | +0.019 |
B | +0.019 |
subs | +0.018 |
ched | +0.017 |
Neg logit contributions | |
azes | -0.028 |
pit | -0.024 |
mmm | -0.023 |
isdom | -0.023 |
ires | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
ch | +0.027 |
B | +0.026 |
subs | +0.025 |
sc | +0.025 |
scrap | +0.023 |
Neg logit contributions | |
azes | -0.057 |
isdom | -0.051 |
pit | -0.051 |
mmm | -0.050 |
ement | -0.050 |
Token | ground |
Token ID | 2323 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
azes | +0.005 |
isdom | +0.004 |
mmm | +0.004 |
pit | +0.004 |
ires | +0.004 |
Neg logit contributions | |
ch | -0.005 |
B | -0.005 |
sc | -0.005 |
subs | -0.005 |
scrap | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.007 |
B | +0.007 |
subs | +0.007 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.012 |
isdom | -0.011 |
mmm | -0.011 |
ires | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
s | +0.002 |
sc | +0.002 |
l | +0.002 |
fl | +0.002 |
B | +0.002 |
Neg logit contributions | |
azes | -0.008 |
isdom | -0.007 |
Majesty | -0.007 |
mmm | -0.007 |
ocolate | -0.007 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
sc | +0.008 |
ch | +0.008 |
B | +0.008 |
subs | +0.007 |
text | +0.007 |
Neg logit contributions | |
azes | -0.011 |
isdom | -0.010 |
pit | -0.010 |
castle | -0.010 |
mmm | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
azes | +0.066 |
ocolate | +0.058 |
ires | +0.058 |
sing | +0.058 |
mmm | +0.057 |
Neg logit contributions | |
went | -0.015 |
bo | -0.014 |
B | -0.014 |
s | -0.014 |
ny | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | -1.10e-04 |
Pos logit contributions | |
azes | +0.016 |
pit | +0.014 |
ires | +0.014 |
sing | +0.014 |
isdom | +0.014 |
Neg logit contributions | |
ch | -0.008 |
B | -0.008 |
sc | -0.008 |
l | -0.007 |
subs | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
azes | +0.000 |
pit | +0.000 |
ires | +0.000 |
mmm | +0.000 |
ement | +0.000 |
Neg logit contributions | |
went | -0.000 |
had | -0.000 |
got | -0.000 |
B | -0.000 |
ched | -0.000 |
Token | each |
Token ID | 1123 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
take | +0.003 |
went | +0.003 |
bo | +0.002 |
let | +0.002 |
s | +0.002 |
Neg logit contributions | |
azes | -0.009 |
ement | -0.008 |
pit | -0.008 |
otion | -0.007 |
isdom | -0.007 |
Token | choose |
Token ID | 3853 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
azes | +0.185 |
sing | +0.152 |
ement | +0.152 |
pit | +0.149 |
mmm | +0.149 |
Neg logit contributions | |
sc | -0.089 |
B | -0.088 |
ch | -0.083 |
ny | -0.082 |
bo | -0.080 |
Token | one |
Token ID | 530 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
azes | +0.006 |
sing | +0.005 |
pit | +0.005 |
studio | +0.005 |
isdom | +0.005 |
Neg logit contributions | |
l | -0.003 |
fl | -0.003 |
sc | -0.003 |
B | -0.003 |
s | -0.003 |
Token | fruit |
Token ID | 8234 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
azes | +0.100 |
Majesty | +0.084 |
balcony | +0.083 |
sing | +0.083 |
isdom | +0.082 |
Neg logit contributions | |
sc | -0.034 |
s | -0.030 |
ch | -0.030 |
fl | -0.028 |
ny | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
azes | +0.072 |
isdom | +0.061 |
sing | +0.059 |
Majesty | +0.059 |
workshop | +0.059 |
Neg logit contributions | |
sc | -0.030 |
s | -0.026 |
fl | -0.025 |
ch | -0.025 |
ny | -0.024 |
Token | take |
Token ID | 1011 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
went | +0.002 |
take | +0.002 |
st | +0.001 |
away | +0.001 |
hurt | +0.001 |
Neg logit contributions | |
azes | -0.005 |
eria | -0.004 |
apping | -0.004 |
ement | -0.004 |
pit | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
azes | +0.020 |
pit | +0.017 |
mmm | +0.017 |
isdom | +0.017 |
ires | +0.017 |
Neg logit contributions | |
ch | -0.009 |
B | -0.009 |
sc | -0.009 |
subs | -0.009 |
ched | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
azes | +0.043 |
pit | +0.036 |
ement | +0.036 |
mmm | +0.035 |
isdom | +0.035 |
Neg logit contributions | |
ch | -0.025 |
B | -0.024 |
sc | -0.023 |
subs | -0.023 |
ched | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
B | +0.004 |
sc | +0.004 |
ch | +0.004 |
subs | +0.004 |
Br | +0.004 |
Neg logit contributions | |
azes | -0.007 |
pit | -0.006 |
castle | -0.006 |
isdom | -0.006 |
ement | -0.006 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
azes | +0.037 |
ement | +0.032 |
ires | +0.031 |
pit | +0.031 |
mmm | +0.031 |
Neg logit contributions | |
B | -0.016 |
sc | -0.016 |
ch | -0.015 |
subs | -0.015 |
ched | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
azes | +0.053 |
mmm | +0.046 |
ocolate | +0.045 |
ae | +0.045 |
pit | +0.044 |
Neg logit contributions | |
sc | -0.032 |
ch | -0.032 |
B | -0.029 |
ched | -0.029 |
scrap | -0.029 |
Token | each |
Token ID | 1123 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
azes | +0.078 |
pit | +0.068 |
mmm | +0.068 |
eria | +0.066 |
castle | +0.065 |
Neg logit contributions | |
B | -0.035 |
ch | -0.035 |
sc | -0.032 |
scrap | -0.032 |
bo | -0.031 |
Token | other |
Token ID | 584 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
azes | +0.185 |
pit | +0.159 |
mmm | +0.157 |
isdom | +0.157 |
ement | +0.156 |
Neg logit contributions | |
sc | -0.083 |
ch | -0.083 |
B | -0.082 |
subs | -0.076 |
ched | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
sc | +0.006 |
s | +0.006 |
ch | +0.005 |
B | +0.005 |
ny | +0.005 |
Neg logit contributions | |
azes | -0.012 |
mmm | -0.011 |
isdom | -0.011 |
pit | -0.010 |
castle | -0.010 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
B | +0.007 |
sc | +0.007 |
scrap | +0.007 |
ch | +0.007 |
subs | +0.007 |
Neg logit contributions | |
azes | -0.014 |
mmm | -0.012 |
ires | -0.012 |
ocolate | -0.012 |
isdom | -0.012 |
Token | sorry |
Token ID | 7926 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
azes | +0.007 |
pit | +0.006 |
mmm | +0.006 |
isdom | +0.006 |
ement | +0.005 |
Neg logit contributions | |
ch | -0.007 |
sc | -0.006 |
B | -0.006 |
subs | -0.006 |
ched | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
ch | +0.005 |
sc | +0.005 |
B | +0.005 |
subs | +0.004 |
fl | +0.004 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.009 |
isdom | -0.009 |
castle | -0.009 |
balcony | -0.009 |
Token | hoop |
Token ID | 44792 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
sc | +0.002 |
ch | +0.002 |
B | +0.002 |
subs | +0.002 |
scrap | +0.001 |
Neg logit contributions | |
azes | -0.002 |
mmm | -0.002 |
isdom | -0.002 |
pit | -0.002 |
ement | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-03 |
Pos logit contributions | |
azes | +0.008 |
mmm | +0.008 |
isdom | +0.008 |
ocolate | +0.007 |
mmmm | +0.007 |
Neg logit contributions | |
sc | -0.003 |
s | -0.003 |
ch | -0.002 |
l | -0.002 |
ched | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
sc | +0.004 |
ch | +0.004 |
B | +0.004 |
subs | +0.004 |
text | +0.003 |
Neg logit contributions | |
azes | -0.009 |
pit | -0.008 |
castle | -0.008 |
isdom | -0.008 |
balcony | -0.008 |
Token | look |
Token ID | 804 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
azes | +0.024 |
ummy | +0.021 |
mmm | +0.021 |
ocolate | +0.021 |
ement | +0.021 |
Neg logit contributions | |
scrap | -0.013 |
sc | -0.013 |
ched | -0.013 |
ny | -0.013 |
ch | -0.012 |
Token | at |
Token ID | 379 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
azes | +0.028 |
pit | +0.023 |
ocolate | +0.023 |
mmm | +0.023 |
isdom | +0.022 |
Neg logit contributions | |
sc | -0.021 |
ch | -0.021 |
B | -0.020 |
ched | -0.019 |
subs | -0.019 |
Token | each |
Token ID | 1123 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
azes | +0.079 |
pit | +0.069 |
mmm | +0.067 |
castle | +0.065 |
balcony | +0.065 |
Neg logit contributions | |
ch | -0.046 |
B | -0.046 |
sc | -0.045 |
scrap | -0.042 |
ched | -0.041 |
Token | other |
Token ID | 584 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
azes | +0.159 |
pit | +0.139 |
ires | +0.137 |
oven | +0.136 |
ement | +0.135 |
Neg logit contributions | |
ch | -0.101 |
subs | -0.100 |
B | -0.099 |
sc | -0.097 |
bo | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
sc | +0.013 |
ch | +0.012 |
B | +0.012 |
s | +0.011 |
ny | +0.011 |
Neg logit contributions | |
azes | -0.024 |
mmm | -0.021 |
isdom | -0.021 |
ocolate | -0.021 |
pit | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
sc | +0.005 |
B | +0.005 |
ch | +0.005 |
Free | +0.004 |
W | +0.004 |
Neg logit contributions | |
azes | -0.011 |
pit | -0.009 |
castle | -0.009 |
isdom | -0.009 |
balcony | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
azes | +0.007 |
pit | +0.006 |
castle | +0.006 |
oven | +0.006 |
ement | +0.006 |
Neg logit contributions | |
B | -0.003 |
ch | -0.002 |
sc | -0.002 |
ched | -0.002 |
bo | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
azes | +0.014 |
mmm | +0.012 |
pit | +0.012 |
ires | +0.012 |
isdom | +0.012 |
Neg logit contributions | |
subs | -0.008 |
sc | -0.008 |
ch | -0.008 |
B | -0.008 |
fl | -0.008 |
Token | stick |
Token ID | 4859 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
ch | +0.006 |
sc | +0.005 |
B | +0.005 |
fl | +0.005 |
subs | +0.005 |
Neg logit contributions | |
azes | -0.007 |
mmm | -0.006 |
ires | -0.006 |
isdom | -0.006 |
ement | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
azes | +0.016 |
mmm | +0.014 |
isdom | +0.014 |
Majesty | +0.013 |
ires | +0.013 |
Neg logit contributions | |
sc | -0.006 |
ch | -0.006 |
B | -0.005 |
ny | -0.005 |
ched | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.007 |
B | +0.006 |
subs | +0.006 |
Free | +0.006 |
Neg logit contributions | |
azes | -0.014 |
pit | -0.013 |
castle | -0.012 |
isdom | -0.012 |
ement | -0.012 |
Token | look |
Token ID | 804 |
Feature activation | -2.58e-03 |
Pos logit contributions | |
azes | +0.019 |
ement | +0.016 |
ummy | +0.016 |
pit | +0.016 |
ires | +0.016 |
Neg logit contributions | |
scrap | -0.010 |
ch | -0.010 |
sc | -0.010 |
bo | -0.009 |
ched | -0.009 |
Token | at |
Token ID | 379 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
azes | +0.005 |
ocolate | +0.004 |
pit | +0.004 |
mmm | +0.004 |
isdom | +0.004 |
Neg logit contributions | |
ch | -0.004 |
sc | -0.004 |
B | -0.004 |
ched | -0.003 |
scrap | -0.003 |
Token | each |
Token ID | 1123 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
azes | +0.078 |
pit | +0.068 |
mmm | +0.068 |
isdom | +0.066 |
castle | +0.066 |
Neg logit contributions | |
ch | -0.035 |
B | -0.034 |
sc | -0.034 |
subs | -0.031 |
scrap | -0.030 |
Token | other |
Token ID | 584 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
azes | +0.152 |
pit | +0.135 |
oven | +0.134 |
fridge | +0.132 |
ires | +0.131 |
Neg logit contributions | |
subs | -0.103 |
ch | -0.102 |
sc | -0.102 |
B | -0.101 |
text | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
sc | +0.007 |
ch | +0.007 |
B | +0.007 |
subs | +0.006 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.014 |
mmm | -0.013 |
isdom | -0.013 |
pit | -0.012 |
ires | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
B | +0.007 |
ch | +0.007 |
sc | +0.007 |
subs | +0.006 |
Br | +0.006 |
Neg logit contributions | |
azes | -0.014 |
pit | -0.013 |
castle | -0.013 |
ement | -0.013 |
isdom | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
azes | +0.016 |
pit | +0.014 |
castle | +0.014 |
ement | +0.014 |
oven | +0.014 |
Neg logit contributions | |
B | -0.006 |
ch | -0.006 |
sc | -0.006 |
ched | -0.005 |
bo | -0.005 |
Token | They |
Token ID | 2990 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
azes | +0.016 |
mmm | +0.014 |
ires | +0.014 |
isdom | +0.013 |
eria | +0.013 |
Neg logit contributions | |
subs | -0.012 |
sc | -0.012 |
ch | -0.012 |
fl | -0.011 |
scrap | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
sc | +0.014 |
ch | +0.014 |
subs | +0.014 |
B | +0.013 |
fl | +0.013 |
Neg logit contributions | |
azes | -0.021 |
ires | -0.018 |
mmm | -0.018 |
isdom | -0.018 |
pit | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
subs | +0.010 |
fl | +0.010 |
sc | +0.010 |
ch | +0.010 |
scrap | +0.010 |
Neg logit contributions | |
azes | -0.011 |
pit | -0.010 |
ires | -0.010 |
patiently | -0.010 |
mmm | -0.010 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
sc | +0.030 |
ch | +0.030 |
subs | +0.030 |
text | +0.028 |
ched | +0.028 |
Neg logit contributions | |
azes | -0.049 |
pit | -0.043 |
mmm | -0.042 |
ires | -0.042 |
ocolate | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
azes | +0.004 |
ires | +0.003 |
pit | +0.003 |
ement | +0.003 |
isdom | +0.003 |
Neg logit contributions | |
ch | -0.003 |
B | -0.003 |
subs | -0.003 |
sc | -0.003 |
bo | -0.003 |
Token | what |
Token ID | 644 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
azes | +0.042 |
ement | +0.036 |
isdom | +0.035 |
pit | +0.035 |
ires | +0.035 |
Neg logit contributions | |
ch | -0.033 |
B | -0.031 |
sc | -0.031 |
subs | -0.030 |
Fl | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
ch | +0.017 |
sc | +0.017 |
B | +0.017 |
subs | +0.016 |
bo | +0.016 |
Neg logit contributions | |
azes | -0.025 |
pit | -0.021 |
isdom | -0.020 |
mmm | -0.020 |
ires | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
azes | +0.147 |
pit | +0.125 |
ement | +0.122 |
isdom | +0.121 |
mmm | +0.120 |
Neg logit contributions | |
ch | -0.114 |
sc | -0.113 |
B | -0.113 |
subs | -0.108 |
ched | -0.103 |
Token | doing |
Token ID | 1804 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
azes | +0.077 |
ement | +0.074 |
ues | +0.071 |
throne | +0.070 |
pit | +0.069 |
Neg logit contributions | |
ch | -0.058 |
st | -0.055 |
B | -0.055 |
hurt | -0.053 |
subs | -0.053 |
Token | with |
Token ID | 351 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
azes | +0.059 |
pit | +0.051 |
balcony | +0.049 |
eria | +0.049 |
ement | +0.049 |
Neg logit contributions | |
ch | -0.045 |
B | -0.043 |
sc | -0.042 |
bo | -0.040 |
ched | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
azes | +0.092 |
pit | +0.084 |
ement | +0.081 |
castle | +0.080 |
sing | +0.079 |
Neg logit contributions | |
ch | -0.036 |
B | -0.032 |
scrap | -0.031 |
Fl | -0.029 |
st | -0.028 |
Token | worm |
Token ID | 23849 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
azes | +0.078 |
ement | +0.062 |
ires | +0.061 |
isdom | +0.060 |
pit | +0.060 |
Neg logit contributions | |
ch | -0.073 |
sc | -0.070 |
B | -0.069 |
subs | -0.067 |
bo | -0.067 |
Token | say |
Token ID | 910 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.007 |
B | +0.007 |
subs | +0.007 |
ched | +0.007 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.008 |
isdom | -0.008 |
mmm | -0.008 |
ires | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
azes | +0.030 |
pit | +0.025 |
mmm | +0.024 |
isdom | +0.024 |
ires | +0.024 |
Neg logit contributions | |
ch | -0.034 |
B | -0.034 |
sc | -0.034 |
subs | -0.033 |
ched | -0.031 |
Token | sorry |
Token ID | 41599 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
sc | +0.006 |
ch | +0.006 |
text | +0.006 |
subs | +0.006 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.009 |
mmm | -0.009 |
ement | -0.009 |
ae | -0.008 |
ires | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
azes | +0.038 |
mmm | +0.034 |
ocolate | +0.033 |
ummy | +0.033 |
ement | +0.032 |
Neg logit contributions | |
sc | -0.050 |
scrap | -0.049 |
subs | -0.049 |
B | -0.049 |
ch | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
ch | +0.032 |
B | +0.031 |
sc | +0.031 |
subs | +0.030 |
ched | +0.029 |
Neg logit contributions | |
azes | -0.036 |
pit | -0.030 |
mmm | -0.029 |
isdom | -0.029 |
ires | -0.029 |
Token | each |
Token ID | 1123 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
azes | +0.013 |
pit | +0.011 |
isdom | +0.011 |
mmm | +0.011 |
ires | +0.011 |
Neg logit contributions | |
ch | -0.012 |
sc | -0.012 |
B | -0.012 |
subs | -0.012 |
ched | -0.011 |
Token | other |
Token ID | 584 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
azes | +0.119 |
oven | +0.110 |
ocolate | +0.110 |
baker | +0.105 |
ae | +0.105 |
Neg logit contributions | |
subs | -0.124 |
sc | -0.116 |
fl | -0.112 |
ch | -0.112 |
bo | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
sc | +0.021 |
ch | +0.021 |
B | +0.021 |
subs | +0.021 |
ched | +0.019 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.023 |
oven | -0.023 |
fridge | -0.023 |
writing | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
azes | +0.006 |
castle | +0.005 |
pit | +0.005 |
isdom | +0.005 |
ement | +0.005 |
Neg logit contributions | |
sc | -0.002 |
B | -0.002 |
ch | -0.002 |
Fl | -0.002 |
subs | -0.002 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
azes | +0.019 |
oven | +0.016 |
pit | +0.015 |
fridge | +0.015 |
isdom | +0.015 |
Neg logit contributions | |
B | -0.017 |
ch | -0.016 |
sc | -0.016 |
subs | -0.016 |
fl | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
azes | +0.021 |
pit | +0.017 |
oven | +0.017 |
isdom | +0.017 |
mmm | +0.017 |
Neg logit contributions | |
sc | -0.023 |
ch | -0.023 |
B | -0.023 |
subs | -0.022 |
ched | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
azes | +0.026 |
pit | +0.021 |
isdom | +0.021 |
ires | +0.021 |
mmm | +0.021 |
Neg logit contributions | |
ch | -0.027 |
sc | -0.027 |
B | -0.027 |
subs | -0.026 |
bo | -0.025 |
Token | sweet |
Token ID | 6029 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
azes | +0.069 |
isdom | +0.058 |
pit | +0.058 |
ement | +0.058 |
balcony | +0.057 |
Neg logit contributions | |
B | -0.044 |
ch | -0.044 |
sc | -0.042 |
subs | -0.040 |
Fl | -0.039 |
Token | ie |
Token ID | 494 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
azes | +0.051 |
pit | +0.042 |
fridge | +0.041 |
isdom | +0.041 |
mmm | +0.041 |
Neg logit contributions | |
sc | -0.049 |
ch | -0.048 |
B | -0.048 |
subs | -0.046 |
ched | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
azes | +0.006 |
pit | +0.005 |
oven | +0.005 |
fridge | +0.005 |
isdom | +0.005 |
Neg logit contributions | |
B | -0.005 |
sc | -0.005 |
ch | -0.005 |
subs | -0.005 |
ched | -0.005 |
Token | What |
Token ID | 1867 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
azes | +0.017 |
pit | +0.015 |
castle | +0.015 |
ement | +0.014 |
isdom | +0.014 |
Neg logit contributions | |
ch | -0.013 |
B | -0.013 |
sc | -0.013 |
subs | -0.012 |
Fl | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
azes | +0.004 |
pit | +0.004 |
ement | +0.004 |
ires | +0.004 |
castle | +0.004 |
Neg logit contributions | |
ch | -0.003 |
B | -0.002 |
sc | -0.002 |
subs | -0.002 |
ched | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
azes | +0.145 |
pit | +0.124 |
ement | +0.120 |
isdom | +0.120 |
mmm | +0.119 |
Neg logit contributions | |
ch | -0.114 |
B | -0.113 |
sc | -0.113 |
subs | -0.108 |
bo | -0.102 |
Token | expecting |
Token ID | 12451 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
azes | +0.070 |
ement | +0.067 |
isdom | +0.063 |
ues | +0.063 |
pit | +0.063 |
Neg logit contributions | |
ch | -0.051 |
st | -0.049 |
B | -0.047 |
fl | -0.046 |
hurt | -0.046 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
azes | +0.096 |
pit | +0.093 |
castle | +0.085 |
ement | +0.085 |
Majesty | +0.084 |
Neg logit contributions | |
ch | -0.070 |
sc | -0.061 |
B | -0.058 |
on | -0.058 |
st | -0.058 |
Token | Dad |
Token ID | 17415 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
azes | +0.031 |
pit | +0.030 |
castle | +0.029 |
ement | +0.028 |
eria | +0.027 |
Neg logit contributions | |
B | -0.026 |
scrap | -0.025 |
ch | -0.025 |
bo | -0.024 |
subs | -0.024 |
Token | says |
Token ID | 1139 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
azes | +0.039 |
mmm | +0.034 |
pit | +0.033 |
isdom | +0.033 |
castle | +0.033 |
Neg logit contributions | |
ch | -0.031 |
sc | -0.031 |
B | -0.030 |
bo | -0.030 |
subs | -0.029 |
Token | looks |
Token ID | 3073 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
sc | +0.009 |
s | +0.009 |
bo | +0.009 |
ch | +0.009 |
ny | +0.008 |
Neg logit contributions | |
azes | -0.019 |
ocolate | -0.018 |
mmm | -0.018 |
isdom | -0.018 |
ruits | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
azes | +0.038 |
mmm | +0.032 |
pit | +0.032 |
ocolate | +0.032 |
isdom | +0.032 |
Neg logit contributions | |
sc | -0.030 |
ch | -0.030 |
B | -0.029 |
subs | -0.028 |
ched | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.007 |
B | +0.007 |
Free | +0.006 |
W | +0.006 |
Neg logit contributions | |
castle | -0.012 |
azes | -0.011 |
pit | -0.011 |
isdom | -0.011 |
ement | -0.010 |
Token | sees |
Token ID | 7224 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ocolate | +0.015 |
azes | +0.015 |
mmm | +0.014 |
eria | +0.014 |
ummy | +0.014 |
Neg logit contributions | |
scrap | -0.007 |
ch | -0.006 |
bo | -0.006 |
l | -0.006 |
sc | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
azes | +0.089 |
mmm | +0.086 |
isdom | +0.084 |
castle | +0.083 |
pit | +0.081 |
Neg logit contributions | |
l | -0.024 |
ch | -0.022 |
B | -0.021 |
scrap | -0.020 |
s | -0.018 |
Token | ele |
Token ID | 9766 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
azes | +0.040 |
isdom | +0.034 |
pit | +0.033 |
mmm | +0.033 |
ires | +0.033 |
Neg logit contributions | |
ch | -0.025 |
sc | -0.025 |
B | -0.025 |
subs | -0.024 |
bo | -0.023 |
Token | venth |
Token ID | 20987 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
azes | +0.142 |
isdom | +0.138 |
pit | +0.134 |
fridge | +0.132 |
ires | +0.130 |
Neg logit contributions | |
B | -0.101 |
ch | -0.101 |
sc | -0.098 |
text | -0.095 |
bo | -0.089 |
Token | pengu |
Token ID | 38373 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
ch | +0.023 |
B | +0.023 |
sc | +0.023 |
subs | +0.022 |
ched | +0.021 |
Neg logit contributions | |
azes | -0.032 |
pit | -0.027 |
oven | -0.026 |
ires | -0.026 |
isdom | -0.026 |
Token | in |
Token ID | 259 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
azes | +0.069 |
fridge | +0.062 |
mmm | +0.061 |
isdom | +0.059 |
sing | +0.059 |
Neg logit contributions | |
ch | -0.054 |
B | -0.054 |
sc | -0.053 |
bo | -0.051 |
l | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-03 |
Pos logit contributions | |
azes | +0.014 |
mmm | +0.013 |
isdom | +0.012 |
ement | +0.012 |
balcony | +0.012 |
Neg logit contributions | |
ch | -0.006 |
sc | -0.005 |
B | -0.005 |
bo | -0.005 |
ched | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
ch | +0.002 |
sc | +0.002 |
B | +0.002 |
Fl | +0.002 |
W | +0.002 |
Neg logit contributions | |
castle | -0.005 |
azes | -0.004 |
pit | -0.004 |
isdom | -0.004 |
workshop | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
ch | +0.000 |
B | +0.000 |
sc | +0.000 |
subs | +0.000 |
bo | +0.000 |
Neg logit contributions | |
azes | -0.000 |
pit | -0.000 |
isdom | -0.000 |
ement | -0.000 |
mmm | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -9.89e-03 |
Pos logit contributions | |
azes | +0.012 |
ires | +0.010 |
mmm | +0.010 |
isdom | +0.010 |
fridge | +0.010 |
Neg logit contributions | |
sc | -0.008 |
subs | -0.008 |
ch | -0.008 |
B | -0.008 |
fl | -0.007 |
Token | They |
Token ID | 2990 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
azes | +0.014 |
mmm | +0.012 |
ires | +0.012 |
eria | +0.012 |
gods | +0.011 |
Neg logit contributions | |
subs | -0.019 |
burn | -0.017 |
fl | -0.017 |
sc | -0.016 |
ch | -0.016 |
Token | look |
Token ID | 804 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
azes | +0.029 |
pit | +0.024 |
ires | +0.024 |
ement | +0.024 |
mmm | +0.024 |
Neg logit contributions | |
ch | -0.020 |
sc | -0.020 |
B | -0.020 |
subs | -0.019 |
ched | -0.018 |
Token | at |
Token ID | 379 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.004 |
ires | +0.004 |
ement | +0.004 |
oven | +0.004 |
Neg logit contributions | |
B | -0.006 |
ch | -0.006 |
sc | -0.006 |
subs | -0.006 |
bo | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
azes | +0.076 |
pit | +0.067 |
mmm | +0.066 |
isdom | +0.065 |
ement | +0.065 |
Neg logit contributions | |
ch | -0.034 |
B | -0.034 |
sc | -0.033 |
subs | -0.031 |
bo | -0.030 |
Token | other |
Token ID | 584 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
azes | +0.110 |
oven | +0.102 |
pit | +0.098 |
fridge | +0.098 |
ires | +0.096 |
Neg logit contributions | |
subs | -0.132 |
sc | -0.124 |
ch | -0.121 |
bo | -0.117 |
beh | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
ch | +0.021 |
sc | +0.021 |
B | +0.021 |
subs | +0.020 |
ched | +0.019 |
Neg logit contributions | |
azes | -0.034 |
pit | -0.029 |
isdom | -0.028 |
ires | -0.028 |
ement | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
B | +0.005 |
ch | +0.005 |
sc | +0.005 |
subs | +0.005 |
Fl | +0.004 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.009 |
castle | -0.009 |
ement | -0.009 |
isdom | -0.009 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
azes | +0.023 |
pit | +0.020 |
mmm | +0.020 |
ement | +0.020 |
ocolate | +0.020 |
Neg logit contributions | |
ch | -0.014 |
scrap | -0.014 |
sc | -0.014 |
subs | -0.014 |
B | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
azes | +0.022 |
pit | +0.018 |
isdom | +0.018 |
ires | +0.018 |
oven | +0.018 |
Neg logit contributions | |
sc | -0.019 |
ch | -0.019 |
B | -0.018 |
subs | -0.018 |
ched | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
azes | +0.052 |
isdom | +0.048 |
ocolate | +0.048 |
mmm | +0.047 |
oven | +0.047 |
Neg logit contributions | |
fl | -0.020 |
B | -0.019 |
subs | -0.018 |
s | -0.018 |
ch | -0.018 |
Token | grateful |
Token ID | 14066 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
ch | +0.026 |
B | +0.026 |
sc | +0.026 |
subs | +0.024 |
text | +0.023 |
Neg logit contributions | |
azes | -0.017 |
writing | -0.014 |
balcony | -0.013 |
sing | -0.013 |
patiently | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.003 |
subs | +0.003 |
fl | +0.003 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
isdom | -0.005 |
mmm | -0.005 |
ement | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
azes | +0.015 |
ires | +0.013 |
mmm | +0.012 |
fridge | +0.012 |
isdom | +0.012 |
Neg logit contributions | |
sc | -0.013 |
ch | -0.012 |
subs | -0.012 |
B | -0.012 |
ched | -0.012 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
azes | +0.040 |
pit | +0.034 |
ires | +0.034 |
ement | +0.034 |
isdom | +0.034 |
Neg logit contributions | |
B | -0.016 |
sc | -0.016 |
ch | -0.016 |
subs | -0.015 |
ched | -0.014 |
Token | each |
Token ID | 1123 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
azes | +0.074 |
pit | +0.068 |
ement | +0.068 |
mmm | +0.066 |
eria | +0.065 |
Neg logit contributions | |
fl | -0.025 |
ch | -0.024 |
B | -0.023 |
subs | -0.022 |
st | -0.020 |
Token | other |
Token ID | 584 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
azes | +0.171 |
pit | +0.149 |
oven | +0.146 |
ires | +0.146 |
isdom | +0.146 |
Neg logit contributions | |
ch | -0.086 |
sc | -0.086 |
B | -0.085 |
subs | -0.081 |
ched | -0.075 |
Token | very |
Token ID | 845 |
Feature activation | -6.92e-04 |
Pos logit contributions | |
sc | +0.018 |
B | +0.017 |
ch | +0.017 |
bo | +0.016 |
subs | +0.016 |
Neg logit contributions | |
azes | -0.034 |
isdom | -0.029 |
ires | -0.029 |
mmm | -0.029 |
pit | -0.029 |
Token | much |
Token ID | 881 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
azes | +0.001 |
pit | +0.001 |
fridge | +0.001 |
oven | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
B | -0.001 |
ch | -0.001 |
sc | -0.001 |
bo | -0.001 |
text | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
sc | +0.014 |
B | +0.013 |
ch | +0.013 |
l | +0.012 |
ny | +0.012 |
Neg logit contributions | |
azes | -0.043 |
isdom | -0.038 |
pit | -0.038 |
ocolate | -0.037 |
mmm | -0.037 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
azes | +0.008 |
ires | +0.007 |
mmm | +0.007 |
pit | +0.007 |
isdom | +0.007 |
Neg logit contributions | |
sc | -0.005 |
ch | -0.005 |
subs | -0.005 |
B | -0.005 |
ched | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
azes | +0.142 |
isdom | +0.123 |
eria | +0.121 |
sing | +0.121 |
workshop | +0.119 |
Neg logit contributions | |
ch | -0.096 |
sc | -0.091 |
l | -0.088 |
subs | -0.088 |
B | -0.087 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
azes | +0.046 |
isdom | +0.036 |
pit | +0.035 |
ement | +0.035 |
ires | +0.035 |
Neg logit contributions | |
ch | -0.059 |
sc | -0.057 |
B | -0.055 |
subs | -0.055 |
bo | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
azes | +0.183 |
isdom | +0.159 |
eria | +0.158 |
sing | +0.157 |
workshop | +0.154 |
Neg logit contributions | |
ch | -0.125 |
sc | -0.122 |
B | -0.119 |
fl | -0.119 |
subs | -0.118 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
azes | +0.058 |
isdom | +0.046 |
pit | +0.045 |
ires | +0.044 |
ement | +0.044 |
Neg logit contributions | |
ch | -0.066 |
sc | -0.064 |
B | -0.062 |
subs | -0.061 |
bo | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
azes | +0.126 |
eria | +0.113 |
sing | +0.111 |
balcony | +0.111 |
isdom | +0.111 |
Neg logit contributions | |
ch | -0.084 |
fl | -0.079 |
l | -0.078 |
subs | -0.077 |
bo | -0.077 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
azes | +0.045 |
isdom | +0.035 |
pit | +0.034 |
ement | +0.034 |
ires | +0.034 |
Neg logit contributions | |
ch | -0.054 |
sc | -0.052 |
B | -0.050 |
subs | -0.050 |
bo | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
azes | +0.158 |
isdom | +0.144 |
eria | +0.144 |
workshop | +0.143 |
sing | +0.141 |
Neg logit contributions | |
l | -0.085 |
ch | -0.085 |
s | -0.082 |
fl | -0.081 |
subs | -0.080 |
Token | nineteen |
Token ID | 43063 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
azes | +0.041 |
isdom | +0.033 |
ement | +0.032 |
ires | +0.031 |
pit | +0.031 |
Neg logit contributions | |
ch | -0.049 |
sc | -0.047 |
subs | -0.046 |
B | -0.045 |
bo | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
azes | +0.132 |
eria | +0.118 |
sing | +0.118 |
ocolate | +0.117 |
balcony | +0.115 |
Neg logit contributions | |
l | -0.066 |
s | -0.060 |
ch | -0.059 |
sc | -0.058 |
subs | -0.057 |
Token | twenty |
Token ID | 8208 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
azes | +0.044 |
isdom | +0.036 |
eria | +0.033 |
ocolate | +0.033 |
journal | +0.033 |
Neg logit contributions | |
ch | -0.056 |
sc | -0.052 |
l | -0.052 |
bo | -0.052 |
fl | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
azes | +0.083 |
fridge | +0.070 |
isdom | +0.070 |
pit | +0.069 |
sing | +0.069 |
Neg logit contributions | |
ch | -0.060 |
sc | -0.058 |
B | -0.057 |
subs | -0.055 |
bo | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
azes | +0.043 |
isdom | +0.039 |
eria | +0.037 |
ocolate | +0.036 |
ires | +0.036 |
Neg logit contributions | |
ch | -0.026 |
sc | -0.024 |
subs | -0.023 |
bo | -0.023 |
fl | -0.023 |
Token | fourteen |
Token ID | 29167 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
azes | +0.023 |
isdom | +0.019 |
ement | +0.018 |
eria | +0.018 |
workshop | +0.017 |
Neg logit contributions | |
ch | -0.024 |
sc | -0.023 |
bo | -0.022 |
B | -0.022 |
subs | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
azes | +0.110 |
isdom | +0.102 |
eria | +0.100 |
sing | +0.097 |
ocolate | +0.097 |
Neg logit contributions | |
ch | -0.061 |
subs | -0.060 |
l | -0.060 |
s | -0.057 |
scrap | -0.057 |
Token | fifteen |
Token ID | 17280 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
azes | +0.031 |
isdom | +0.026 |
ement | +0.024 |
pit | +0.024 |
studio | +0.024 |
Neg logit contributions | |
ch | -0.039 |
sc | -0.036 |
bo | -0.036 |
subs | -0.036 |
B | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
azes | +0.120 |
isdom | +0.111 |
sing | +0.107 |
eria | +0.106 |
ocolate | +0.104 |
Neg logit contributions | |
ch | -0.067 |
l | -0.064 |
subs | -0.061 |
s | -0.060 |
sc | -0.060 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
azes | +0.039 |
isdom | +0.032 |
ement | +0.030 |
pit | +0.029 |
ires | +0.029 |
Neg logit contributions | |
ch | -0.047 |
sc | -0.045 |
bo | -0.043 |
B | -0.042 |
subs | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
azes | +0.161 |
isdom | +0.151 |
sing | +0.149 |
eria | +0.148 |
itor | +0.145 |
Neg logit contributions | |
l | -0.081 |
s | -0.079 |
ch | -0.079 |
subs | -0.076 |
fl | -0.073 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
azes | +0.048 |
isdom | +0.039 |
ires | +0.037 |
pit | +0.037 |
ement | +0.037 |
Neg logit contributions | |
ch | -0.052 |
sc | -0.050 |
bo | -0.047 |
B | -0.046 |
subs | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
azes | +0.114 |
eria | +0.106 |
isdom | +0.105 |
sing | +0.105 |
balcony | +0.104 |
Neg logit contributions | |
ch | -0.069 |
l | -0.065 |
fl | -0.065 |
bo | -0.064 |
s | -0.064 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
azes | +0.039 |
isdom | +0.032 |
ement | +0.030 |
pit | +0.030 |
ires | +0.029 |
Neg logit contributions | |
ch | -0.044 |
sc | -0.041 |
bo | -0.040 |
subs | -0.039 |
B | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
azes | +0.142 |
isdom | +0.138 |
ocolate | +0.135 |
eria | +0.133 |
itor | +0.133 |
Neg logit contributions | |
s | -0.070 |
l | -0.069 |
ch | -0.066 |
subs | -0.062 |
fl | -0.060 |
Token | They |
Token ID | 1119 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
ch | +0.002 |
sc | +0.002 |
B | +0.002 |
subs | +0.001 |
ched | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.002 |
isdom | -0.002 |
mmm | -0.002 |
ires | -0.002 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
azes | +0.007 |
patiently | +0.006 |
isdom | +0.006 |
fridge | +0.006 |
oven | +0.006 |
Neg logit contributions | |
ch | -0.008 |
sc | -0.008 |
B | -0.008 |
subs | -0.007 |
fl | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
sc | +0.032 |
ch | +0.032 |
B | +0.031 |
subs | +0.031 |
bo | +0.029 |
Neg logit contributions | |
azes | -0.043 |
ires | -0.036 |
isdom | -0.036 |
pit | -0.036 |
oven | -0.036 |
Token | recommend |
Token ID | 4313 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
sc | +0.012 |
ch | +0.012 |
B | +0.012 |
subs | +0.012 |
ched | +0.011 |
Neg logit contributions | |
azes | -0.015 |
pit | -0.012 |
isdom | -0.012 |
mmm | -0.012 |
oven | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -9.41e-03 |
Pos logit contributions | |
azes | +0.027 |
pit | +0.025 |
mmm | +0.023 |
ement | +0.023 |
isdom | +0.023 |
Neg logit contributions | |
ch | -0.017 |
B | -0.016 |
sc | -0.016 |
subs | -0.015 |
ched | -0.014 |
Token | each |
Token ID | 1123 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
azes | +0.019 |
pit | +0.016 |
ement | +0.016 |
mmm | +0.016 |
ires | +0.016 |
Neg logit contributions | |
ch | -0.012 |
B | -0.012 |
sc | -0.012 |
subs | -0.011 |
bo | -0.011 |
Token | other |
Token ID | 584 |
Feature activation | -5.54e-04 |
Pos logit contributions | |
azes | +0.136 |
oven | +0.125 |
fridge | +0.120 |
ires | +0.118 |
office | +0.117 |
Neg logit contributions | |
subs | -0.112 |
sc | -0.111 |
ch | -0.105 |
ched | -0.104 |
B | -0.103 |
Token | what |
Token ID | 644 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
azes | +0.001 |
pit | +0.001 |
isdom | +0.001 |
ires | +0.001 |
oven | +0.001 |
Neg logit contributions | |
ch | -0.001 |
sc | -0.001 |
B | -0.001 |
subs | -0.001 |
bo | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
sc | +0.040 |
ch | +0.038 |
B | +0.038 |
subs | +0.037 |
bo | +0.035 |
Neg logit contributions | |
azes | -0.054 |
writing | -0.046 |
isdom | -0.045 |
ires | -0.045 |
oven | -0.044 |
Token | best |
Token ID | 1266 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
azes | +0.078 |
pit | +0.066 |
mmm | +0.064 |
ement | +0.064 |
isdom | +0.064 |
Neg logit contributions | |
ch | -0.067 |
sc | -0.066 |
B | -0.065 |
subs | -0.062 |
ched | -0.060 |
Token | for |
Token ID | 329 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
azes | +0.103 |
pit | +0.088 |
isdom | +0.086 |
mmm | +0.086 |
ement | +0.086 |
Neg logit contributions | |
ch | -0.067 |
sc | -0.066 |
B | -0.066 |
subs | -0.063 |
ched | -0.059 |
Token | Then |
Token ID | 3244 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
sc | +0.010 |
ch | +0.010 |
B | +0.009 |
text | +0.009 |
Fl | +0.009 |
Neg logit contributions | |
azes | -0.022 |
castle | -0.021 |
pit | -0.021 |
isdom | -0.020 |
ement | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
sc | +0.032 |
B | +0.032 |
ch | +0.032 |
subs | +0.030 |
ched | +0.029 |
Neg logit contributions | |
azes | -0.036 |
pit | -0.030 |
writing | -0.030 |
oven | -0.030 |
mmm | -0.030 |
Token | try |
Token ID | 1949 |
Feature activation | -7.08e-03 |
Pos logit contributions | |
azes | +0.019 |
ement | +0.017 |
mmm | +0.017 |
isdom | +0.016 |
ummy | +0.016 |
Neg logit contributions | |
sc | -0.010 |
ch | -0.010 |
scrap | -0.010 |
bo | -0.010 |
subs | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.89e-03 |
Pos logit contributions | |
azes | +0.020 |
mmm | +0.019 |
ement | +0.018 |
eria | +0.018 |
isdom | +0.018 |
Neg logit contributions | |
s | -0.003 |
l | -0.003 |
off | -0.003 |
fl | -0.003 |
ch | -0.003 |
Token | find |
Token ID | 1064 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
azes | +0.014 |
ement | +0.013 |
ires | +0.012 |
isdom | +0.012 |
ummy | +0.012 |
Neg logit contributions | |
B | -0.006 |
hurt | -0.006 |
bo | -0.006 |
ch | -0.006 |
ny | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
azes | +0.101 |
pit | +0.089 |
eria | +0.085 |
castle | +0.085 |
mmm | +0.084 |
Neg logit contributions | |
ch | -0.030 |
away | -0.027 |
ched | -0.025 |
B | -0.025 |
off | -0.024 |
Token | other |
Token ID | 584 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
azes | +0.192 |
mmm | +0.163 |
ement | +0.161 |
isdom | +0.161 |
balcony | +0.159 |
Neg logit contributions | |
sc | -0.072 |
B | -0.072 |
ch | -0.070 |
ny | -0.066 |
subs | -0.061 |
Token | 's |
Token ID | 338 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
sc | +0.011 |
B | +0.010 |
ch | +0.010 |
ny | +0.010 |
bo | +0.009 |
Neg logit contributions | |
azes | -0.026 |
mmm | -0.023 |
isdom | -0.023 |
ires | -0.022 |
ement | -0.022 |
Token | fruit |
Token ID | 8234 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
fl | +0.003 |
scrap | +0.003 |
subs | +0.002 |
ch | +0.002 |
hurts | +0.002 |
Neg logit contributions | |
azes | -0.004 |
mmm | -0.003 |
otion | -0.003 |
ifting | -0.003 |
ement | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
azes | +0.045 |
isdom | +0.039 |
mmm | +0.038 |
ement | +0.037 |
ires | +0.037 |
Neg logit contributions | |
sc | -0.018 |
ch | -0.016 |
B | -0.016 |
ny | -0.016 |
subs | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
sc | +0.013 |
ch | +0.012 |
B | +0.012 |
Fl | +0.011 |
text | +0.011 |
Neg logit contributions | |
azes | -0.023 |
castle | -0.021 |
pit | -0.021 |
isdom | -0.021 |
ement | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
azes | +0.025 |
mmm | +0.020 |
pit | +0.020 |
isdom | +0.020 |
ocolate | +0.019 |
Neg logit contributions | |
sc | -0.024 |
ch | -0.023 |
B | -0.023 |
subs | -0.022 |
ched | -0.021 |
Token | treasures |
Token ID | 29561 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
azes | +0.069 |
castle | +0.060 |
pit | +0.060 |
mmm | +0.058 |
ires | +0.057 |
Neg logit contributions | |
B | -0.043 |
ch | -0.040 |
sc | -0.039 |
subs | -0.037 |
fl | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
sc | +0.004 |
B | +0.003 |
ch | +0.003 |
subs | +0.003 |
ched | +0.003 |
Neg logit contributions | |
azes | -0.007 |
mmm | -0.006 |
isdom | -0.006 |
ires | -0.006 |
ocolate | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ch | +0.010 |
sc | +0.010 |
B | +0.010 |
Spot | +0.008 |
text | +0.008 |
Neg logit contributions | |
azes | -0.027 |
castle | -0.026 |
pit | -0.025 |
ement | -0.024 |
patiently | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
B | +0.016 |
ch | +0.015 |
sc | +0.015 |
ched | +0.013 |
bo | +0.012 |
Neg logit contributions | |
azes | -0.043 |
pit | -0.040 |
castle | -0.039 |
fridge | -0.038 |
oven | -0.038 |
Token | When |
Token ID | 2215 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
sc | +0.015 |
ch | +0.015 |
B | +0.014 |
subs | +0.014 |
bo | +0.013 |
Neg logit contributions | |
azes | -0.023 |
pit | -0.020 |
mmm | -0.020 |
isdom | -0.020 |
ires | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
sc | +0.084 |
B | +0.082 |
ch | +0.081 |
subs | +0.078 |
bo | +0.077 |
Neg logit contributions | |
azes | -0.111 |
oven | -0.095 |
mmm | -0.095 |
pit | -0.093 |
isdom | -0.093 |
Token | was |
Token ID | 373 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
sc | +0.028 |
burn | +0.028 |
B | +0.027 |
Br | +0.027 |
scrap | +0.027 |
Neg logit contributions | |
azes | -0.042 |
pit | -0.039 |
ement | -0.037 |
castle | -0.036 |
patiently | -0.036 |
Token | time |
Token ID | 640 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
ch | +0.010 |
B | +0.010 |
sc | +0.010 |
subs | +0.009 |
ched | +0.008 |
Neg logit contributions | |
azes | -0.031 |
pit | -0.027 |
isdom | -0.027 |
ement | -0.027 |
ires | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
ch | +0.047 |
sc | +0.046 |
B | +0.044 |
subs | +0.044 |
ched | +0.041 |
Neg logit contributions | |
azes | -0.102 |
pit | -0.089 |
isdom | -0.088 |
mmm | -0.088 |
ires | -0.088 |
Token | go |
Token ID | 467 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
sc | +0.012 |
B | +0.012 |
ch | +0.011 |
ched | +0.011 |
subs | +0.010 |
Neg logit contributions | |
azes | -0.015 |
fridge | -0.013 |
castle | -0.013 |
mmm | -0.013 |
oven | -0.013 |
Token | broken |
Token ID | 5445 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
azes | +0.017 |
oven | +0.014 |
writing | +0.014 |
fridge | +0.014 |
pit | +0.014 |
Neg logit contributions | |
sc | -0.016 |
B | -0.016 |
ch | -0.015 |
subs | -0.015 |
text | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
ch | +0.031 |
sc | +0.031 |
B | +0.031 |
subs | +0.029 |
bo | +0.027 |
Neg logit contributions | |
azes | -0.046 |
pit | -0.039 |
isdom | -0.038 |
mmm | -0.038 |
ires | -0.038 |
Token | it |
Token ID | 340 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
sc | +0.070 |
B | +0.069 |
ch | +0.068 |
subs | +0.066 |
ched | +0.063 |
Neg logit contributions | |
azes | -0.082 |
fridge | -0.071 |
oven | -0.070 |
pit | -0.068 |
writing | -0.068 |
Token | didn |
Token ID | 1422 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Br | +0.054 |
B | +0.052 |
Ar | +0.051 |
sc | +0.051 |
ch | +0.050 |
Neg logit contributions | |
azes | -0.067 |
fridge | -0.067 |
oven | -0.064 |
desk | -0.062 |
writing | -0.060 |
Token | 't |
Token ID | 470 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
sc | +0.136 |
fl | +0.136 |
B | +0.131 |
Br | +0.128 |
subs | +0.126 |
Neg logit contributions | |
azes | -0.095 |
mmm | -0.076 |
ummy | -0.075 |
ires | -0.074 |
oven | -0.073 |
Token | work |
Token ID | 670 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
sc | +0.067 |
B | +0.067 |
ch | +0.066 |
subs | +0.064 |
ched | +0.060 |
Neg logit contributions | |
azes | -0.090 |
isdom | -0.075 |
fridge | -0.075 |
pit | -0.075 |
mmm | -0.074 |
Token | anymore |
Token ID | 7471 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
B | +0.123 |
Br | +0.122 |
ch | +0.122 |
sc | +0.122 |
fl | +0.119 |
Neg logit contributions | |
azes | -0.109 |
writing | -0.095 |
patiently | -0.093 |
ement | -0.090 |
fridge | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
B | +0.027 |
ch | +0.027 |
sc | +0.026 |
subs | +0.025 |
ched | +0.024 |
Neg logit contributions | |
azes | -0.060 |
pit | -0.054 |
oven | -0.053 |
ires | -0.053 |
ement | -0.053 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ch | +0.023 |
sc | +0.023 |
subs | +0.023 |
B | +0.022 |
ched | +0.021 |
Neg logit contributions | |
azes | -0.029 |
fridge | -0.025 |
pit | -0.024 |
ement | -0.024 |
mmm | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
ch | +0.032 |
sc | +0.032 |
B | +0.031 |
subs | +0.030 |
ched | +0.027 |
Neg logit contributions | |
azes | -0.071 |
pit | -0.062 |
fridge | -0.061 |
isdom | -0.061 |
oven | -0.061 |
Token | sad |
Token ID | 6507 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.004 |
mmm | +0.004 |
isdom | +0.004 |
ires | +0.004 |
Neg logit contributions | |
ch | -0.003 |
B | -0.003 |
subs | -0.003 |
sc | -0.003 |
scrap | -0.003 |
Token | history |
Token ID | 2106 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
azes | +0.011 |
mmm | +0.009 |
ement | +0.009 |
pit | +0.009 |
isdom | +0.009 |
Neg logit contributions | |
ch | -0.007 |
B | -0.007 |
fl | -0.007 |
subs | -0.007 |
sc | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
sc | +0.007 |
ch | +0.007 |
B | +0.006 |
l | +0.006 |
subs | +0.006 |
Neg logit contributions | |
azes | -0.021 |
sing | -0.019 |
mmm | -0.019 |
pit | -0.019 |
ocolate | -0.019 |
Token | Every |
Token ID | 3887 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
B | +0.008 |
ch | +0.008 |
sc | +0.007 |
Ch | +0.006 |
Fl | +0.006 |
Neg logit contributions | |
castle | -0.015 |
pit | -0.015 |
azes | -0.014 |
patiently | -0.014 |
Majesty | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ch | +0.032 |
sc | +0.027 |
B | +0.026 |
subs | +0.025 |
ny | +0.023 |
Neg logit contributions | |
azes | -0.111 |
mmm | -0.099 |
pit | -0.099 |
ires | -0.099 |
ement | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
sc | +0.087 |
B | +0.087 |
ch | +0.087 |
subs | +0.084 |
bo | +0.081 |
Neg logit contributions | |
azes | -0.076 |
pit | -0.060 |
mmm | -0.060 |
isdom | -0.059 |
ires | -0.059 |
Token | night |
Token ID | 1755 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
ch | +0.023 |
sc | +0.022 |
B | +0.022 |
subs | +0.020 |
scrap | +0.020 |
Neg logit contributions | |
azes | -0.046 |
pit | -0.041 |
ement | -0.041 |
castle | -0.038 |
mmm | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
sc | +0.111 |
B | +0.111 |
subs | +0.108 |
ch | +0.108 |
bo | +0.105 |
Neg logit contributions | |
azes | -0.087 |
writing | -0.069 |
oven | -0.067 |
mmm | -0.067 |
fridge | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
azes | +0.010 |
pit | +0.010 |
ement | +0.009 |
castle | +0.009 |
isdom | +0.009 |
Neg logit contributions | |
ch | -0.004 |
B | -0.004 |
sc | -0.004 |
subs | -0.003 |
Free | -0.003 |
Token | spray |
Token ID | 11662 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ch | +0.029 |
B | +0.028 |
sc | +0.026 |
subs | +0.026 |
scrap | +0.023 |
Neg logit contributions | |
azes | -0.075 |
pit | -0.065 |
ires | -0.065 |
isdom | -0.064 |
mmm | -0.064 |
Token | of |
Token ID | 286 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ch | +0.026 |
sc | +0.026 |
B | +0.025 |
subs | +0.024 |
ched | +0.023 |
Neg logit contributions | |
azes | -0.042 |
mmm | -0.036 |
pit | -0.035 |
isdom | -0.035 |
ires | -0.035 |
Token | water |
Token ID | 1660 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
ch | +0.026 |
B | +0.023 |
scrap | +0.021 |
sc | +0.020 |
st | +0.020 |
Neg logit contributions | |
azes | -0.057 |
pit | -0.054 |
ae | -0.051 |
mmm | -0.050 |
ement | -0.050 |
Token | their |
Token ID | 511 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
sc | +0.011 |
ch | +0.011 |
B | +0.011 |
subs | +0.011 |
bo | +0.010 |
Neg logit contributions | |
azes | -0.011 |
oven | -0.010 |
isdom | -0.009 |
ires | -0.009 |
mmm | -0.009 |
Token | medicine |
Token ID | 9007 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ch | +0.034 |
B | +0.034 |
sc | +0.033 |
Br | +0.033 |
ched | +0.033 |
Neg logit contributions | |
azes | -0.033 |
fridge | -0.033 |
oven | -0.032 |
refrigerator | -0.032 |
pasta | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
sc | +0.045 |
ch | +0.043 |
B | +0.042 |
subs | +0.040 |
ched | +0.039 |
Neg logit contributions | |
azes | -0.083 |
mmm | -0.070 |
isdom | -0.069 |
pit | -0.069 |
ires | -0.069 |
Token | stuck |
Token ID | 7819 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ch | +0.017 |
sc | +0.017 |
B | +0.017 |
subs | +0.016 |
bo | +0.015 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.023 |
oven | -0.023 |
isdom | -0.023 |
fridge | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ch | +0.043 |
sc | +0.043 |
B | +0.043 |
subs | +0.041 |
ched | +0.038 |
Neg logit contributions | |
azes | -0.063 |
pit | -0.053 |
isdom | -0.052 |
mmm | -0.052 |
ires | -0.052 |
Token | therm |
Token ID | 21969 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
ch | +0.035 |
sc | +0.035 |
B | +0.035 |
subs | +0.033 |
bo | +0.031 |
Neg logit contributions | |
azes | -0.048 |
pit | -0.040 |
isdom | -0.040 |
ires | -0.039 |
mmm | -0.039 |
Token | ometer |
Token ID | 15635 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ch | +0.100 |
sc | +0.098 |
B | +0.098 |
subs | +0.095 |
bo | +0.092 |
Neg logit contributions | |
azes | -0.111 |
pit | -0.092 |
isdom | -0.089 |
mmm | -0.089 |
ement | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
B | +0.036 |
sc | +0.035 |
ch | +0.035 |
subs | +0.034 |
text | +0.032 |
Neg logit contributions | |
azes | -0.055 |
pit | -0.048 |
oven | -0.048 |
fridge | -0.047 |
castle | -0.046 |
Token | their |
Token ID | 511 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
ch | +0.016 |
sc | +0.016 |
B | +0.016 |
subs | +0.015 |
ched | +0.014 |
Neg logit contributions | |
azes | -0.031 |
pit | -0.027 |
oven | -0.027 |
fridge | -0.027 |
mmm | -0.027 |
Token | mouth |
Token ID | 5422 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
azes | +0.002 |
pit | +0.002 |
mmm | +0.002 |
isdom | +0.002 |
ires | +0.002 |
Neg logit contributions | |
ch | -0.002 |
sc | -0.002 |
B | -0.002 |
subs | -0.002 |
bo | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
ch | +0.016 |
sc | +0.016 |
B | +0.016 |
subs | +0.015 |
ched | +0.015 |
Neg logit contributions | |
azes | -0.030 |
isdom | -0.026 |
pit | -0.026 |
mmm | -0.026 |
ires | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
ch | +0.028 |
sc | +0.028 |
B | +0.027 |
subs | +0.026 |
ched | +0.025 |
Neg logit contributions | |
azes | -0.051 |
pit | -0.044 |
ement | -0.044 |
ires | -0.043 |
mmm | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ch | +0.009 |
B | +0.008 |
subs | +0.008 |
sc | +0.008 |
scrap | +0.008 |
Neg logit contributions | |
azes | -0.017 |
ement | -0.015 |
pit | -0.015 |
mmm | -0.015 |
ires | -0.015 |
Token | pay |
Token ID | 1414 |
Feature activation | +4.76e-03 |
Pos logit contributions | |
ch | +0.022 |
B | +0.021 |
bo | +0.021 |
sc | +0.021 |
subs | +0.020 |
Neg logit contributions | |
azes | -0.036 |
ement | -0.032 |
pit | -0.031 |
ires | -0.031 |
eria | -0.029 |
Token | one |
Token ID | 530 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.006 |
B | +0.006 |
bo | +0.006 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.010 |
pit | -0.009 |
castle | -0.008 |
ement | -0.008 |
balcony | -0.008 |
Token | dollar |
Token ID | 8872 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
azes | +0.044 |
pit | +0.036 |
isdom | +0.036 |
ement | +0.035 |
balcony | +0.035 |
Neg logit contributions | |
ch | -0.027 |
sc | -0.027 |
B | -0.025 |
bo | -0.023 |
subs | -0.023 |
Token | per |
Token ID | 583 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
azes | +0.023 |
pit | +0.019 |
balcony | +0.019 |
ement | +0.019 |
isdom | +0.019 |
Neg logit contributions | |
sc | -0.011 |
ch | -0.011 |
B | -0.010 |
bo | -0.010 |
fl | -0.009 |
Token | cup |
Token ID | 6508 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
B | +0.077 |
subs | +0.073 |
scrap | +0.071 |
text | +0.070 |
Br | +0.068 |
Neg logit contributions | |
azes | -0.112 |
ires | -0.104 |
oven | -0.103 |
isdom | -0.102 |
mmm | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
sc | +0.010 |
ch | +0.009 |
B | +0.008 |
bo | +0.008 |
ched | +0.008 |
Neg logit contributions | |
azes | -0.020 |
isdom | -0.017 |
pit | -0.017 |
balcony | -0.017 |
Majesty | -0.017 |
Token | Or |
Token ID | 1471 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
ch | +0.004 |
sc | +0.004 |
B | +0.004 |
bo | +0.004 |
Fl | +0.004 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
castle | -0.005 |
balcony | -0.005 |
ement | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ch | +0.014 |
sc | +0.013 |
B | +0.013 |
subs | +0.012 |
bo | +0.012 |
Neg logit contributions | |
azes | -0.017 |
pit | -0.015 |
ement | -0.015 |
castle | -0.014 |
balcony | -0.014 |
Token | can |
Token ID | 460 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ch | +0.023 |
sc | +0.023 |
B | +0.022 |
subs | +0.020 |
ched | +0.020 |
Neg logit contributions | |
azes | -0.056 |
pit | -0.049 |
ement | -0.048 |
ires | -0.048 |
mmm | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.005 |
workshop | +0.005 |
ires | +0.004 |
sing | +0.004 |
Neg logit contributions | |
ch | -0.003 |
B | -0.003 |
ched | -0.003 |
sc | -0.003 |
l | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
azes | +0.034 |
pit | +0.030 |
castle | +0.029 |
ement | +0.029 |
isdom | +0.029 |
Neg logit contributions | |
ch | -0.018 |
B | -0.017 |
sc | -0.016 |
Fl | -0.015 |
fl | -0.015 |
Token | L |
Token ID | 43 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
azes | +0.009 |
mmm | +0.009 |
ocolate | +0.008 |
isdom | +0.008 |
ae | +0.008 |
Neg logit contributions | |
subs | -0.006 |
ch | -0.006 |
sc | -0.006 |
text | -0.005 |
scrap | -0.005 |
Token | ily |
Token ID | 813 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ch | +0.010 |
B | +0.010 |
sc | +0.010 |
subs | +0.009 |
ched | +0.009 |
Neg logit contributions | |
azes | -0.007 |
pit | -0.006 |
balcony | -0.005 |
fridge | -0.005 |
castle | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ch | +0.023 |
B | +0.022 |
sc | +0.022 |
subs | +0.022 |
ched | +0.021 |
Neg logit contributions | |
azes | -0.031 |
ires | -0.026 |
ement | -0.025 |
pit | -0.025 |
balcony | -0.025 |
Token | you |
Token ID | 345 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
azes | +0.045 |
ement | +0.040 |
pit | +0.039 |
ires | +0.037 |
castle | +0.037 |
Neg logit contributions | |
ch | -0.025 |
Fl | -0.021 |
sc | -0.021 |
B | -0.021 |
subs | -0.021 |
Token | have |
Token ID | 423 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
ch | +0.017 |
B | +0.016 |
sc | +0.016 |
ched | +0.015 |
subs | +0.015 |
Neg logit contributions | |
azes | -0.041 |
pit | -0.036 |
ement | -0.036 |
ires | -0.036 |
castle | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ch | +0.006 |
B | +0.005 |
sc | +0.005 |
subs | +0.005 |
scrap | +0.005 |
Neg logit contributions | |
azes | -0.014 |
pit | -0.012 |
ement | -0.012 |
ires | -0.012 |
mmm | -0.011 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
ch | +0.015 |
bo | +0.014 |
B | +0.014 |
sc | +0.014 |
ny | +0.014 |
Neg logit contributions | |
azes | -0.027 |
ement | -0.023 |
pit | -0.023 |
ires | -0.023 |
eria | -0.022 |
Token | your |
Token ID | 534 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
azes | +0.048 |
pit | +0.041 |
sing | +0.039 |
castle | +0.039 |
balcony | +0.038 |
Neg logit contributions | |
ch | -0.026 |
sc | -0.026 |
B | -0.025 |
Fl | -0.023 |
away | -0.023 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -1.04e-03 |
Pos logit contributions | |
azes | +0.003 |
pit | +0.003 |
otion | +0.003 |
eria | +0.002 |
mmm | +0.002 |
Neg logit contributions | |
scrap | -0.003 |
ch | -0.003 |
sc | -0.003 |
fl | -0.003 |
B | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
azes | +0.005 |
mmm | +0.004 |
isdom | +0.004 |
pit | +0.004 |
ires | +0.004 |
Neg logit contributions | |
B | -0.001 |
ch | -0.001 |
sc | -0.001 |
subs | -0.001 |
scrap | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
azes | +0.037 |
mmm | +0.034 |
isdom | +0.033 |
ocolate | +0.033 |
mmmm | +0.032 |
Neg logit contributions | |
sc | -0.016 |
B | -0.014 |
ch | -0.014 |
ched | -0.013 |
s | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ch | +0.013 |
B | +0.013 |
sc | +0.013 |
subs | +0.012 |
bo | +0.011 |
Neg logit contributions | |
azes | -0.021 |
pit | -0.018 |
isdom | -0.018 |
fridge | -0.018 |
oven | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +8.62e-04 |
Pos logit contributions | |
azes | +0.053 |
mmm | +0.047 |
pit | +0.045 |
isdom | +0.045 |
ocolate | +0.045 |
Neg logit contributions | |
B | -0.030 |
ch | -0.030 |
sc | -0.029 |
ched | -0.028 |
scrap | -0.027 |
Token | pepper |
Token ID | 13385 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ch | +0.001 |
sc | +0.001 |
B | +0.001 |
subs | +0.001 |
scrap | +0.001 |
Neg logit contributions | |
azes | -0.002 |
mmm | -0.001 |
isdom | -0.001 |
ement | -0.001 |
ires | -0.001 |
Token | resting |
Token ID | 19186 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
ch | +0.013 |
sc | +0.012 |
subs | +0.012 |
ched | +0.012 |
B | +0.011 |
Neg logit contributions | |
azes | -0.026 |
isdom | -0.022 |
mmm | -0.021 |
ires | -0.021 |
ocolate | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
sc | +0.010 |
ch | +0.010 |
B | +0.010 |
subs | +0.009 |
ched | +0.008 |
Neg logit contributions | |
azes | -0.023 |
isdom | -0.020 |
mmm | -0.020 |
pit | -0.019 |
ires | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
B | +0.003 |
ch | +0.003 |
sc | +0.003 |
subs | +0.002 |
scrap | +0.002 |
Neg logit contributions | |
azes | -0.010 |
isdom | -0.008 |
ires | -0.008 |
pit | -0.008 |
mmm | -0.008 |
Token | bush |
Token ID | 24484 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ch | +0.012 |
sc | +0.011 |
B | +0.011 |
subs | +0.010 |
scrap | +0.010 |
Neg logit contributions | |
azes | -0.015 |
ires | -0.012 |
isdom | -0.012 |
mmm | -0.012 |
pit | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-04 |
Pos logit contributions | |
azes | +0.063 |
isdom | +0.054 |
ires | +0.054 |
mmm | +0.053 |
Majesty | +0.053 |
Neg logit contributions | |
sc | -0.023 |
ch | -0.022 |
B | -0.020 |
ny | -0.019 |
ched | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
B | +0.000 |
sc | +0.000 |
ch | +0.000 |
Fl | +0.000 |
Spot | +0.000 |
Neg logit contributions | |
azes | -0.001 |
castle | -0.000 |
pit | -0.000 |
ement | -0.000 |
isdom | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -4.84e-04 |
Pos logit contributions | |
B | +0.015 |
ch | +0.015 |
sc | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.041 |
pit | -0.036 |
ires | -0.036 |
mmm | -0.035 |
ement | -0.035 |
Token | sorry |
Token ID | 7926 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
azes | +0.001 |
pit | +0.001 |
ires | +0.001 |
ement | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
ch | -0.001 |
B | -0.001 |
subs | -0.001 |
sc | -0.001 |
ched | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ch | +0.003 |
B | +0.003 |
sc | +0.003 |
subs | +0.003 |
bo | +0.003 |
Neg logit contributions | |
azes | -0.005 |
pit | -0.004 |
ement | -0.004 |
mmm | -0.004 |
isdom | -0.004 |
Token | helped |
Token ID | 4193 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
sc | +0.018 |
ch | +0.018 |
B | +0.017 |
subs | +0.016 |
text | +0.016 |
Neg logit contributions | |
azes | -0.030 |
patiently | -0.027 |
oven | -0.027 |
fridge | -0.027 |
writing | -0.026 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
sc | +0.041 |
ch | +0.040 |
subs | +0.040 |
B | +0.039 |
fl | +0.038 |
Neg logit contributions | |
azes | -0.037 |
fridge | -0.031 |
oven | -0.030 |
patiently | -0.030 |
writing | -0.030 |
Token | print |
Token ID | 3601 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ch | +0.016 |
sc | +0.016 |
B | +0.016 |
subs | +0.015 |
ched | +0.014 |
Neg logit contributions | |
azes | -0.023 |
pit | -0.020 |
mmm | -0.019 |
ement | -0.019 |
ires | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ch | +0.016 |
sc | +0.016 |
B | +0.015 |
ched | +0.015 |
subs | +0.015 |
Neg logit contributions | |
azes | -0.031 |
mmm | -0.027 |
isdom | -0.026 |
pit | -0.026 |
balcony | -0.026 |
Token | drawings |
Token ID | 23388 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ch | +0.039 |
B | +0.039 |
sc | +0.038 |
subs | +0.037 |
ched | +0.036 |
Neg logit contributions | |
azes | -0.029 |
pit | -0.023 |
isdom | -0.022 |
oven | -0.022 |
fridge | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
sc | +0.023 |
subs | +0.021 |
ched | +0.021 |
ch | +0.021 |
B | +0.021 |
Neg logit contributions | |
azes | -0.062 |
isdom | -0.054 |
mmm | -0.054 |
ires | -0.053 |
Majesty | -0.052 |
Token | |
Token ID | 220 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
sc | +0.015 |
ch | +0.015 |
B | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.019 |
pit | -0.016 |
fridge | -0.015 |
ires | -0.015 |
mmm | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
B | +0.013 |
sc | +0.013 |
ch | +0.013 |
subs | +0.012 |
ched | +0.011 |
Neg logit contributions | |
azes | -0.030 |
pit | -0.027 |
castle | -0.026 |
oven | -0.026 |
isdom | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
sc | +0.047 |
ch | +0.046 |
subs | +0.046 |
B | +0.044 |
ched | +0.042 |
Neg logit contributions | |
azes | -0.052 |
writing | -0.042 |
fridge | -0.042 |
mmm | -0.042 |
pit | -0.042 |
Token | time |
Token ID | 640 |
Feature activation | -9.89e-05 |
Pos logit contributions | |
sc | +0.032 |
ch | +0.032 |
B | +0.032 |
subs | +0.031 |
ched | +0.028 |
Neg logit contributions | |
azes | -0.079 |
pit | -0.069 |
mmm | -0.068 |
isdom | -0.068 |
oven | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
azes | +0.000 |
oven | +0.000 |
isdom | +0.000 |
ires | +0.000 |
pit | +0.000 |
Neg logit contributions | |
B | -0.000 |
ch | -0.000 |
sc | -0.000 |
subs | -0.000 |
text | -0.000 |
Token | there |
Token ID | 612 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
azes | +0.058 |
pit | +0.049 |
isdom | +0.048 |
mmm | +0.048 |
ires | +0.048 |
Neg logit contributions | |
ch | -0.042 |
sc | -0.042 |
B | -0.042 |
subs | -0.040 |
ched | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
ch | +0.026 |
sc | +0.026 |
B | +0.025 |
subs | +0.024 |
bo | +0.021 |
Neg logit contributions | |
azes | -0.088 |
pit | -0.078 |
isdom | -0.077 |
mmm | -0.077 |
ires | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
azes | +0.017 |
pit | +0.015 |
isdom | +0.014 |
ement | +0.014 |
ires | +0.014 |
Neg logit contributions | |
B | -0.011 |
ch | -0.011 |
sc | -0.011 |
subs | -0.010 |
bo | -0.010 |
Token | mighty |
Token ID | 18680 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
B | +0.025 |
ch | +0.025 |
sc | +0.022 |
subs | +0.021 |
bo | +0.020 |
Neg logit contributions | |
azes | -0.061 |
pit | -0.053 |
ement | -0.052 |
isdom | -0.052 |
mmm | -0.052 |
Token | land |
Token ID | 1956 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ch | +0.004 |
B | +0.004 |
ny | +0.003 |
k | +0.003 |
st | +0.003 |
Neg logit contributions | |
azes | -0.008 |
ires | -0.007 |
mmm | -0.007 |
ement | -0.007 |
ocolate | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
B | +0.016 |
ch | +0.016 |
sc | +0.016 |
subs | +0.016 |
text | +0.015 |
Neg logit contributions | |
azes | -0.021 |
pit | -0.018 |
oven | -0.018 |
ires | -0.018 |
castle | -0.018 |
Token | In |
Token ID | 554 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ch | +0.015 |
B | +0.014 |
sc | +0.013 |
Free | +0.012 |
subs | +0.012 |
Neg logit contributions | |
azes | -0.023 |
pit | -0.022 |
castle | -0.022 |
ement | -0.021 |
patiently | -0.021 |
Token | this |
Token ID | 428 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ch | +0.014 |
B | +0.013 |
subs | +0.013 |
sc | +0.012 |
text | +0.012 |
Neg logit contributions | |
azes | -0.042 |
pit | -0.037 |
ement | -0.037 |
isdom | -0.036 |
ruits | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
ch | +0.001 |
B | +0.001 |
sc | +0.001 |
subs | +0.001 |
bo | +0.001 |
Neg logit contributions | |
azes | -0.002 |
pit | -0.002 |
isdom | -0.002 |
ires | -0.002 |
oven | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
azes | +0.010 |
pit | +0.009 |
isdom | +0.008 |
oven | +0.008 |
ires | +0.008 |
Neg logit contributions | |
B | -0.005 |
ch | -0.005 |
sc | -0.005 |
subs | -0.004 |
ched | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
azes | +0.023 |
mmm | +0.020 |
pit | +0.020 |
ocolate | +0.020 |
ae | +0.020 |
Neg logit contributions | |
sc | -0.012 |
subs | -0.012 |
ch | -0.012 |
fl | -0.011 |
B | -0.011 |
Token | silly |
Token ID | 14397 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
B | +0.019 |
ch | +0.018 |
sc | +0.018 |
subs | +0.018 |
scrap | +0.017 |
Neg logit contributions | |
azes | -0.038 |
mmm | -0.032 |
isdom | -0.031 |
ues | -0.030 |
castle | -0.030 |
Token | refrigerator |
Token ID | 30500 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
ny | +0.009 |
fl | +0.008 |
B | +0.008 |
subs | +0.008 |
went | +0.008 |
Neg logit contributions | |
azes | -0.012 |
mmm | -0.010 |
ues | -0.010 |
ifting | -0.009 |
ents | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
subs | +0.004 |
sc | +0.004 |
ch | +0.004 |
bo | +0.004 |
B | +0.004 |
Neg logit contributions | |
azes | -0.018 |
mmm | -0.016 |
ires | -0.016 |
isdom | -0.015 |
ruits | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
sc | +0.030 |
ch | +0.030 |
B | +0.030 |
subs | +0.028 |
ched | +0.027 |
Neg logit contributions | |
azes | -0.049 |
pit | -0.043 |
oven | -0.042 |
writing | -0.042 |
fridge | -0.041 |
Token | little |
Token ID | 1310 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
B | +0.023 |
sc | +0.021 |
subs | +0.021 |
scrap | +0.021 |
ch | +0.020 |
Neg logit contributions | |
azes | -0.064 |
mmm | -0.056 |
isdom | -0.055 |
ues | -0.054 |
ires | -0.052 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.58e-04 |
Pos logit contributions | |
B | +0.021 |
sc | +0.020 |
ch | +0.020 |
subs | +0.019 |
fl | +0.017 |
Neg logit contributions | |
azes | -0.071 |
mmm | -0.062 |
isdom | -0.062 |
ires | -0.061 |
castle | -0.060 |
Token | became |
Token ID | 2627 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
azes | +0.001 |
ires | +0.001 |
mmm | +0.001 |
pit | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
ch | -0.000 |
sc | -0.000 |
subs | -0.000 |
B | -0.000 |
bo | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
azes | +0.014 |
pit | +0.012 |
writing | +0.012 |
oven | +0.012 |
patiently | +0.012 |
Neg logit contributions | |
ch | -0.013 |
sc | -0.013 |
B | -0.013 |
subs | -0.012 |
bo | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
azes | +0.007 |
mmm | +0.006 |
ummy | +0.006 |
isdom | +0.006 |
ement | +0.006 |
Neg logit contributions | |
sc | -0.003 |
B | -0.003 |
ch | -0.003 |
ched | -0.002 |
l | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
azes | +0.044 |
mmm | +0.039 |
pit | +0.039 |
isdom | +0.038 |
ement | +0.038 |
Neg logit contributions | |
B | -0.019 |
ch | -0.018 |
sc | -0.018 |
scrap | -0.016 |
subs | -0.016 |
Token | new |
Token ID | 649 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
ch | +0.012 |
sc | +0.012 |
B | +0.012 |
subs | +0.011 |
fl | +0.011 |
Neg logit contributions | |
azes | -0.014 |
mmm | -0.012 |
isdom | -0.011 |
ement | -0.011 |
pit | -0.011 |
Token | things |
Token ID | 1243 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ch | +0.007 |
sc | +0.007 |
fl | +0.007 |
B | +0.006 |
scrap | +0.006 |
Neg logit contributions | |
azes | -0.012 |
mmm | -0.011 |
ifting | -0.010 |
ement | -0.010 |
otion | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
sc | +0.010 |
B | +0.009 |
ch | +0.009 |
s | +0.008 |
ny | +0.008 |
Neg logit contributions | |
azes | -0.036 |
isdom | -0.033 |
mmm | -0.032 |
Majesty | -0.031 |
ocolate | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | -4.79e-04 |
Pos logit contributions | |
ch | +0.002 |
B | +0.002 |
sc | +0.002 |
subs | +0.002 |
Br | +0.002 |
Neg logit contributions | |
azes | -0.004 |
pit | -0.004 |
ement | -0.004 |
castle | -0.004 |
oven | -0.004 |
Token | are |
Token ID | 389 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
azes | +0.001 |
ement | +0.001 |
mmm | +0.001 |
ires | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
sc | -0.000 |
ch | -0.000 |
B | -0.000 |
scrap | -0.000 |
subs | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
azes | +0.071 |
ement | +0.062 |
mmm | +0.062 |
isdom | +0.061 |
pit | +0.058 |
Neg logit contributions | |
ch | -0.055 |
B | -0.053 |
subs | -0.053 |
sc | -0.052 |
scrap | -0.050 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
azes | +0.006 |
pit | +0.005 |
isdom | +0.005 |
ement | +0.005 |
mmm | +0.005 |
Neg logit contributions | |
ch | -0.005 |
B | -0.005 |
sc | -0.005 |
subs | -0.005 |
bo | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
azes | +0.039 |
mmm | +0.037 |
isdom | +0.036 |
ement | +0.036 |
ocolate | +0.036 |
Neg logit contributions | |
B | -0.015 |
fl | -0.014 |
ch | -0.013 |
s | -0.012 |
sc | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
azes | +0.007 |
ires | +0.006 |
pit | +0.006 |
mmm | +0.006 |
isdom | +0.006 |
Neg logit contributions | |
sc | -0.005 |
ch | -0.005 |
B | -0.004 |
subs | -0.004 |
ched | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
B | +0.001 |
ch | +0.001 |
sc | +0.001 |
subs | +0.001 |
ched | +0.001 |
Neg logit contributions | |
azes | -0.001 |
pit | -0.001 |
isdom | -0.001 |
oven | -0.001 |
fridge | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
azes | +0.024 |
ement | +0.021 |
ocolate | +0.021 |
ruits | +0.021 |
pit | +0.021 |
Neg logit contributions | |
B | -0.014 |
ch | -0.014 |
subs | -0.014 |
fl | -0.013 |
sc | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
sc | +0.034 |
ch | +0.034 |
B | +0.033 |
text | +0.030 |
bo | +0.030 |
Neg logit contributions | |
azes | -0.034 |
writing | -0.030 |
patiently | -0.028 |
fridge | -0.027 |
balcony | -0.027 |
Token | thanked |
Token ID | 26280 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
azes | +0.008 |
patiently | +0.007 |
writing | +0.007 |
castle | +0.006 |
isdom | +0.006 |
Neg logit contributions | |
sc | -0.006 |
ch | -0.005 |
B | -0.005 |
fl | -0.005 |
subs | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
azes | +0.010 |
pit | +0.009 |
ires | +0.008 |
ement | +0.008 |
mmm | +0.008 |
Neg logit contributions | |
B | -0.005 |
ch | -0.005 |
sc | -0.005 |
subs | -0.005 |
bo | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
B | +0.009 |
subs | +0.009 |
ch | +0.009 |
scrap | +0.009 |
sc | +0.008 |
Neg logit contributions | |
azes | -0.011 |
mmm | -0.009 |
pit | -0.009 |
isdom | -0.009 |
ocolate | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
azes | +0.039 |
pit | +0.032 |
mmm | +0.032 |
ires | +0.032 |
isdom | +0.032 |
Neg logit contributions | |
ch | -0.028 |
sc | -0.028 |
B | -0.028 |
subs | -0.026 |
bo | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
azes | +0.017 |
pit | +0.014 |
mmm | +0.014 |
ires | +0.014 |
isdom | +0.014 |
Neg logit contributions | |
sc | -0.015 |
ch | -0.015 |
B | -0.015 |
subs | -0.014 |
bo | -0.014 |
Token | getting |
Token ID | 1972 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
azes | +0.025 |
pit | +0.021 |
ires | +0.020 |
mmm | +0.020 |
ement | +0.020 |
Neg logit contributions | |
B | -0.025 |
ch | -0.025 |
sc | -0.025 |
subs | -0.024 |
ched | -0.023 |
Token | him |
Token ID | 683 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
sc | +0.012 |
ch | +0.012 |
B | +0.012 |
subs | +0.012 |
text | +0.011 |
Neg logit contributions | |
azes | -0.015 |
writing | -0.012 |
patiently | -0.012 |
oven | -0.012 |
fridge | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
azes | +0.010 |
writing | +0.009 |
fridge | +0.009 |
patiently | +0.009 |
isdom | +0.009 |
Neg logit contributions | |
sc | -0.009 |
B | -0.009 |
ch | -0.009 |
subs | -0.008 |
Br | -0.008 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.77e-03 |
Pos logit contributions | |
sc | +0.007 |
ch | +0.007 |
B | +0.007 |
subs | +0.007 |
ched | +0.006 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.011 |
oven | -0.011 |
fridge | -0.011 |
ement | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
B | +0.005 |
ch | +0.004 |
sc | +0.004 |
subs | +0.004 |
bo | +0.004 |
Neg logit contributions | |
azes | -0.012 |
ires | -0.010 |
pit | -0.010 |
mmm | -0.010 |
fridge | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
azes | +0.064 |
mmm | +0.055 |
ocolate | +0.055 |
ae | +0.054 |
pit | +0.054 |
Neg logit contributions | |
sc | -0.032 |
ch | -0.031 |
B | -0.030 |
ched | -0.029 |
subs | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
azes | +0.032 |
isdom | +0.027 |
pit | +0.027 |
mmm | +0.026 |
oven | +0.026 |
Neg logit contributions | |
B | -0.024 |
ch | -0.023 |
sc | -0.023 |
subs | -0.023 |
ched | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
B | +0.014 |
ch | +0.014 |
sc | +0.013 |
subs | +0.013 |
bo | +0.013 |
Neg logit contributions | |
azes | -0.030 |
ocolate | -0.027 |
ires | -0.026 |
oven | -0.026 |
ruits | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
azes | +0.072 |
pit | +0.063 |
mmm | +0.062 |
ruits | +0.060 |
castle | +0.060 |
Neg logit contributions | |
B | -0.041 |
ch | -0.039 |
sc | -0.037 |
ched | -0.037 |
subs | -0.036 |
Token | friendly |
Token ID | 8030 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
azes | +0.012 |
ires | +0.011 |
isdom | +0.010 |
mmm | +0.010 |
pit | +0.010 |
Neg logit contributions | |
ch | -0.006 |
B | -0.006 |
sc | -0.006 |
subs | -0.006 |
scrap | -0.005 |
Token | ot |
Token ID | 30972 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
azes | +0.018 |
ires | +0.016 |
mmm | +0.016 |
pit | +0.016 |
ruits | +0.015 |
Neg logit contributions | |
ch | -0.009 |
B | -0.008 |
subs | -0.007 |
ny | -0.007 |
sc | -0.007 |
Token | ter |
Token ID | 353 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
azes | +0.016 |
pit | +0.014 |
castle | +0.013 |
ement | +0.013 |
fridge | +0.013 |
Neg logit contributions | |
sc | -0.021 |
ch | -0.020 |
subs | -0.020 |
B | -0.020 |
text | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
azes | +0.019 |
pit | +0.016 |
isdom | +0.016 |
ement | +0.016 |
oven | +0.015 |
Neg logit contributions | |
sc | -0.016 |
ch | -0.016 |
B | -0.015 |
subs | -0.015 |
ched | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
azes | +0.013 |
pit | +0.011 |
castle | +0.011 |
isdom | +0.010 |
ires | +0.010 |
Neg logit contributions | |
ch | -0.009 |
sc | -0.009 |
B | -0.008 |
subs | -0.008 |
bo | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
B | +0.006 |
sc | +0.005 |
subs | +0.005 |
ch | +0.005 |
Br | +0.005 |
Neg logit contributions | |
azes | -0.007 |
oven | -0.006 |
fridge | -0.006 |
writing | -0.006 |
refrigerator | -0.006 |
Token | hurt |
Token ID | 5938 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
azes | +0.024 |
oven | +0.020 |
writing | +0.020 |
pit | +0.020 |
fridge | +0.020 |
Neg logit contributions | |
sc | -0.015 |
B | -0.014 |
ch | -0.014 |
subs | -0.013 |
fl | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
sc | +0.024 |
ch | +0.023 |
B | +0.023 |
subs | +0.023 |
ched | +0.021 |
Neg logit contributions | |
azes | -0.030 |
pit | -0.025 |
ires | -0.025 |
ement | -0.025 |
mmm | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ch | +0.014 |
sc | +0.014 |
B | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.024 |
pit | -0.020 |
isdom | -0.020 |
mmm | -0.020 |
ires | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
sc | +0.014 |
ch | +0.014 |
B | +0.014 |
subs | +0.014 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.023 |
mmm | -0.022 |
isdom | -0.022 |
ires | -0.022 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
sc | +0.006 |
subs | +0.006 |
fl | +0.006 |
burn | +0.006 |
text | +0.006 |
Neg logit contributions | |
azes | -0.009 |
mmm | -0.007 |
isdom | -0.007 |
ires | -0.007 |
ocolate | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
azes | +0.005 |
pit | +0.004 |
oven | +0.004 |
fridge | +0.004 |
isdom | +0.004 |
Neg logit contributions | |
sc | -0.004 |
B | -0.004 |
ch | -0.004 |
subs | -0.004 |
ched | -0.004 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
azes | +0.012 |
writing | +0.010 |
oven | +0.009 |
fridge | +0.009 |
sing | +0.009 |
Neg logit contributions | |
sc | -0.010 |
B | -0.010 |
ch | -0.010 |
subs | -0.009 |
fl | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
ch | +0.003 |
sc | +0.003 |
B | +0.003 |
subs | +0.003 |
ched | +0.003 |
Neg logit contributions | |
azes | -0.005 |
pit | -0.004 |
isdom | -0.004 |
mmm | -0.004 |
ires | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
ch | +0.006 |
B | +0.006 |
sc | +0.006 |
subs | +0.006 |
bo | +0.006 |
Neg logit contributions | |
azes | -0.011 |
pit | -0.010 |
castle | -0.010 |
isdom | -0.010 |
ement | -0.009 |
Token | runs |
Token ID | 4539 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
azes | +0.003 |
oven | +0.002 |
fridge | +0.002 |
ires | +0.002 |
writing | +0.002 |
Neg logit contributions | |
B | -0.003 |
sc | -0.002 |
subs | -0.002 |
ch | -0.002 |
Br | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
sc | +0.044 |
ch | +0.041 |
subs | +0.041 |
ched | +0.040 |
B | +0.038 |
Neg logit contributions | |
azes | -0.037 |
writing | -0.031 |
fridge | -0.030 |
oven | -0.030 |
university | -0.029 |
Token | fancy |
Token ID | 14996 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
B | +0.033 |
ch | +0.032 |
sc | +0.031 |
subs | +0.030 |
bo | +0.029 |
Neg logit contributions | |
azes | -0.056 |
mmm | -0.048 |
ement | -0.047 |
isdom | -0.047 |
pit | -0.047 |
Token | cabin |
Token ID | 9351 |
Feature activation | -8.83e-03 |
Pos logit contributions | |
B | +0.026 |
ch | +0.025 |
sc | +0.024 |
ny | +0.024 |
subs | +0.024 |
Neg logit contributions | |
azes | -0.024 |
mmm | -0.020 |
ocolate | -0.019 |
ement | -0.018 |
isdom | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
azes | +0.020 |
mmm | +0.018 |
isdom | +0.018 |
pit | +0.017 |
ement | +0.017 |
Neg logit contributions | |
sc | -0.009 |
B | -0.009 |
ch | -0.009 |
subs | -0.008 |
bo | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
sc | +0.018 |
ch | +0.018 |
subs | +0.017 |
B | +0.017 |
ched | +0.017 |
Neg logit contributions | |
azes | -0.023 |
fridge | -0.019 |
oven | -0.019 |
writing | -0.019 |
ires | -0.019 |
Token | woods |
Token ID | 16479 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
azes | +0.011 |
mmm | +0.009 |
isdom | +0.009 |
pit | +0.009 |
ement | +0.009 |
Neg logit contributions | |
B | -0.011 |
ch | -0.011 |
sc | -0.011 |
subs | -0.010 |
bo | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
azes | +0.017 |
mmm | +0.016 |
isdom | +0.015 |
ement | +0.015 |
pit | +0.015 |
Neg logit contributions | |
sc | -0.007 |
B | -0.007 |
ch | -0.007 |
subs | -0.006 |
bo | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
B | +0.015 |
ch | +0.015 |
sc | +0.015 |
Fl | +0.014 |
| | +0.014 |
Neg logit contributions | |
azes | -0.021 |
castle | -0.020 |
pit | -0.019 |
isdom | -0.018 |
Majesty | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
B | +0.020 |
ch | +0.019 |
sc | +0.019 |
subs | +0.019 |
bo | +0.018 |
Neg logit contributions | |
azes | -0.027 |
pit | -0.023 |
mmm | -0.022 |
ement | -0.022 |
isdom | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
sc | +0.015 |
ch | +0.015 |
B | +0.014 |
subs | +0.014 |
bo | +0.013 |
Neg logit contributions | |
azes | -0.016 |
writing | -0.013 |
fridge | -0.013 |
pit | -0.013 |
oven | -0.013 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
B | +0.024 |
ch | +0.023 |
subs | +0.022 |
sc | +0.022 |
scrap | +0.021 |
Neg logit contributions | |
azes | -0.062 |
mmm | -0.053 |
ement | -0.053 |
ires | -0.052 |
ocolate | -0.052 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
azes | +0.044 |
pit | +0.038 |
isdom | +0.037 |
ement | +0.037 |
castle | +0.037 |
Neg logit contributions | |
B | -0.035 |
ch | -0.035 |
sc | -0.035 |
subs | -0.033 |
scrap | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +2.57e-04 |
Pos logit contributions | |
sc | +0.014 |
B | +0.014 |
ch | +0.013 |
subs | +0.013 |
ched | +0.012 |
Neg logit contributions | |
azes | -0.032 |
ires | -0.028 |
isdom | -0.028 |
ement | -0.028 |
pit | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
ch | +0.000 |
B | +0.000 |
sc | +0.000 |
subs | +0.000 |
ched | +0.000 |
Neg logit contributions | |
azes | -0.001 |
pit | -0.000 |
isdom | -0.000 |
mmm | -0.000 |
ires | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
azes | +0.008 |
castle | +0.007 |
isdom | +0.007 |
pit | +0.007 |
mmm | +0.007 |
Neg logit contributions | |
B | -0.006 |
ch | -0.006 |
sc | -0.006 |
subs | -0.005 |
ny | -0.005 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
B | +0.003 |
sc | +0.003 |
ch | +0.003 |
subs | +0.002 |
bo | +0.002 |
Neg logit contributions | |
azes | -0.006 |
pit | -0.005 |
ement | -0.005 |
isdom | -0.005 |
oven | -0.005 |
Token | we |
Token ID | 356 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
azes | +0.037 |
pit | +0.031 |
isdom | +0.031 |
mmm | +0.031 |
ires | +0.031 |
Neg logit contributions | |
ch | -0.027 |
sc | -0.027 |
B | -0.027 |
subs | -0.026 |
bo | -0.024 |
Token | take |
Token ID | 1011 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
azes | +0.106 |
pit | +0.090 |
ement | +0.090 |
isdom | +0.088 |
ires | +0.088 |
Neg logit contributions | |
ch | -0.060 |
B | -0.059 |
sc | -0.058 |
subs | -0.056 |
bo | -0.055 |
Token | some |
Token ID | 617 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
sc | +0.029 |
B | +0.029 |
ch | +0.029 |
subs | +0.029 |
ched | +0.027 |
Neg logit contributions | |
azes | -0.032 |
oven | -0.027 |
isdom | -0.027 |
pit | -0.027 |
mmm | -0.027 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
azes | +0.010 |
pit | +0.008 |
isdom | +0.008 |
ement | +0.008 |
mmm | +0.008 |
Neg logit contributions | |
ch | -0.007 |
sc | -0.007 |
B | -0.007 |
subs | -0.007 |
bo | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
castle | +0.064 |
azes | +0.064 |
pit | +0.063 |
throne | +0.060 |
ement | +0.060 |
Neg logit contributions | |
B | -0.014 |
ch | -0.011 |
s | -0.009 |
L | -0.009 |
Spot | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
sc | +0.002 |
ch | +0.002 |
B | +0.002 |
subs | +0.002 |
ched | +0.002 |
Neg logit contributions | |
azes | -0.003 |
ires | -0.003 |
pit | -0.003 |
mmm | -0.003 |
isdom | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
azes | +0.044 |
castle | +0.041 |
isdom | +0.040 |
ocolate | +0.040 |
sing | +0.040 |
Neg logit contributions | |
B | -0.020 |
sc | -0.019 |
ch | -0.018 |
subs | -0.017 |
ny | -0.017 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
azes | +0.039 |
ires | +0.034 |
pit | +0.034 |
ocolate | +0.034 |
oven | +0.034 |
Neg logit contributions | |
B | -0.017 |
ch | -0.017 |
sc | -0.017 |
subs | -0.017 |
ched | -0.015 |
Token | Annie |
Token ID | 25860 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
azes | +0.050 |
mmm | +0.045 |
castle | +0.044 |
sing | +0.044 |
pit | +0.043 |
Neg logit contributions | |
B | -0.020 |
l | -0.020 |
sc | -0.019 |
ch | -0.018 |
subs | -0.018 |
Token | what |
Token ID | 644 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
azes | +0.019 |
mmm | +0.016 |
ement | +0.016 |
ires | +0.016 |
pit | +0.016 |
Neg logit contributions | |
sc | -0.011 |
ch | -0.011 |
B | -0.010 |
ched | -0.010 |
bo | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
B | +0.006 |
ch | +0.005 |
subs | +0.005 |
sc | +0.005 |
l | +0.005 |
Neg logit contributions | |
azes | -0.013 |
pit | -0.011 |
ires | -0.011 |
mmm | -0.011 |
sing | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
azes | +0.061 |
ocolate | +0.055 |
pit | +0.054 |
oven | +0.054 |
ires | +0.053 |
Neg logit contributions | |
B | -0.016 |
ch | -0.016 |
sc | -0.015 |
subs | -0.015 |
ched | -0.014 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
azes | +0.089 |
pit | +0.079 |
ocolate | +0.078 |
ement | +0.078 |
mmm | +0.078 |
Neg logit contributions | |
fl | -0.070 |
ched | -0.063 |
ch | -0.063 |
hurt | -0.062 |
sc | -0.062 |
Token | under |
Token ID | 739 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
azes | +0.055 |
sing | +0.048 |
pit | +0.046 |
mmm | +0.046 |
oven | +0.046 |
Neg logit contributions | |
sc | -0.020 |
B | -0.018 |
fl | -0.018 |
ched | -0.017 |
on | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
azes | +0.030 |
pit | +0.027 |
castle | +0.026 |
mmm | +0.026 |
ires | +0.026 |
Neg logit contributions | |
B | -0.011 |
ch | -0.010 |
sc | -0.010 |
scrap | -0.010 |
subs | -0.010 |
Token | post |
Token ID | 1281 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
azes | +0.029 |
pit | +0.023 |
ires | +0.023 |
isdom | +0.022 |
mmm | +0.022 |
Neg logit contributions | |
ch | -0.032 |
B | -0.031 |
sc | -0.030 |
subs | -0.030 |
fl | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
azes | +0.043 |
ires | +0.036 |
mmm | +0.036 |
isdom | +0.035 |
ruits | +0.035 |
Neg logit contributions | |
sc | -0.027 |
ch | -0.025 |
bo | -0.024 |
l | -0.024 |
subs | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
ch | +0.008 |
B | +0.008 |
sc | +0.008 |
subs | +0.008 |
ched | +0.008 |
Neg logit contributions | |
azes | -0.009 |
pit | -0.007 |
ires | -0.007 |
isdom | -0.007 |
fridge | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
azes | +0.032 |
pit | +0.026 |
ires | +0.026 |
isdom | +0.026 |
ement | +0.025 |
Neg logit contributions | |
B | -0.027 |
ch | -0.027 |
sc | -0.026 |
subs | -0.025 |
bo | -0.024 |
Token | Of |
Token ID | 5189 |
Feature activation | -3.16e-03 |
Pos logit contributions | |
azes | +0.016 |
mmm | +0.014 |
ires | +0.014 |
patiently | +0.014 |
pit | +0.014 |
Neg logit contributions | |
subs | -0.014 |
ch | -0.014 |
text | -0.014 |
scrap | -0.014 |
sc | -0.014 |
Token | course |
Token ID | 1781 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
ement | +0.002 |
azes | +0.002 |
oven | +0.002 |
mmm | +0.002 |
isdom | +0.001 |
Neg logit contributions | |
sc | -0.008 |
subs | -0.008 |
ch | -0.008 |
ched | -0.008 |
scrap | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
azes | +0.050 |
pit | +0.041 |
mmm | +0.041 |
ement | +0.041 |
isdom | +0.041 |
Neg logit contributions | |
sc | -0.047 |
ch | -0.047 |
B | -0.047 |
subs | -0.045 |
ched | -0.043 |
Token | Thank |
Token ID | 6952 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
azes | +0.040 |
pit | +0.033 |
mmm | +0.032 |
isdom | +0.032 |
ires | +0.032 |
Neg logit contributions | |
B | -0.035 |
sc | -0.035 |
ch | -0.035 |
subs | -0.034 |
ched | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
azes | +0.059 |
mmm | +0.051 |
ocolate | +0.047 |
isdom | +0.046 |
ummy | +0.046 |
Neg logit contributions | |
sc | -0.084 |
subs | -0.084 |
scrap | -0.082 |
ch | -0.081 |
ched | -0.079 |
Token | for |
Token ID | 329 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
azes | +0.016 |
pit | +0.013 |
ires | +0.012 |
isdom | +0.012 |
ement | +0.012 |
Neg logit contributions | |
ch | -0.014 |
sc | -0.013 |
B | -0.013 |
subs | -0.012 |
text | -0.012 |
Token | offering |
Token ID | 6011 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
azes | +0.022 |
pit | +0.019 |
ement | +0.018 |
ires | +0.018 |
castle | +0.017 |
Neg logit contributions | |
B | -0.026 |
ch | -0.025 |
sc | -0.025 |
subs | -0.024 |
ched | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -8.05e-03 |
Pos logit contributions | |
azes | +0.063 |
pit | +0.055 |
castle | +0.052 |
sing | +0.052 |
ement | +0.050 |
Neg logit contributions | |
ch | -0.037 |
sc | -0.036 |
B | -0.036 |
ched | -0.032 |
text | -0.031 |
Token | help |
Token ID | 1037 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
azes | +0.017 |
pit | +0.014 |
ement | +0.014 |
ires | +0.014 |
castle | +0.014 |
Neg logit contributions | |
ch | -0.011 |
B | -0.011 |
sc | -0.010 |
subs | -0.010 |
bo | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
azes | +0.018 |
isdom | +0.015 |
mmm | +0.015 |
ires | +0.015 |
ement | +0.015 |
Neg logit contributions | |
ch | -0.014 |
sc | -0.014 |
B | -0.014 |
subs | -0.013 |
scrap | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
azes | +0.026 |
isdom | +0.023 |
pit | +0.022 |
ement | +0.022 |
mmm | +0.022 |
Neg logit contributions | |
ch | -0.015 |
B | -0.014 |
sc | -0.014 |
subs | -0.014 |
scrap | -0.013 |
Token | cannot |
Token ID | 2314 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
azes | +0.009 |
mmm | +0.008 |
isdom | +0.008 |
pit | +0.008 |
ocolate | +0.008 |
Neg logit contributions | |
ch | -0.006 |
sc | -0.006 |
ched | -0.006 |
scrap | -0.006 |
bo | -0.006 |
Token | grab |
Token ID | 5552 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
ch | +0.011 |
B | +0.011 |
sc | +0.010 |
bo | +0.010 |
subs | +0.010 |
Neg logit contributions | |
azes | -0.019 |
pit | -0.017 |
ement | -0.016 |
isdom | -0.016 |
oven | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
azes | +0.014 |
pit | +0.012 |
ires | +0.012 |
ement | +0.012 |
oven | +0.012 |
Neg logit contributions | |
sc | -0.010 |
ch | -0.010 |
B | -0.010 |
subs | -0.010 |
ched | -0.009 |
Token | o |
Token ID | 267 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
azes | +0.018 |
pit | +0.015 |
isdom | +0.015 |
mmm | +0.015 |
ires | +0.015 |
Neg logit contributions | |
ch | -0.016 |
sc | -0.016 |
B | -0.016 |
subs | -0.015 |
bo | -0.014 |
Token | at |
Token ID | 265 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
azes | +0.061 |
pit | +0.047 |
isdom | +0.046 |
mmm | +0.046 |
ires | +0.046 |
Neg logit contributions | |
ch | -0.087 |
sc | -0.087 |
B | -0.087 |
subs | -0.084 |
bo | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
azes | +0.022 |
pit | +0.019 |
oven | +0.019 |
mmm | +0.019 |
ement | +0.018 |
Neg logit contributions | |
ch | -0.014 |
B | -0.014 |
sc | -0.014 |
subs | -0.013 |
ched | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
B | +0.009 |
ch | +0.009 |
sc | +0.009 |
subs | +0.008 |
bo | +0.008 |
Neg logit contributions | |
azes | -0.016 |
castle | -0.014 |
pit | -0.014 |
isdom | -0.014 |
ement | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
sc | +0.015 |
ch | +0.015 |
B | +0.015 |
subs | +0.015 |
ched | +0.013 |
Neg logit contributions | |
azes | -0.026 |
pit | -0.022 |
mmm | -0.022 |
ires | -0.022 |
isdom | -0.022 |
Token | Tom |
Token ID | 13787 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
sc | +0.010 |
subs | +0.010 |
ch | +0.010 |
B | +0.010 |
fl | +0.010 |
Neg logit contributions | |
azes | -0.012 |
mmm | -0.010 |
pit | -0.010 |
ires | -0.010 |
ae | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -7.21e-04 |
Pos logit contributions | |
azes | +0.092 |
mmm | +0.084 |
isdom | +0.083 |
ement | +0.080 |
pit | +0.080 |
Neg logit contributions | |
ch | -0.042 |
B | -0.041 |
sc | -0.037 |
fl | -0.036 |
scrap | -0.035 |
Token | big |
Token ID | 1263 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
azes | +0.002 |
isdom | +0.002 |
mmm | +0.002 |
ires | +0.001 |
ement | +0.001 |
Neg logit contributions | |
ch | -0.001 |
B | -0.001 |
sc | -0.001 |
subs | -0.001 |
scrap | -0.001 |
Token | board |
Token ID | 3096 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
azes | +0.041 |
isdom | +0.036 |
ires | +0.035 |
mmm | +0.034 |
idge | +0.034 |
Neg logit contributions | |
ch | -0.024 |
sc | -0.021 |
st | -0.020 |
B | -0.020 |
k | -0.019 |
Token | at |
Token ID | 379 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
azes | +0.053 |
isdom | +0.048 |
mmm | +0.047 |
Majesty | +0.046 |
ires | +0.045 |
Neg logit contributions | |
sc | -0.029 |
ch | -0.028 |
B | -0.025 |
subs | -0.024 |
ny | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
azes | +0.071 |
isdom | +0.064 |
mmm | +0.064 |
ement | +0.064 |
pit | +0.062 |
Neg logit contributions | |
ch | -0.016 |
B | -0.016 |
sc | -0.016 |
subs | -0.013 |
fl | -0.013 |
Token | edge |
Token ID | 5743 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
azes | +0.039 |
isdom | +0.033 |
mmm | +0.032 |
ement | +0.031 |
pit | +0.031 |
Neg logit contributions | |
ch | -0.040 |
sc | -0.040 |
B | -0.039 |
subs | -0.037 |
bo | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
azes | +0.115 |
isdom | +0.102 |
mmm | +0.101 |
ement | +0.098 |
Majesty | +0.098 |
Neg logit contributions | |
ch | -0.053 |
sc | -0.052 |
B | -0.050 |
subs | -0.046 |
bo | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
B | +0.006 |
ch | +0.006 |
sc | +0.005 |
Fl | +0.004 |
subs | +0.004 |
Neg logit contributions | |
azes | -0.026 |
isdom | -0.023 |
mmm | -0.023 |
ement | -0.023 |
sing | -0.022 |
Token | pool |
Token ID | 5933 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
azes | +0.024 |
pit | +0.019 |
oven | +0.019 |
fridge | +0.019 |
ires | +0.019 |
Neg logit contributions | |
B | -0.034 |
ch | -0.034 |
sc | -0.034 |
subs | -0.034 |
ched | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +6.77e-04 |
Pos logit contributions | |
azes | +0.070 |
isdom | +0.066 |
mmm | +0.063 |
Majesty | +0.062 |
ement | +0.060 |
Neg logit contributions | |
sc | -0.022 |
ch | -0.018 |
ny | -0.017 |
B | -0.016 |
s | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
ch | +0.001 |
B | +0.001 |
sc | +0.001 |
subs | +0.001 |
fl | +0.001 |
Neg logit contributions | |
azes | -0.001 |
isdom | -0.001 |
castle | -0.001 |
ement | -0.001 |
writing | -0.001 |