Token | be |
Token ID | 307 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
disl | +0.010 |
ados | +0.009 |
Mickey | +0.009 |
array | +0.009 |
avocado | +0.009 |
Neg logit contributions | |
a | -0.013 |
- | -0.011 |
ah | -0.011 |
be | -0.011 |
ch | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
a | +0.086 |
ah | +0.081 |
be | +0.074 |
fly | +0.072 |
iest | +0.068 |
Neg logit contributions | |
disl | -0.087 |
ados | -0.079 |
Mickey | -0.078 |
vitamins | -0.075 |
court | -0.074 |
Token | driver |
Token ID | 4639 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
avocado | +0.006 |
disl | +0.006 |
vitamins | +0.006 |
ados | +0.006 |
Mickey | +0.006 |
Neg logit contributions | |
a | -0.006 |
- | -0.005 |
be | -0.005 |
ah | -0.005 |
y | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
a | +0.207 |
ah | +0.172 |
web | +0.171 |
iest | +0.171 |
ch | +0.169 |
Neg logit contributions | |
avocado | -0.241 |
court | -0.236 |
ados | -0.236 |
disl | -0.227 |
Mickey | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
a | +0.001 |
- | +0.001 |
ah | +0.001 |
be | +0.001 |
ch | +0.001 |
Neg logit contributions | |
disl | -0.001 |
ados | -0.001 |
vitamins | -0.001 |
Mickey | -0.001 |
array | -0.001 |
Token | passenger |
Token ID | 11849 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
disl | +0.008 |
avocado | +0.008 |
ados | +0.008 |
vitamins | +0.007 |
Mickey | +0.007 |
Neg logit contributions | |
a | -0.007 |
- | -0.006 |
ah | -0.006 |
be | -0.006 |
y | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
a | +0.479 |
ch | +0.416 |
less | +0.412 |
ah | +0.391 |
web | +0.383 |
Neg logit contributions | |
disl | -0.501 |
court | -0.498 |
ados | -0.468 |
avocado | -0.457 |
yard | -0.451 |
Token | They |
Token ID | 1119 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
a | +0.004 |
ah | +0.003 |
- | +0.003 |
be | +0.003 |
ch | +0.003 |
Neg logit contributions | |
ados | -0.003 |
disl | -0.003 |
array | -0.003 |
vitamins | -0.003 |
avocado | -0.003 |
Token | say |
Token ID | 910 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
disl | +0.063 |
ados | +0.059 |
vitamins | +0.058 |
Mickey | +0.057 |
array | +0.057 |
Neg logit contributions | |
a | -0.068 |
- | -0.061 |
be | -0.058 |
ah | -0.058 |
ch | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
a | +0.099 |
ah | +0.085 |
be | +0.081 |
- | +0.081 |
fly | +0.079 |
Neg logit contributions | |
disl | -0.104 |
ados | -0.101 |
vitamins | -0.095 |
avocado | -0.095 |
Mickey | -0.094 |
Token | " |
Token ID | 366 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
disl | +0.022 |
ados | +0.020 |
Mickey | +0.019 |
avocado | +0.019 |
Bruce | +0.019 |
Neg logit contributions | |
a | -0.033 |
ah | -0.029 |
- | -0.029 |
be | -0.028 |
iest | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
a | +0.074 |
ah | +0.060 |
- | +0.059 |
be | +0.059 |
fly | +0.053 |
Neg logit contributions | |
disl | -0.130 |
ados | -0.130 |
Mickey | -0.127 |
array | -0.126 |
vitamins | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
disl | +0.018 |
ados | +0.017 |
Mickey | +0.016 |
vitamins | +0.016 |
array | +0.016 |
Neg logit contributions | |
a | -0.026 |
- | -0.023 |
be | -0.022 |
ah | -0.022 |
ch | -0.021 |
Token | group |
Token ID | 1448 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
a | +0.020 |
be | +0.018 |
ah | +0.018 |
- | +0.017 |
ist | +0.017 |
Neg logit contributions | |
avocado | -0.021 |
Mickey | -0.021 |
disl | -0.020 |
av | -0.020 |
court | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
a | +0.039 |
ah | +0.033 |
z | +0.029 |
fly | +0.029 |
be | +0.027 |
Neg logit contributions | |
court | -0.092 |
Mickey | -0.089 |
Bruce | -0.088 |
ados | -0.086 |
array | -0.086 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
a | +0.138 |
- | +0.121 |
ah | +0.119 |
be | +0.117 |
ch | +0.108 |
Neg logit contributions | |
disl | -0.131 |
ados | -0.127 |
vitamins | -0.123 |
Mickey | -0.120 |
array | -0.120 |
Token | chie |
Token ID | 3043 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
ados | +0.045 |
disl | +0.044 |
array | +0.043 |
av | +0.042 |
avocado | +0.042 |
Neg logit contributions | |
a | -0.017 |
ah | -0.014 |
- | -0.014 |
ch | -0.012 |
fly | -0.012 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
a | +0.471 |
closer | +0.424 |
less | +0.417 |
fly | +0.414 |
- | +0.412 |
Neg logit contributions | |
disl | -0.499 |
array | -0.441 |
ados | -0.430 |
vitamins | -0.426 |
avocado | -0.423 |
Token | mice |
Token ID | 10693 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
a | +0.192 |
- | +0.165 |
ah | +0.163 |
be | +0.162 |
ch | +0.151 |
Neg logit contributions | |
disl | -0.173 |
ados | -0.169 |
vitamins | -0.161 |
array | -0.160 |
Mickey | -0.158 |
Token | came |
Token ID | 1625 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
disl | +0.142 |
ados | +0.138 |
vitamins | +0.134 |
Mickey | +0.133 |
array | +0.133 |
Neg logit contributions | |
a | -0.094 |
- | -0.079 |
ah | -0.077 |
be | -0.076 |
ch | -0.070 |
Token | by |
Token ID | 416 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
a | +0.087 |
ah | +0.076 |
be | +0.071 |
- | +0.068 |
iest | +0.065 |
Neg logit contributions | |
disl | -0.134 |
ados | -0.131 |
Mickey | -0.130 |
Bruce | -0.126 |
array | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
disl | +0.214 |
ados | +0.206 |
array | +0.199 |
vitamins | +0.199 |
Mickey | +0.197 |
Neg logit contributions | |
a | -0.149 |
- | -0.125 |
ah | -0.123 |
be | -0.121 |
ch | -0.111 |
Token | buck |
Token ID | 10230 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
a | +0.035 |
less | +0.031 |
ah | +0.030 |
- | +0.030 |
ch | +0.029 |
Neg logit contributions | |
disl | -0.044 |
array | -0.043 |
Mickey | -0.042 |
avocado | -0.041 |
ados | -0.041 |
Token | led |
Token ID | 992 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
a | +0.087 |
be | +0.074 |
- | +0.074 |
ah | +0.073 |
ch | +0.070 |
Neg logit contributions | |
disl | -0.086 |
ados | -0.085 |
array | -0.081 |
vitamins | -0.080 |
Mickey | -0.079 |
Token | up |
Token ID | 510 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ados | +0.005 |
disl | +0.004 |
vitamins | +0.004 |
Mickey | +0.004 |
avocado | +0.004 |
Neg logit contributions | |
a | -0.006 |
be | -0.005 |
ah | -0.005 |
- | -0.005 |
fly | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
ados | +0.203 |
avocado | +0.202 |
av | +0.200 |
Mickey | +0.194 |
Bruce | +0.194 |
Neg logit contributions | |
a | -0.188 |
be | -0.171 |
ch | -0.156 |
ah | -0.153 |
fly | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
disl | +0.004 |
vitamins | +0.004 |
array | +0.004 |
ados | +0.004 |
avocado | +0.004 |
Neg logit contributions | |
a | -0.006 |
fly | -0.005 |
ah | -0.005 |
be | -0.005 |
- | -0.005 |
Token | passenger |
Token ID | 11849 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
avocado | +0.011 |
disl | +0.011 |
array | +0.010 |
ados | +0.010 |
vitamins | +0.010 |
Neg logit contributions | |
a | -0.014 |
- | -0.011 |
ah | -0.011 |
be | -0.011 |
as | -0.011 |
Token | seat |
Token ID | 5852 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
a | +0.496 |
ch | +0.447 |
less | +0.446 |
fly | +0.431 |
web | +0.422 |
Neg logit contributions | |
court | -0.439 |
yard | -0.426 |
Her | -0.420 |
avocado | -0.420 |
array | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
a | +0.132 |
ch | +0.120 |
fly | +0.113 |
be | +0.112 |
ah | +0.108 |
Neg logit contributions | |
ados | -0.142 |
yard | -0.139 |
court | -0.138 |
avocado | -0.135 |
herself | -0.134 |
Token | They |
Token ID | 1119 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
a | +0.007 |
of | +0.007 |
- | +0.006 |
ch | +0.005 |
y | +0.005 |
Neg logit contributions | |
ados | -0.018 |
disl | -0.018 |
vitamins | -0.018 |
av | -0.017 |
avocado | -0.017 |
Token | drove |
Token ID | 10357 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Mickey | +0.041 |
disl | +0.040 |
array | +0.039 |
Bruce | +0.039 |
court | +0.038 |
Neg logit contributions | |
a | -0.054 |
- | -0.049 |
less | -0.048 |
fly | -0.046 |
ah | -0.045 |
Token | along |
Token ID | 1863 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
a | +0.204 |
fly | +0.195 |
ah | +0.173 |
web | +0.173 |
rot | +0.169 |
Neg logit contributions | |
Jack | -0.146 |
Jerry | -0.141 |
Bruce | -0.140 |
ados | -0.139 |
Mickey | -0.138 |
Token | was |
Token ID | 373 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
a | +0.017 |
less | +0.015 |
ah | +0.015 |
be | +0.014 |
- | +0.014 |
Neg logit contributions | |
disl | -0.020 |
vitamins | -0.019 |
array | -0.019 |
ados | -0.019 |
court | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
disl | +0.028 |
Mickey | +0.026 |
ados | +0.026 |
vitamins | +0.025 |
court | +0.025 |
Neg logit contributions | |
a | -0.033 |
ah | -0.031 |
be | -0.029 |
- | -0.028 |
y | -0.027 |
Token | driver |
Token ID | 4639 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
vitamins | +0.014 |
court | +0.014 |
disl | +0.014 |
Mickey | +0.013 |
array | +0.013 |
Neg logit contributions | |
a | -0.015 |
- | -0.014 |
ry | -0.013 |
less | -0.013 |
y | -0.013 |
Token | or |
Token ID | 393 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
a | +0.182 |
less | +0.151 |
closer | +0.147 |
be | +0.147 |
ah | +0.146 |
Neg logit contributions | |
avocado | -0.222 |
ados | -0.215 |
Mickey | -0.214 |
court | -0.204 |
disl | -0.203 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
disl | +0.099 |
ados | +0.096 |
vitamins | +0.093 |
array | +0.092 |
Mickey | +0.091 |
Neg logit contributions | |
a | -0.080 |
- | -0.069 |
ah | -0.066 |
be | -0.066 |
ch | -0.061 |
Token | passenger |
Token ID | 11849 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
disl | +0.018 |
vitamins | +0.017 |
court | +0.017 |
array | +0.017 |
Mickey | +0.016 |
Neg logit contributions | |
a | -0.018 |
- | -0.016 |
ah | -0.015 |
y | -0.015 |
be | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
a | +0.508 |
less | +0.433 |
ch | +0.405 |
web | +0.399 |
ah | +0.396 |
Neg logit contributions | |
court | -0.442 |
disl | -0.429 |
Everyone | -0.406 |
sidewalk | -0.402 |
yard | -0.397 |
Token |
|
Token ID | 198 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
a | +0.005 |
be | +0.004 |
ah | +0.004 |
ch | +0.004 |
- | +0.004 |
Neg logit contributions | |
disl | -0.004 |
ados | -0.004 |
vitamins | -0.004 |
array | -0.004 |
avocado | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ados | +0.050 |
disl | +0.050 |
vitamins | +0.047 |
array | +0.046 |
avocado | +0.046 |
Neg logit contributions | |
a | -0.044 |
- | -0.037 |
be | -0.036 |
ah | -0.035 |
ch | -0.034 |
Token | One |
Token ID | 3198 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
disl | +0.050 |
ados | +0.049 |
vitamins | +0.047 |
Mickey | +0.046 |
array | +0.046 |
Neg logit contributions | |
a | -0.038 |
- | -0.031 |
be | -0.030 |
ah | -0.030 |
ch | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
fly | +0.058 |
king | +0.056 |
cher | +0.056 |
rot | +0.055 |
flake | +0.052 |
Neg logit contributions | |
Every | -0.013 |
Everyone | -0.012 |
One | -0.011 |
Sundays | -0.011 |
disl | -0.010 |
Token | One |
Token ID | 3198 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
disl | +0.019 |
array | +0.018 |
vitamins | +0.017 |
ados | +0.017 |
Mickey | +0.017 |
Neg logit contributions | |
a | -0.023 |
- | -0.021 |
ah | -0.020 |
be | -0.020 |
less | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
cher | +0.059 |
fly | +0.056 |
king | +0.055 |
ist | +0.055 |
chers | +0.055 |
Neg logit contributions | |
Every | -0.014 |
Billy | -0.013 |
Everyone | -0.013 |
disl | -0.012 |
avocado | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
a | +0.049 |
be | +0.041 |
ah | +0.041 |
fly | +0.038 |
- | +0.037 |
Neg logit contributions | |
ados | -0.063 |
Mickey | -0.062 |
disl | -0.061 |
avocado | -0.060 |
Bruce | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Mickey | +0.020 |
ados | +0.019 |
avocado | +0.018 |
Bruce | +0.018 |
av | +0.018 |
Neg logit contributions | |
a | -0.023 |
ah | -0.021 |
be | -0.021 |
- | -0.020 |
fly | -0.019 |
Token | new |
Token ID | 649 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
a | +0.042 |
z | +0.041 |
ah | +0.040 |
ac | +0.040 |
ist | +0.040 |
Neg logit contributions | |
Mickey | -0.032 |
courtroom | -0.029 |
court | -0.029 |
avocado | -0.029 |
Bruce | -0.029 |
Token | passenger |
Token ID | 11849 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
disl | +0.023 |
court | +0.023 |
sidewalk | +0.022 |
courtroom | +0.022 |
squash | +0.021 |
Neg logit contributions | |
a | -0.024 |
less | -0.022 |
pr | -0.022 |
as | -0.022 |
light | -0.022 |
Token | climbed |
Token ID | 19952 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
a | +0.496 |
less | +0.470 |
ch | +0.417 |
as | +0.405 |
closer | +0.399 |
Neg logit contributions | |
court | -0.425 |
disl | -0.404 |
array | -0.404 |
courtroom | -0.396 |
yard | -0.386 |
Token | aboard |
Token ID | 15500 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
a | +0.004 |
be | +0.003 |
as | +0.003 |
less | +0.003 |
ah | +0.003 |
Neg logit contributions | |
ados | -0.003 |
av | -0.003 |
Bruce | -0.003 |
Mickey | -0.003 |
array | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
a | +0.075 |
be | +0.068 |
ah | +0.063 |
ch | +0.062 |
- | +0.060 |
Neg logit contributions | |
court | -0.081 |
Bruce | -0.081 |
Mickey | -0.081 |
avocado | -0.079 |
ados | -0.079 |
Token | They |
Token ID | 1119 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
a | +0.017 |
- | +0.016 |
ch | +0.016 |
ah | +0.015 |
of | +0.015 |
Neg logit contributions | |
disl | -0.014 |
ados | -0.012 |
vitamins | -0.012 |
array | -0.012 |
avocado | -0.011 |
Token | introduced |
Token ID | 5495 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
disl | +0.047 |
Mickey | +0.046 |
ados | +0.046 |
array | +0.046 |
Bruce | +0.045 |
Neg logit contributions | |
a | -0.048 |
- | -0.042 |
ah | -0.040 |
be | -0.040 |
less | -0.039 |
Token | know |
Token ID | 760 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
a | +0.044 |
- | +0.039 |
be | +0.037 |
ah | +0.037 |
ch | +0.035 |
Neg logit contributions | |
disl | -0.041 |
ados | -0.039 |
vitamins | -0.038 |
Mickey | -0.037 |
array | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
a | +0.041 |
ah | +0.036 |
be | +0.035 |
- | +0.035 |
ch | +0.033 |
Neg logit contributions | |
disl | -0.044 |
ados | -0.042 |
vitamins | -0.041 |
Mickey | -0.040 |
avocado | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
a | +0.003 |
- | +0.002 |
ah | +0.002 |
be | +0.002 |
ch | +0.002 |
Neg logit contributions | |
disl | -0.003 |
ados | -0.003 |
vitamins | -0.003 |
Mickey | -0.003 |
array | -0.003 |
Token | friendly |
Token ID | 8030 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
disl | +0.007 |
vitamins | +0.006 |
court | +0.006 |
sidewalk | +0.006 |
courtroom | +0.006 |
Neg logit contributions | |
a | -0.008 |
ah | -0.008 |
y | -0.008 |
fly | -0.008 |
light | -0.007 |
Token | new |
Token ID | 649 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
a | +0.016 |
ah | +0.014 |
fly | +0.014 |
light | +0.013 |
pr | +0.013 |
Neg logit contributions | |
disl | -0.017 |
court | -0.016 |
courtroom | -0.016 |
Everyone | -0.015 |
vitamins | -0.015 |
Token | passenger |
Token ID | 11849 |
Feature activation | +8.01e+00 |
Pos logit contributions | |
disl | +0.027 |
court | +0.025 |
vitamins | +0.024 |
Everyone | +0.023 |
courtroom | +0.023 |
Neg logit contributions | |
a | -0.024 |
fly | -0.023 |
light | -0.022 |
ah | -0.022 |
less | -0.022 |
Token | would |
Token ID | 561 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
a | +0.445 |
less | +0.395 |
ch | +0.391 |
be | +0.371 |
ah | +0.370 |
Neg logit contributions | |
disl | -0.509 |
Mickey | -0.457 |
ados | -0.457 |
vitamins | -0.456 |
avocado | -0.456 |
Token | change |
Token ID | 1487 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
a | +0.144 |
- | +0.124 |
ah | +0.118 |
be | +0.118 |
ch | +0.110 |
Neg logit contributions | |
disl | -0.171 |
ados | -0.161 |
vitamins | -0.159 |
Mickey | -0.158 |
array | -0.156 |
Token | their |
Token ID | 511 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
a | +0.151 |
ah | +0.139 |
be | +0.136 |
ch | +0.127 |
- | +0.124 |
Neg logit contributions | |
disl | -0.173 |
ados | -0.160 |
vitamins | -0.160 |
Mickey | -0.156 |
avocado | -0.154 |
Token | lives |
Token ID | 3160 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
a | +0.107 |
ah | +0.097 |
be | +0.091 |
- | +0.089 |
ch | +0.089 |
Neg logit contributions | |
disl | -0.069 |
vitamins | -0.063 |
ados | -0.060 |
array | -0.058 |
avocado | -0.057 |
Token | forever |
Token ID | 8097 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ah | +0.004 |
a | +0.003 |
ch | +0.003 |
be | +0.003 |
fly | +0.003 |
Neg logit contributions | |
court | -0.005 |
disl | -0.005 |
av | -0.005 |
vitamins | -0.004 |
avocado | -0.004 |
Token | For |
Token ID | 1114 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
a | +0.028 |
- | +0.025 |
be | +0.025 |
ch | +0.024 |
ah | +0.024 |
Neg logit contributions | |
disl | -0.019 |
ados | -0.018 |
vitamins | -0.017 |
array | -0.017 |
avocado | -0.016 |
Token | hidden |
Token ID | 7104 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
a | +0.051 |
ah | +0.043 |
- | +0.043 |
be | +0.042 |
less | +0.041 |
Neg logit contributions | |
disl | -0.049 |
vitamins | -0.046 |
ados | -0.046 |
Mickey | -0.045 |
Bruce | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
disl | +0.055 |
ados | +0.053 |
vitamins | +0.052 |
Mickey | +0.048 |
Bruce | +0.048 |
Neg logit contributions | |
a | -0.075 |
be | -0.071 |
ah | -0.069 |
ch | -0.064 |
less | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
a | +0.004 |
ah | +0.003 |
be | +0.003 |
- | +0.003 |
ch | +0.003 |
Neg logit contributions | |
disl | -0.003 |
vitamins | -0.003 |
Mickey | -0.003 |
court | -0.003 |
array | -0.003 |
Token | friendly |
Token ID | 8030 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
array | +0.006 |
disl | +0.006 |
vitamins | +0.006 |
court | +0.006 |
courtroom | +0.005 |
Neg logit contributions | |
a | -0.009 |
fly | -0.008 |
ah | -0.007 |
- | -0.007 |
ba | -0.007 |
Token | passenger |
Token ID | 11849 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
a | +0.018 |
ah | +0.015 |
fly | +0.015 |
ba | +0.014 |
vy | +0.014 |
Neg logit contributions | |
disl | -0.015 |
array | -0.014 |
court | -0.014 |
vitamins | -0.014 |
courtroom | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
a | +0.444 |
ch | +0.391 |
less | +0.391 |
ah | +0.386 |
be | +0.359 |
Neg logit contributions | |
disl | -0.502 |
court | -0.489 |
ados | -0.471 |
Mickey | -0.471 |
array | -0.465 |
Token | pocket |
Token ID | 10000 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
disl | +0.043 |
vitamins | +0.039 |
ados | +0.038 |
court | +0.037 |
array | +0.037 |
Neg logit contributions | |
a | -0.053 |
ah | -0.048 |
ch | -0.044 |
ba | -0.043 |
be | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
disl | +0.196 |
ados | +0.192 |
Mickey | +0.189 |
vitamins | +0.189 |
avocado | +0.186 |
Neg logit contributions | |
a | -0.133 |
ah | -0.120 |
be | -0.114 |
ch | -0.107 |
- | -0.101 |
Token | something |
Token ID | 1223 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
disl | +0.020 |
Mickey | +0.020 |
vitamins | +0.019 |
Bruce | +0.019 |
avocado | +0.019 |
Neg logit contributions | |
a | -0.019 |
ah | -0.017 |
be | -0.016 |
- | -0.016 |
ch | -0.015 |
Token | magical |
Token ID | 10883 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
disl | +0.066 |
vitamins | +0.063 |
avocado | +0.061 |
Mickey | +0.060 |
Bruce | +0.060 |
Neg logit contributions | |
a | -0.071 |
ah | -0.066 |
be | -0.065 |
- | -0.058 |
z | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
disl | +0.011 |
ados | +0.010 |
vitamins | +0.010 |
array | +0.010 |
Mickey | +0.010 |
Neg logit contributions | |
a | -0.012 |
- | -0.010 |
ah | -0.010 |
be | -0.010 |
ch | -0.009 |
Token | When |
Token ID | 2215 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
disl | +0.012 |
Mickey | +0.011 |
array | +0.011 |
ados | +0.011 |
vitamins | +0.011 |
Neg logit contributions | |
a | -0.010 |
- | -0.009 |
ah | -0.009 |
be | -0.009 |
less | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
Mickey | +0.014 |
ados | +0.013 |
Bruce | +0.013 |
disl | +0.013 |
avocado | +0.013 |
Neg logit contributions | |
a | -0.018 |
ah | -0.015 |
- | -0.015 |
be | -0.014 |
as | -0.014 |
Token | friendly |
Token ID | 8030 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
disl | +0.005 |
court | +0.005 |
sidewalk | +0.005 |
Mickey | +0.005 |
vitamins | +0.005 |
Neg logit contributions | |
a | -0.006 |
fly | -0.005 |
y | -0.005 |
less | -0.005 |
ah | -0.005 |
Token | new |
Token ID | 649 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
a | +0.016 |
ah | +0.013 |
pr | +0.013 |
less | +0.013 |
vy | +0.012 |
Neg logit contributions | |
disl | -0.017 |
Mickey | -0.016 |
court | -0.016 |
Everyone | -0.016 |
sidewalk | -0.016 |
Token | passenger |
Token ID | 11849 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
disl | +0.025 |
court | +0.025 |
Everyone | +0.024 |
requests | +0.024 |
vitamins | +0.024 |
Neg logit contributions | |
a | -0.024 |
less | -0.021 |
fly | -0.021 |
ifying | -0.021 |
ah | -0.019 |
Token | placed |
Token ID | 4624 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
a | +0.475 |
less | +0.445 |
ch | +0.408 |
be | +0.383 |
closer | +0.382 |
Neg logit contributions | |
disl | -0.445 |
Mickey | -0.435 |
court | -0.426 |
From | -0.422 |
array | -0.421 |
Token | the |
Token ID | 262 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
a | +0.047 |
be | +0.042 |
ah | +0.040 |
- | +0.039 |
ch | +0.036 |
Neg logit contributions | |
ados | -0.044 |
Mickey | -0.042 |
disl | -0.041 |
Bruce | -0.041 |
avocado | -0.040 |
Token | conductor |
Token ID | 39206 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
vitamins | +0.005 |
disl | +0.005 |
court | +0.004 |
avocado | +0.004 |
mischief | +0.004 |
Neg logit contributions | |
a | -0.005 |
fly | -0.005 |
y | -0.005 |
ah | -0.005 |
ist | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
a | +0.204 |
ah | +0.185 |
less | +0.173 |
ch | +0.165 |
be | +0.160 |
Neg logit contributions | |
Mickey | -0.225 |
avocado | -0.222 |
av | -0.221 |
ados | -0.220 |
disl | -0.220 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
vitamins | +0.045 |
disl | +0.045 |
avocado | +0.042 |
ados | +0.042 |
court | +0.041 |
Neg logit contributions | |
a | -0.044 |
ah | -0.040 |
be | -0.038 |
y | -0.038 |
fly | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
disl | +0.004 |
ados | +0.004 |
Mickey | +0.004 |
vitamins | +0.004 |
array | +0.004 |
Neg logit contributions | |
a | -0.006 |
- | -0.006 |
be | -0.006 |
ah | -0.006 |
ch | -0.005 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
disl | +0.002 |
ados | +0.002 |
array | +0.001 |
vitamins | +0.001 |
Mickey | +0.001 |
Neg logit contributions | |
a | -0.001 |
- | -0.001 |
be | -0.001 |
ah | -0.001 |
ch | -0.001 |
Token | got |
Token ID | 1392 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
a | +0.013 |
ah | +0.011 |
be | +0.011 |
- | +0.011 |
less | +0.010 |
Neg logit contributions | |
disl | -0.015 |
Mickey | -0.015 |
ados | -0.015 |
array | -0.014 |
avocado | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
disl | +0.024 |
ados | +0.023 |
array | +0.023 |
vitamins | +0.023 |
Mickey | +0.021 |
Neg logit contributions | |
a | -0.016 |
- | -0.014 |
be | -0.013 |
ah | -0.013 |
closer | -0.012 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
a | +0.045 |
be | +0.039 |
ah | +0.039 |
as | +0.038 |
iest | +0.038 |
Neg logit contributions | |
avocado | -0.037 |
Mickey | -0.036 |
disl | -0.035 |
av | -0.035 |
court | -0.034 |
Token | chie |
Token ID | 3043 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
ados | +0.043 |
disl | +0.043 |
array | +0.041 |
avocado | +0.041 |
av | +0.041 |
Neg logit contributions | |
a | -0.017 |
- | -0.014 |
ah | -0.014 |
ch | -0.012 |
fly | -0.011 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
a | +0.541 |
fly | +0.482 |
steering | +0.479 |
less | +0.478 |
be | +0.467 |
Neg logit contributions | |
disl | -0.424 |
avocado | -0.353 |
array | -0.353 |
vitamins | -0.347 |
ados | -0.344 |
Token | look |
Token ID | 804 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
a | +0.182 |
be | +0.148 |
ah | +0.143 |
- | +0.142 |
as | +0.136 |
Neg logit contributions | |
disl | -0.187 |
ados | -0.180 |
avocado | -0.178 |
vitamins | -0.174 |
Mickey | -0.173 |
Token | in |
Token ID | 287 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
a | +0.090 |
be | +0.076 |
ah | +0.075 |
fly | +0.073 |
passenger | +0.066 |
Neg logit contributions | |
disl | -0.129 |
ados | -0.128 |
avocado | -0.127 |
av | -0.123 |
vitamins | -0.122 |
Token | its |
Token ID | 663 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
disl | +0.014 |
ados | +0.013 |
vitamins | +0.013 |
array | +0.013 |
Mickey | +0.013 |
Neg logit contributions | |
a | -0.012 |
- | -0.010 |
ah | -0.010 |
be | -0.009 |
ch | -0.009 |
Token | eye |
Token ID | 4151 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
a | +0.058 |
- | +0.049 |
be | +0.049 |
ah | +0.049 |
ch | +0.045 |
Neg logit contributions | |
disl | -0.056 |
ados | -0.054 |
vitamins | -0.051 |
Mickey | -0.051 |
array | -0.051 |
Token | so |
Token ID | 523 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
a | +0.036 |
ah | +0.031 |
be | +0.030 |
fly | +0.027 |
ch | +0.027 |
Neg logit contributions | |
ados | -0.050 |
disl | -0.049 |
Mickey | -0.049 |
avocado | -0.048 |
Bruce | -0.048 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
disl | +0.098 |
ados | +0.094 |
vitamins | +0.091 |
array | +0.090 |
Mickey | +0.089 |
Neg logit contributions | |
a | -0.100 |
- | -0.087 |
ah | -0.085 |
be | -0.084 |
ch | -0.079 |
Token | no |
Token ID | 645 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
a | +0.007 |
- | +0.006 |
ah | +0.006 |
be | +0.006 |
ch | +0.005 |
Neg logit contributions | |
disl | -0.007 |
ados | -0.007 |
vitamins | -0.006 |
array | -0.006 |
Mickey | -0.006 |
Token | more |
Token ID | 517 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
a | +0.094 |
be | +0.079 |
as | +0.076 |
ah | +0.074 |
fly | +0.074 |
Neg logit contributions | |
avocado | -0.095 |
disl | -0.095 |
vitamins | -0.094 |
array | -0.091 |
Mickey | -0.091 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
disl | +0.004 |
ados | +0.004 |
vitamins | +0.004 |
array | +0.004 |
avocado | +0.004 |
Neg logit contributions | |
a | -0.004 |
ah | -0.003 |
be | -0.003 |
- | -0.003 |
ch | -0.003 |
Token | chie |
Token ID | 3043 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
ados | +0.043 |
disl | +0.043 |
array | +0.041 |
avocado | +0.040 |
av | +0.040 |
Neg logit contributions | |
a | -0.022 |
ah | -0.018 |
- | -0.018 |
ch | -0.015 |
less | -0.015 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
a | +0.510 |
fly | +0.464 |
closer | +0.453 |
less | +0.452 |
steering | +0.447 |
Neg logit contributions | |
disl | -0.428 |
vitamins | -0.369 |
array | -0.365 |
avocado | -0.360 |
ados | -0.353 |
Token | mice |
Token ID | 10693 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
a | +0.167 |
ah | +0.138 |
be | +0.137 |
- | +0.136 |
fly | +0.125 |
Neg logit contributions | |
disl | -0.169 |
ados | -0.162 |
vitamins | -0.161 |
avocado | -0.156 |
array | -0.156 |
Token | could |
Token ID | 714 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
disl | +0.156 |
ados | +0.147 |
Mickey | +0.146 |
vitamins | +0.146 |
Bruce | +0.143 |
Neg logit contributions | |
a | -0.103 |
ah | -0.088 |
- | -0.086 |
be | -0.084 |
ch | -0.078 |
Token | come |
Token ID | 1282 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
disl | +0.001 |
ados | +0.001 |
vitamins | +0.001 |
array | +0.001 |
Mickey | +0.001 |
Neg logit contributions | |
a | -0.001 |
- | -0.001 |
ah | -0.001 |
be | -0.001 |
ch | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
a | +0.143 |
ah | +0.129 |
be | +0.115 |
- | +0.108 |
ch | +0.107 |
Neg logit contributions | |
Mickey | -0.208 |
disl | -0.208 |
ados | -0.203 |
Bruce | -0.197 |
avocado | -0.195 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ados | +0.055 |
disl | +0.055 |
avocado | +0.052 |
vitamins | +0.051 |
av | +0.050 |
Neg logit contributions | |
a | -0.049 |
ah | -0.043 |
be | -0.042 |
fly | -0.041 |
mer | -0.041 |
Token | " |
Token ID | 366 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
disl | +0.022 |
ados | +0.021 |
Mickey | +0.020 |
avocado | +0.019 |
Bruce | +0.019 |
Neg logit contributions | |
a | -0.034 |
ah | -0.030 |
- | -0.029 |
iest | -0.029 |
be | -0.028 |
Token | I |
Token ID | 40 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
a | +0.185 |
- | +0.172 |
ah | +0.159 |
less | +0.155 |
fly | +0.154 |
Neg logit contributions | |
disl | -0.128 |
vitamins | -0.113 |
ados | -0.111 |
array | -0.110 |
Mickey | -0.103 |
Token | am |
Token ID | 716 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
disl | +0.029 |
vitamins | +0.024 |
earn | +0.022 |
court | +0.021 |
array | +0.021 |
Neg logit contributions | |
web | -0.033 |
fly | -0.032 |
a | -0.031 |
king | -0.030 |
leon | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
a | +0.115 |
ah | +0.104 |
- | +0.102 |
be | +0.099 |
y | +0.097 |
Neg logit contributions | |
disl | -0.104 |
Mickey | -0.100 |
ados | -0.097 |
avocado | -0.095 |
Bruce | -0.094 |
Token | passenger |
Token ID | 11849 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
avocado | +0.019 |
vitamins | +0.019 |
court | +0.019 |
Mickey | +0.018 |
disl | +0.018 |
Neg logit contributions | |
a | -0.019 |
- | -0.019 |
y | -0.017 |
less | -0.017 |
ry | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
a | +0.546 |
ch | +0.517 |
less | +0.509 |
vy | +0.504 |
pr | +0.493 |
Neg logit contributions | |
court | -0.284 |
avocado | -0.266 |
ados | -0.252 |
Everyone | -0.251 |
This | -0.237 |
Token | I |
Token ID | 314 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
a | +0.008 |
- | +0.007 |
ah | +0.007 |
be | +0.007 |
y | +0.006 |
Neg logit contributions | |
disl | -0.004 |
ados | -0.004 |
vitamins | -0.004 |
Mickey | -0.004 |
array | -0.003 |
Token | look |
Token ID | 804 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
disl | +0.007 |
vitamins | +0.006 |
earn | +0.005 |
court | +0.005 |
array | +0.005 |
Neg logit contributions | |
a | -0.006 |
fly | -0.006 |
less | -0.006 |
king | -0.006 |
- | -0.006 |
Token | out |
Token ID | 503 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
a | +0.095 |
fly | +0.090 |
ah | +0.089 |
be | +0.084 |
web | +0.080 |
Neg logit contributions | |
disl | -0.096 |
avocado | -0.096 |
vitamins | -0.094 |
Bruce | -0.093 |
ados | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
a | +0.045 |
fly | +0.043 |
ah | +0.043 |
be | +0.040 |
man | +0.038 |
Neg logit contributions | |
ados | -0.037 |
avocado | -0.036 |
vitamins | -0.036 |
av | -0.035 |
oranges | -0.034 |
Token | driver |
Token ID | 4639 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
disl | +0.015 |
ados | +0.015 |
vitamins | +0.014 |
avocado | +0.014 |
Mickey | +0.014 |
Neg logit contributions | |
a | -0.013 |
- | -0.012 |
ah | -0.011 |
be | -0.011 |
less | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
a | +0.198 |
less | +0.180 |
ah | +0.179 |
steering | +0.179 |
souven | +0.177 |
Neg logit contributions | |
avocado | -0.196 |
Mickey | -0.180 |
av | -0.179 |
disl | -0.176 |
ados | -0.173 |
Token | I |
Token ID | 314 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
a | +0.025 |
- | +0.023 |
ah | +0.022 |
be | +0.022 |
ch | +0.021 |
Neg logit contributions | |
disl | -0.018 |
ados | -0.018 |
array | -0.017 |
vitamins | -0.017 |
av | -0.016 |
Token | am |
Token ID | 716 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
disl | +0.006 |
vitamins | +0.005 |
array | +0.005 |
Mickey | +0.005 |
Bruce | +0.005 |
Neg logit contributions | |
a | -0.006 |
- | -0.006 |
be | -0.006 |
ah | -0.005 |
less | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
a | +0.108 |
ah | +0.095 |
- | +0.094 |
be | +0.093 |
y | +0.086 |
Neg logit contributions | |
disl | -0.114 |
Mickey | -0.108 |
ados | -0.107 |
avocado | -0.105 |
vitamins | -0.105 |
Token | passenger |
Token ID | 11849 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
disl | +0.016 |
avocado | +0.015 |
vitamins | +0.015 |
ados | +0.015 |
Mickey | +0.015 |
Neg logit contributions | |
a | -0.013 |
- | -0.011 |
ah | -0.010 |
be | -0.010 |
less | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
a | +0.494 |
ch | +0.469 |
less | +0.462 |
ah | +0.451 |
fly | +0.424 |
Neg logit contributions | |
avocado | -0.355 |
court | -0.355 |
ados | -0.329 |
disl | -0.320 |
Mickey | -0.316 |
Token | You |
Token ID | 921 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
a | +0.026 |
- | +0.023 |
be | +0.023 |
ah | +0.023 |
ch | +0.022 |
Neg logit contributions | |
disl | -0.019 |
ados | -0.019 |
array | -0.018 |
vitamins | -0.018 |
avocado | -0.017 |
Token | have |
Token ID | 423 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
disl | +0.062 |
Mickey | +0.058 |
vitamins | +0.057 |
ados | +0.057 |
array | +0.056 |
Neg logit contributions | |
a | -0.061 |
- | -0.055 |
ah | -0.053 |
be | -0.051 |
less | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
a | +0.092 |
ah | +0.080 |
- | +0.079 |
be | +0.076 |
fly | +0.072 |
Neg logit contributions | |
disl | -0.114 |
vitamins | -0.112 |
ados | -0.110 |
array | -0.106 |
avocado | -0.105 |
Token | go |
Token ID | 467 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
disl | +0.008 |
ados | +0.008 |
vitamins | +0.007 |
array | +0.007 |
Mickey | +0.007 |
Neg logit contributions | |
a | -0.008 |
- | -0.007 |
ah | -0.006 |
be | -0.006 |
ch | -0.006 |
Token | sweet |
Token ID | 6029 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
a | +0.036 |
fly | +0.034 |
ah | +0.033 |
be | +0.033 |
ilot | +0.032 |
Neg logit contributions | |
avocado | -0.035 |
court | -0.035 |
disl | -0.034 |
av | -0.031 |
Mickey | -0.031 |
Token | tune |
Token ID | 14009 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
avocado | +0.000 |
disl | +0.000 |
ados | +0.000 |
Mickey | +0.000 |
av | +0.000 |
Neg logit contributions | |
a | -0.000 |
be | -0.000 |
as | -0.000 |
ah | -0.000 |
passenger | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
a | +0.147 |
be | +0.125 |
mer | +0.123 |
vy | +0.123 |
ah | +0.123 |
Neg logit contributions | |
ados | -0.163 |
disl | -0.155 |
avocado | -0.155 |
Mickey | -0.152 |
herself | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
disl | +0.013 |
ados | +0.013 |
Mickey | +0.012 |
vitamins | +0.012 |
array | +0.012 |
Neg logit contributions | |
a | -0.017 |
- | -0.015 |
be | -0.015 |
ah | -0.015 |
ch | -0.014 |
Token | mis |
Token ID | 2984 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
a | +0.036 |
ah | +0.033 |
ac | +0.031 |
z | +0.031 |
as | +0.030 |
Neg logit contributions | |
avocado | -0.036 |
disl | -0.035 |
Mickey | -0.035 |
courtroom | -0.034 |
av | -0.034 |
Token | chie |
Token ID | 3043 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
ados | +0.060 |
disl | +0.060 |
array | +0.059 |
avocado | +0.057 |
Mickey | +0.056 |
Neg logit contributions | |
a | -0.024 |
- | -0.022 |
ah | -0.021 |
ch | -0.019 |
less | -0.019 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
a | +0.510 |
less | +0.475 |
fly | +0.464 |
steering | +0.462 |
closer | +0.457 |
Neg logit contributions | |
disl | -0.403 |
array | -0.335 |
vitamins | -0.320 |
avocado | -0.314 |
iveness | -0.304 |
Token | fox |
Token ID | 21831 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
a | +0.152 |
be | +0.123 |
as | +0.120 |
z | +0.119 |
- | +0.113 |
Neg logit contributions | |
disl | -0.173 |
avocado | -0.173 |
Mickey | -0.166 |
ados | -0.165 |
Bruce | -0.163 |
Token | appeared |
Token ID | 4120 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
a | +0.048 |
ah | +0.040 |
be | +0.039 |
- | +0.039 |
less | +0.039 |
Neg logit contributions | |
disl | -0.063 |
Mickey | -0.062 |
ados | -0.061 |
array | -0.059 |
av | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
a | +0.118 |
be | +0.105 |
ah | +0.105 |
ch | +0.092 |
passenger | +0.090 |
Neg logit contributions | |
ados | -0.170 |
Mickey | -0.164 |
av | -0.164 |
avocado | -0.162 |
Bruce | -0.159 |
Token | " |
Token ID | 366 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
a | +0.022 |
- | +0.020 |
ah | +0.019 |
ch | +0.018 |
be | +0.018 |
Neg logit contributions | |
disl | -0.016 |
vitamins | -0.016 |
ados | -0.016 |
array | -0.015 |
avocado | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
disl | +0.026 |
ados | +0.026 |
vitamins | +0.025 |
array | +0.024 |
Mickey | +0.024 |
Neg logit contributions | |
a | -0.028 |
- | -0.024 |
ah | -0.023 |
be | -0.023 |
ch | -0.022 |
Token | One |
Token ID | 3198 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
disl | +0.027 |
ados | +0.026 |
vitamins | +0.025 |
array | +0.025 |
Mickey | +0.024 |
Neg logit contributions | |
a | -0.026 |
- | -0.023 |
ah | -0.022 |
be | -0.022 |
ch | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
be | +0.060 |
a | +0.060 |
steering | +0.059 |
ist | +0.059 |
cher | +0.057 |
Neg logit contributions | |
avocado | -0.032 |
Mickey | -0.028 |
Freddy | -0.027 |
disl | -0.026 |
broccoli | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
a | +0.054 |
be | +0.044 |
ah | +0.043 |
- | +0.041 |
fly | +0.039 |
Neg logit contributions | |
ados | -0.073 |
Mickey | -0.072 |
disl | -0.071 |
avocado | -0.070 |
Bruce | -0.070 |
Token | mis |
Token ID | 2984 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
a | +0.041 |
ist | +0.036 |
be | +0.035 |
ah | +0.035 |
as | +0.035 |
Neg logit contributions | |
Mickey | -0.041 |
avocado | -0.039 |
av | -0.037 |
disl | -0.037 |
Bruce | -0.037 |
Token | chie |
Token ID | 3043 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
ados | +0.061 |
disl | +0.060 |
avocado | +0.059 |
array | +0.058 |
vitamins | +0.058 |
Neg logit contributions | |
a | -0.024 |
- | -0.021 |
ah | -0.019 |
ch | -0.019 |
less | -0.018 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
a | +0.513 |
less | +0.473 |
closer | +0.463 |
fly | +0.462 |
steering | +0.461 |
Neg logit contributions | |
disl | -0.394 |
array | -0.335 |
vitamins | -0.331 |
avocado | -0.322 |
ados | -0.308 |
Token | monkey |
Token ID | 21657 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
a | +0.147 |
be | +0.121 |
- | +0.113 |
as | +0.109 |
z | +0.109 |
Neg logit contributions | |
disl | -0.176 |
Mickey | -0.173 |
avocado | -0.173 |
ados | -0.171 |
av | -0.165 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
a | +0.058 |
be | +0.048 |
- | +0.048 |
ah | +0.047 |
less | +0.045 |
Neg logit contributions | |
disl | -0.085 |
ados | -0.083 |
Mickey | -0.082 |
array | -0.081 |
avocado | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
a | +0.047 |
- | +0.043 |
ah | +0.037 |
ch | +0.034 |
of | +0.034 |
Neg logit contributions | |
disl | -0.089 |
array | -0.086 |
vitamins | -0.086 |
ados | -0.084 |
courtroom | -0.079 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
disl | +0.006 |
ados | +0.006 |
avocado | +0.006 |
array | +0.006 |
vitamins | +0.006 |
Neg logit contributions | |
a | -0.005 |
- | -0.004 |
be | -0.004 |
ah | -0.004 |
ch | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
disl | +0.124 |
ados | +0.122 |
array | +0.121 |
vitamins | +0.119 |
Mickey | +0.114 |
Neg logit contributions | |
a | -0.050 |
- | -0.043 |
ah | -0.034 |
be | -0.032 |
of | -0.031 |
Token | Let |
Token ID | 5756 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
a | +0.093 |
- | +0.078 |
be | +0.076 |
ah | +0.075 |
ch | +0.069 |
Neg logit contributions | |
disl | -0.100 |
ados | -0.099 |
vitamins | -0.094 |
array | -0.094 |
Mickey | -0.091 |
Token | 's |
Token ID | 338 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
a | +0.028 |
- | +0.024 |
be | +0.023 |
ah | +0.023 |
ch | +0.021 |
Neg logit contributions | |
disl | -0.034 |
ados | -0.033 |
vitamins | -0.033 |
array | -0.032 |
Mickey | -0.031 |
Token | go |
Token ID | 467 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
disl | +0.049 |
ados | +0.048 |
vitamins | +0.047 |
array | +0.046 |
Mickey | +0.044 |
Neg logit contributions | |
a | -0.041 |
- | -0.036 |
be | -0.034 |
ah | -0.033 |
ch | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Bruce | +0.012 |
Mickey | +0.012 |
court | +0.012 |
disl | +0.012 |
array | +0.011 |
Neg logit contributions | |
a | -0.012 |
ah | -0.010 |
fly | -0.009 |
web | -0.009 |
as | -0.009 |
Token | mate |
Token ID | 16133 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
disl | +0.018 |
ados | +0.017 |
Mickey | +0.017 |
avocado | +0.016 |
vitamins | +0.016 |
Neg logit contributions | |
a | -0.027 |
- | -0.025 |
ah | -0.024 |
be | -0.024 |
ch | -0.023 |
Token | y |
Token ID | 88 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ch | +0.294 |
a | +0.286 |
spe | +0.262 |
br | +0.251 |
be | +0.247 |
Neg logit contributions | |
disl | -0.562 |
ados | -0.531 |
vitamins | -0.524 |
avocado | -0.507 |
Freddy | -0.505 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
a | +0.205 |
ah | +0.178 |
be | +0.177 |
- | +0.173 |
ch | +0.165 |
Neg logit contributions | |
disl | -0.250 |
ados | -0.240 |
vitamins | -0.239 |
Mickey | -0.237 |
Bruce | -0.230 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
disl | +0.192 |
ados | +0.183 |
vitamins | +0.181 |
array | +0.181 |
avocado | +0.170 |
Neg logit contributions | |
a | -0.192 |
- | -0.166 |
be | -0.157 |
ah | -0.157 |
ch | -0.146 |
Token | said |
Token ID | 531 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
disl | +0.085 |
ados | +0.083 |
array | +0.078 |
vitamins | +0.078 |
avocado | +0.075 |
Neg logit contributions | |
a | -0.106 |
- | -0.093 |
ah | -0.089 |
be | -0.089 |
ch | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
disl | +0.002 |
ados | +0.002 |
Mickey | +0.002 |
Bruce | +0.002 |
Freddy | +0.002 |
Neg logit contributions | |
a | -0.001 |
ah | -0.001 |
be | -0.001 |
ch | -0.001 |
fly | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
a | +0.095 |
ah | +0.084 |
be | +0.079 |
fly | +0.076 |
- | +0.075 |
Neg logit contributions | |
disl | -0.106 |
ados | -0.103 |
array | -0.098 |
Mickey | -0.098 |
court | -0.097 |
Token | became |
Token ID | 2627 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
a | +0.014 |
- | +0.012 |
ah | +0.012 |
be | +0.011 |
ch | +0.011 |
Neg logit contributions | |
disl | -0.016 |
ados | -0.016 |
array | -0.015 |
vitamins | -0.015 |
Mickey | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
disl | +0.028 |
ados | +0.028 |
Mickey | +0.027 |
vitamins | +0.027 |
avocado | +0.026 |
Neg logit contributions | |
a | -0.025 |
ah | -0.022 |
- | -0.021 |
be | -0.021 |
fly | -0.020 |
Token | great |
Token ID | 1049 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
a | +0.039 |
ah | +0.036 |
fly | +0.036 |
ist | +0.035 |
iest | +0.035 |
Neg logit contributions | |
court | -0.035 |
disl | -0.035 |
courtroom | -0.035 |
Mickey | -0.035 |
avocado | -0.034 |
Token | violin |
Token ID | 38283 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
a | +0.023 |
fly | +0.019 |
ah | +0.019 |
be | +0.019 |
ch | +0.018 |
Neg logit contributions | |
disl | -0.023 |
Mickey | -0.022 |
avocado | -0.022 |
court | -0.022 |
array | -0.022 |
Token | ist |
Token ID | 396 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
ados | +0.081 |
court | +0.081 |
Mickey | +0.080 |
avocado | +0.077 |
av | +0.075 |
Neg logit contributions | |
a | -0.074 |
be | -0.063 |
ah | -0.062 |
fly | -0.060 |
ba | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
a | +0.493 |
be | +0.422 |
ah | +0.398 |
fly | +0.395 |
ch | +0.393 |
Neg logit contributions | |
disl | -0.475 |
ados | -0.450 |
avocado | -0.412 |
vitamins | -0.411 |
array | -0.410 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
a | +0.021 |
of | +0.019 |
ah | +0.018 |
- | +0.017 |
ch | +0.017 |
Neg logit contributions | |
disl | -0.030 |
vitamins | -0.029 |
array | -0.029 |
ados | -0.028 |
av | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
a | +0.098 |
- | +0.087 |
ah | +0.084 |
be | +0.084 |
ch | +0.078 |
Neg logit contributions | |
disl | -0.084 |
ados | -0.081 |
vitamins | -0.078 |
array | -0.077 |
Mickey | -0.076 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
a | +0.022 |
- | +0.018 |
be | +0.017 |
ah | +0.017 |
ch | +0.015 |
Neg logit contributions | |
disl | -0.050 |
ados | -0.049 |
Mickey | -0.048 |
avocado | -0.047 |
vitamins | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
a | +0.087 |
- | +0.075 |
be | +0.074 |
ah | +0.074 |
fly | +0.067 |
Neg logit contributions | |
disl | -0.106 |
ados | -0.101 |
vitamins | -0.100 |
avocado | -0.100 |
Mickey | -0.099 |
Token | But |
Token ID | 1537 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
disl | +0.019 |
ados | +0.018 |
vitamins | +0.018 |
array | +0.018 |
Mickey | +0.017 |
Neg logit contributions | |
a | -0.013 |
- | -0.011 |
be | -0.011 |
ah | -0.011 |
ch | -0.010 |
Token | then |
Token ID | 788 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
a | +0.049 |
be | +0.042 |
- | +0.042 |
ah | +0.041 |
ch | +0.039 |
Neg logit contributions | |
disl | -0.055 |
ados | -0.055 |
Mickey | -0.055 |
avocado | -0.053 |
Bruce | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
disl | +0.001 |
ados | +0.001 |
Mickey | +0.001 |
array | +0.001 |
vitamins | +0.001 |
Neg logit contributions | |
a | -0.000 |
- | -0.000 |
be | -0.000 |
ah | -0.000 |
ch | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
disl | +0.013 |
ados | +0.013 |
Mickey | +0.013 |
avocado | +0.013 |
Bruce | +0.012 |
Neg logit contributions | |
a | -0.014 |
be | -0.012 |
ah | -0.012 |
- | -0.012 |
ch | -0.011 |
Token | mis |
Token ID | 2984 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
a | +0.040 |
ah | +0.035 |
z | +0.035 |
ba | +0.034 |
be | +0.034 |
Neg logit contributions | |
avocado | -0.037 |
av | -0.036 |
Mickey | -0.035 |
disl | -0.035 |
courtroom | -0.035 |
Token | chie |
Token ID | 3043 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
ados | +0.053 |
disl | +0.053 |
array | +0.051 |
avocado | +0.051 |
courtroom | +0.050 |
Neg logit contributions | |
a | -0.024 |
- | -0.022 |
ah | -0.022 |
ch | -0.021 |
man | -0.020 |
Token | vous |
Token ID | 31222 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
a | +0.509 |
less | +0.476 |
steering | +0.470 |
fly | +0.455 |
passenger | +0.454 |
Neg logit contributions | |
disl | -0.394 |
array | -0.324 |
avocado | -0.310 |
vitamins | -0.307 |
iveness | -0.297 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
a | +0.149 |
be | +0.125 |
z | +0.117 |
- | +0.115 |
as | +0.113 |
Neg logit contributions | |
disl | -0.176 |
avocado | -0.171 |
ados | -0.167 |
Mickey | -0.166 |
Bruce | -0.164 |
Token | came |
Token ID | 1625 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
a | +0.027 |
be | +0.023 |
- | +0.022 |
ah | +0.022 |
less | +0.021 |
Neg logit contributions | |
Mickey | -0.037 |
ados | -0.035 |
disl | -0.035 |
Bruce | -0.035 |
Freddy | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
a | +0.091 |
ah | +0.082 |
be | +0.078 |
iest | +0.076 |
ber | +0.073 |
Neg logit contributions | |
ados | -0.113 |
Mickey | -0.113 |
Bruce | -0.109 |
disl | -0.108 |
Freddy | -0.107 |
Token | started |
Token ID | 2067 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
a | +0.016 |
- | +0.014 |
ah | +0.013 |
be | +0.013 |
ch | +0.012 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.017 |
vitamins | -0.016 |
array | -0.016 |
Mickey | -0.016 |
Token | finally |
Token ID | 3443 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
a | +0.044 |
- | +0.037 |
be | +0.036 |
ah | +0.036 |
ch | +0.033 |
Neg logit contributions | |
disl | -0.058 |
ados | -0.056 |
Mickey | -0.054 |
array | -0.054 |
vitamins | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
a | +0.096 |
- | +0.080 |
ah | +0.075 |
be | +0.072 |
ch | +0.065 |
Neg logit contributions | |
disl | -0.190 |
ados | -0.186 |
vitamins | -0.183 |
array | -0.180 |
Mickey | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
a | +0.012 |
- | +0.011 |
ah | +0.010 |
be | +0.010 |
ch | +0.010 |
Neg logit contributions | |
disl | -0.013 |
ados | -0.012 |
vitamins | -0.012 |
array | -0.012 |
Mickey | -0.012 |
Token | z |
Token ID | 1976 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
a | +0.022 |
- | +0.019 |
ah | +0.018 |
be | +0.018 |
ch | +0.016 |
Neg logit contributions | |
disl | -0.026 |
ados | -0.025 |
avocado | -0.025 |
vitamins | -0.025 |
Mickey | -0.024 |
Token | ig |
Token ID | 328 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
a | +0.079 |
closer | +0.075 |
less | +0.074 |
y | +0.074 |
fly | +0.073 |
Neg logit contributions | |
ados | -0.102 |
disl | -0.102 |
court | -0.101 |
courtroom | -0.097 |
azes | -0.095 |
Token | zag |
Token ID | 50183 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
a | +0.283 |
ah | +0.239 |
ch | +0.238 |
be | +0.237 |
- | +0.232 |
Neg logit contributions | |
disl | -0.391 |
ados | -0.367 |
array | -0.353 |
Mickey | -0.348 |
avocado | -0.346 |
Token | had |
Token ID | 550 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
a | +0.418 |
ah | +0.351 |
- | +0.346 |
less | +0.338 |
be | +0.338 |
Neg logit contributions | |
disl | -0.512 |
ados | -0.471 |
array | -0.467 |
vitamins | -0.459 |
avocado | -0.456 |
Token | an |
Token ID | 281 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
a | +0.045 |
- | +0.039 |
be | +0.037 |
ah | +0.037 |
ch | +0.033 |
Neg logit contributions | |
disl | -0.059 |
ados | -0.058 |
array | -0.055 |
vitamins | -0.055 |
Mickey | -0.055 |
Token | idea |
Token ID | 2126 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
disl | +0.024 |
ados | +0.023 |
vitamins | +0.022 |
array | +0.022 |
Mickey | +0.022 |
Neg logit contributions | |
a | -0.024 |
- | -0.022 |
ah | -0.021 |
be | -0.021 |
ch | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
disl | +0.036 |
ados | +0.034 |
court | +0.033 |
vitamins | +0.033 |
Mickey | +0.033 |
Neg logit contributions | |
a | -0.032 |
ah | -0.028 |
be | -0.027 |
ch | -0.027 |
fly | -0.025 |
Token | It |
Token ID | 632 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
a | +0.039 |
- | +0.033 |
be | +0.033 |
ah | +0.033 |
ch | +0.031 |
Neg logit contributions | |
disl | -0.029 |
vitamins | -0.028 |
ados | -0.028 |
array | -0.027 |
avocado | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
a | +0.011 |
- | +0.009 |
be | +0.009 |
ah | +0.008 |
ch | +0.008 |
Neg logit contributions | |
disl | -0.024 |
ados | -0.024 |
array | -0.023 |
vitamins | -0.023 |
Mickey | -0.022 |
Token | see |
Token ID | 766 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
disl | +0.025 |
ados | +0.024 |
vitamins | +0.023 |
array | +0.023 |
Mickey | +0.023 |
Neg logit contributions | |
a | -0.020 |
- | -0.017 |
ah | -0.017 |
be | -0.017 |
ch | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
a | +0.091 |
- | +0.078 |
ah | +0.077 |
be | +0.077 |
ch | +0.070 |
Neg logit contributions | |
disl | -0.099 |
ados | -0.097 |
vitamins | -0.093 |
Mickey | -0.092 |
array | -0.091 |
Token | graceful |
Token ID | 44363 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
disl | +0.012 |
vitamins | +0.012 |
ados | +0.012 |
avocado | +0.012 |
av | +0.011 |
Neg logit contributions | |
a | -0.012 |
- | -0.011 |
ah | -0.011 |
be | -0.011 |
ch | -0.010 |
Token | violin |
Token ID | 38283 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
a | +0.001 |
be | +0.001 |
ah | +0.001 |
less | +0.001 |
- | +0.001 |
Neg logit contributions | |
disl | -0.001 |
ados | -0.001 |
avocado | -0.001 |
vitamins | -0.001 |
array | -0.001 |
Token | ist |
Token ID | 396 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
ados | +0.080 |
avocado | +0.078 |
disl | +0.078 |
vitamins | +0.076 |
Mickey | +0.076 |
Neg logit contributions | |
a | -0.071 |
ah | -0.062 |
be | -0.061 |
less | -0.057 |
- | -0.057 |
Token | ." |
Token ID | 526 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
a | +0.427 |
be | +0.355 |
- | +0.349 |
ah | +0.341 |
less | +0.323 |
Neg logit contributions | |
disl | -0.547 |
ados | -0.515 |
vitamins | -0.489 |
avocado | -0.481 |
array | -0.478 |
Token |
|
Token ID | 198 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
vitamins | +0.103 |
disl | +0.103 |
array | +0.100 |
ados | +0.097 |
avocado | +0.091 |
Neg logit contributions | |
a | -0.092 |
- | -0.080 |
be | -0.075 |
ah | -0.075 |
fly | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
disl | +0.040 |
ados | +0.040 |
vitamins | +0.039 |
array | +0.038 |
avocado | +0.036 |
Neg logit contributions | |
a | -0.038 |
- | -0.033 |
be | -0.031 |
ah | -0.031 |
ch | -0.029 |
Token | They |
Token ID | 2990 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
disl | +0.040 |
ados | +0.038 |
Mickey | +0.037 |
array | +0.036 |
vitamins | +0.036 |
Neg logit contributions | |
a | -0.032 |
- | -0.029 |
ah | -0.028 |
be | -0.027 |
less | -0.026 |
Token | went |
Token ID | 1816 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
a | +0.029 |
- | +0.026 |
be | +0.025 |
ah | +0.025 |
ch | +0.024 |
Neg logit contributions | |
disl | -0.026 |
ados | -0.025 |
Mickey | -0.025 |
array | -0.024 |
vitamins | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
a | +0.050 |
- | +0.043 |
ah | +0.042 |
be | +0.041 |
ch | +0.038 |
Neg logit contributions | |
disl | -0.068 |
ados | -0.066 |
array | -0.064 |
vitamins | -0.064 |
Mickey | -0.063 |
Token | something |
Token ID | 1223 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
a | +0.060 |
- | +0.051 |
ah | +0.047 |
be | +0.046 |
ch | +0.043 |
Neg logit contributions | |
disl | -0.090 |
ados | -0.089 |
vitamins | -0.086 |
array | -0.085 |
Mickey | -0.083 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
disl | +0.080 |
avocado | +0.077 |
Mickey | +0.076 |
ados | +0.076 |
vitamins | +0.075 |
Neg logit contributions | |
a | -0.078 |
ah | -0.069 |
be | -0.069 |
- | -0.063 |
passenger | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ados | +0.177 |
avocado | +0.176 |
av | +0.171 |
vitamins | +0.167 |
Mickey | +0.164 |
Neg logit contributions | |
a | -0.096 |
be | -0.078 |
ah | -0.071 |
ch | -0.066 |
as | -0.065 |
Token | gl |
Token ID | 1278 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
a | +0.010 |
- | +0.009 |
ah | +0.008 |
be | +0.008 |
ch | +0.007 |
Neg logit contributions | |
disl | -0.014 |
ados | -0.014 |
vitamins | -0.013 |
array | -0.013 |
Mickey | -0.013 |
Token | ist |
Token ID | 396 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
a | +0.052 |
ch | +0.049 |
be | +0.048 |
ah | +0.046 |
plane | +0.046 |
Neg logit contributions | |
disl | -0.062 |
ados | -0.060 |
av | -0.055 |
array | -0.055 |
Bruce | -0.055 |
Token | ening |
Token ID | 3101 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
a | +0.555 |
- | +0.474 |
be | +0.474 |
ah | +0.469 |
ch | +0.448 |
Neg logit contributions | |
disl | -0.412 |
ados | -0.399 |
vitamins | -0.375 |
array | -0.373 |
avocado | -0.370 |
Token | on |
Token ID | 319 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
a | +0.051 |
be | +0.041 |
ah | +0.041 |
ch | +0.035 |
- | +0.035 |
Neg logit contributions | |
ados | -0.101 |
avocado | -0.098 |
av | -0.096 |
vitamins | -0.096 |
disl | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
a | +0.027 |
- | +0.024 |
ah | +0.023 |
be | +0.022 |
ch | +0.020 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.035 |
array | -0.034 |
vitamins | -0.034 |
Mickey | -0.033 |
Token | ground |
Token ID | 2323 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
disl | +0.005 |
ados | +0.005 |
vitamins | +0.004 |
avocado | +0.004 |
array | +0.004 |
Neg logit contributions | |
a | -0.010 |
- | -0.009 |
ah | -0.009 |
be | -0.009 |
ch | -0.008 |
Token | - |
Token ID | 532 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ados | +0.247 |
disl | +0.243 |
avocado | +0.239 |
array | +0.237 |
Mickey | +0.236 |
Neg logit contributions | |
a | -0.180 |
ah | -0.150 |
be | -0.148 |
- | -0.144 |
ch | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ados | +0.358 |
disl | +0.352 |
vitamins | +0.345 |
avocado | +0.344 |
Mickey | +0.341 |
Neg logit contributions | |
a | -0.163 |
ah | -0.125 |
be | -0.122 |
- | -0.122 |
ch | -0.107 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
a | +0.016 |
- | +0.016 |
of | +0.014 |
y | +0.013 |
in | +0.013 |
Neg logit contributions | |
disl | -0.016 |
array | -0.014 |
Mickey | -0.014 |
Mic | -0.014 |
handed | -0.013 |
Token | says |
Token ID | 1139 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
a | +0.023 |
- | +0.021 |
ah | +0.020 |
be | +0.020 |
y | +0.019 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.016 |
vitamins | -0.015 |
array | -0.015 |
Mickey | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ados | +0.065 |
disl | +0.064 |
vitamins | +0.063 |
avocado | +0.062 |
Mickey | +0.062 |
Neg logit contributions | |
a | -0.040 |
ah | -0.033 |
- | -0.033 |
be | -0.032 |
ch | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
a | +0.015 |
be | +0.012 |
- | +0.012 |
ah | +0.011 |
closer | +0.010 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.036 |
array | -0.035 |
vitamins | -0.034 |
Mickey | -0.033 |
Token | av |
Token ID | 1196 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
a | +0.080 |
- | +0.070 |
be | +0.066 |
ah | +0.065 |
ch | +0.061 |
Neg logit contributions | |
disl | -0.087 |
ados | -0.083 |
array | -0.081 |
vitamins | -0.080 |
Mickey | -0.078 |
Token | oc |
Token ID | 420 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
ados | +0.418 |
disl | +0.414 |
vitamins | +0.400 |
Mickey | +0.397 |
array | +0.394 |
Neg logit contributions | |
a | -0.323 |
- | -0.267 |
ah | -0.262 |
be | -0.261 |
ch | -0.244 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
- | +0.055 |
a | +0.053 |
ah | +0.050 |
be | +0.049 |
man | +0.048 |
Neg logit contributions | |
disl | -0.010 |
array | -0.009 |
mischief | -0.007 |
vitamins | -0.007 |
Mickey | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ados | +0.415 |
Mickey | +0.404 |
disl | +0.401 |
avocado | +0.400 |
vitamins | +0.399 |
Neg logit contributions | |
a | -0.292 |
ah | -0.264 |
be | -0.263 |
ch | -0.246 |
- | -0.239 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
a | +0.013 |
- | +0.011 |
of | +0.011 |
be | +0.010 |
closer | +0.010 |
Neg logit contributions | |
disl | -0.019 |
array | -0.018 |
Mickey | -0.018 |
ados | -0.017 |
vitamins | -0.017 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
a | +0.075 |
- | +0.066 |
be | +0.058 |
ah | +0.058 |
y | +0.055 |
Neg logit contributions | |
disl | -0.089 |
ados | -0.088 |
Mickey | -0.083 |
Bruce | -0.081 |
array | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
disl | +0.093 |
Mickey | +0.088 |
avocado | +0.087 |
ados | +0.087 |
array | +0.087 |
Neg logit contributions | |
a | -0.060 |
ah | -0.051 |
be | -0.050 |
ch | -0.048 |
- | -0.048 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
a | +0.023 |
of | +0.022 |
y | +0.021 |
- | +0.021 |
ch | +0.020 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.015 |
handed | -0.014 |
array | -0.014 |
courtroom | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
ados | +0.094 |
disl | +0.093 |
vitamins | +0.088 |
array | +0.087 |
Mickey | +0.086 |
Neg logit contributions | |
a | -0.065 |
- | -0.057 |
be | -0.051 |
ah | -0.051 |
y | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
disl | +0.098 |
array | +0.094 |
Bruce | +0.092 |
ados | +0.092 |
handed | +0.092 |
Neg logit contributions | |
- | -0.024 |
a | -0.021 |
be | -0.017 |
ch | -0.017 |
on | -0.014 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ados | +0.004 |
disl | +0.004 |
vitamins | +0.004 |
array | +0.004 |
Mickey | +0.004 |
Neg logit contributions | |
a | -0.003 |
- | -0.003 |
ah | -0.003 |
be | -0.003 |
ch | -0.003 |
Token | av |
Token ID | 1196 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
disl | +0.079 |
array | +0.071 |
courtroom | +0.069 |
handed | +0.066 |
weaknesses | +0.066 |
Neg logit contributions | |
- | -0.089 |
a | -0.079 |
on | -0.073 |
of | -0.071 |
in | -0.069 |
Token | oc |
Token ID | 420 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
disl | +0.505 |
array | +0.467 |
ados | +0.461 |
vitamins | +0.461 |
Bruce | +0.452 |
Neg logit contributions | |
a | -0.258 |
- | -0.243 |
ah | -0.215 |
be | -0.206 |
ch | -0.187 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
- | +0.059 |
rot | +0.045 |
be | +0.043 |
man | +0.043 |
a | +0.043 |
Neg logit contributions | |
disl | -0.024 |
array | -0.024 |
mischief | -0.021 |
vitamins | -0.020 |
Afterwards | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
disl | +0.489 |
ados | +0.475 |
vitamins | +0.462 |
array | +0.461 |
Mickey | +0.455 |
Neg logit contributions | |
a | -0.249 |
- | -0.204 |
ah | -0.192 |
be | -0.191 |
ch | -0.169 |
Token | they |
Token ID | 484 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
disl | +0.035 |
array | +0.033 |
ados | +0.032 |
vitamins | +0.031 |
iveness | +0.031 |
Neg logit contributions | |
a | -0.019 |
- | -0.017 |
of | -0.016 |
be | -0.016 |
ah | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
a | +0.023 |
- | +0.019 |
be | +0.019 |
ah | +0.019 |
y | +0.017 |
Neg logit contributions | |
disl | -0.043 |
ados | -0.040 |
array | -0.040 |
vitamins | -0.038 |
Mickey | -0.037 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
a | +0.023 |
- | +0.021 |
be | +0.020 |
ah | +0.020 |
ch | +0.019 |
Neg logit contributions | |
ados | -0.012 |
disl | -0.012 |
array | -0.011 |
vitamins | -0.011 |
avocado | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
disl | +0.061 |
ados | +0.059 |
vitamins | +0.058 |
Mickey | +0.057 |
avocado | +0.057 |
Neg logit contributions | |
a | -0.058 |
ah | -0.051 |
be | -0.050 |
- | -0.049 |
ch | -0.046 |
Token | could |
Token ID | 714 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
a | +0.022 |
- | +0.018 |
ah | +0.017 |
be | +0.017 |
ch | +0.016 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.036 |
vitamins | -0.035 |
Mickey | -0.035 |
array | -0.034 |
Token | grow |
Token ID | 1663 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ados | +0.013 |
disl | +0.013 |
array | +0.013 |
vitamins | +0.013 |
courtroom | +0.012 |
Neg logit contributions | |
a | -0.012 |
- | -0.010 |
be | -0.010 |
ah | -0.009 |
closer | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
avocado | +0.039 |
av | +0.039 |
ados | +0.039 |
vitamins | +0.039 |
disl | +0.038 |
Neg logit contributions | |
a | -0.033 |
ah | -0.031 |
be | -0.029 |
passenger | -0.026 |
ch | -0.026 |
Token | av |
Token ID | 1196 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
disl | +0.004 |
array | +0.004 |
ados | +0.004 |
Mickey | +0.004 |
vitamins | +0.004 |
Neg logit contributions | |
a | -0.004 |
- | -0.004 |
be | -0.004 |
of | -0.004 |
ah | -0.004 |
Token | oc |
Token ID | 420 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
disl | +0.458 |
ados | +0.443 |
vitamins | +0.431 |
array | +0.429 |
Mickey | +0.423 |
Neg logit contributions | |
a | -0.293 |
- | -0.249 |
ah | -0.236 |
be | -0.235 |
ch | -0.212 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
- | +0.064 |
a | +0.059 |
be | +0.056 |
ah | +0.056 |
less | +0.054 |
Neg logit contributions | |
array | -0.012 |
disl | -0.012 |
mischief | -0.009 |
Mickey | -0.008 |
vitamins | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ados | +0.421 |
avocado | +0.416 |
disl | +0.413 |
av | +0.413 |
Mickey | +0.407 |
Neg logit contributions | |
a | -0.280 |
ah | -0.251 |
be | -0.232 |
- | -0.222 |
ch | -0.219 |
Token | share |
Token ID | 2648 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
a | +0.016 |
- | +0.014 |
be | +0.014 |
ah | +0.013 |
closer | +0.013 |
Neg logit contributions | |
disl | -0.019 |
ados | -0.019 |
array | -0.018 |
vitamins | -0.017 |
Mickey | -0.017 |
Token | them |
Token ID | 606 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
disl | +0.109 |
ados | +0.106 |
array | +0.104 |
vitamins | +0.103 |
Mickey | +0.101 |
Neg logit contributions | |
a | -0.084 |
- | -0.073 |
be | -0.068 |
ah | -0.067 |
ch | -0.062 |
Token | but |
Token ID | 475 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
disl | +0.022 |
ados | +0.022 |
vitamins | +0.021 |
array | +0.021 |
Mickey | +0.020 |
Neg logit contributions | |
a | -0.023 |
- | -0.020 |
ah | -0.019 |
be | -0.019 |
ch | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
a | +0.109 |
- | +0.094 |
ah | +0.091 |
be | +0.090 |
ch | +0.083 |
Neg logit contributions | |
disl | -0.122 |
ados | -0.118 |
vitamins | -0.114 |
array | -0.114 |
Mickey | -0.112 |
Token | were |
Token ID | 547 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
a | +0.022 |
- | +0.018 |
ah | +0.018 |
be | +0.018 |
ch | +0.016 |
Neg logit contributions | |
disl | -0.029 |
ados | -0.029 |
vitamins | -0.028 |
Mickey | -0.028 |
array | -0.028 |
Token | no |
Token ID | 645 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
disl | +0.004 |
vitamins | +0.004 |
ados | +0.004 |
avocado | +0.004 |
Mickey | +0.004 |
Neg logit contributions | |
a | -0.004 |
- | -0.004 |
ah | -0.004 |
be | -0.004 |
ch | -0.003 |
Token | other |
Token ID | 584 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
a | +0.091 |
- | +0.086 |
be | +0.077 |
ah | +0.077 |
of | +0.073 |
Neg logit contributions | |
disl | -0.115 |
ados | -0.106 |
array | -0.105 |
Mickey | -0.103 |
vitamins | -0.101 |
Token | av |
Token ID | 1196 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
disl | +0.070 |
array | +0.067 |
ados | +0.066 |
Mickey | +0.065 |
vitamins | +0.063 |
Neg logit contributions | |
a | -0.068 |
- | -0.063 |
be | -0.057 |
ah | -0.056 |
of | -0.054 |
Token | oc |
Token ID | 420 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
disl | +0.444 |
ados | +0.434 |
vitamins | +0.419 |
array | +0.417 |
Mickey | +0.413 |
Neg logit contributions | |
a | -0.304 |
- | -0.256 |
ah | -0.246 |
be | -0.244 |
ch | -0.222 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
- | +0.061 |
a | +0.055 |
be | +0.054 |
ah | +0.054 |
less | +0.052 |
Neg logit contributions | |
disl | -0.014 |
array | -0.013 |
mischief | -0.010 |
vitamins | -0.010 |
Mickey | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
disl | +0.460 |
ados | +0.456 |
vitamins | +0.442 |
Mickey | +0.437 |
array | +0.435 |
Neg logit contributions | |
a | -0.264 |
ah | -0.216 |
- | -0.213 |
be | -0.209 |
ch | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
a | +0.022 |
be | +0.020 |
of | +0.020 |
- | +0.019 |
ch | +0.019 |
Neg logit contributions | |
disl | -0.026 |
vitamins | -0.024 |
ados | -0.023 |
array | -0.022 |
avocado | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
disl | +0.015 |
ados | +0.015 |
vitamins | +0.014 |
array | +0.014 |
avocado | +0.014 |
Neg logit contributions | |
a | -0.015 |
- | -0.013 |
be | -0.012 |
ah | -0.012 |
ch | -0.012 |
Token | before |
Token ID | 878 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
a | +0.116 |
- | +0.096 |
ah | +0.093 |
be | +0.093 |
ch | +0.085 |
Neg logit contributions | |
disl | -0.180 |
ados | -0.175 |
vitamins | -0.172 |
array | -0.169 |
Mickey | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
disl | +0.172 |
ados | +0.164 |
array | +0.161 |
vitamins | +0.160 |
Mickey | +0.156 |
Neg logit contributions | |
a | -0.061 |
- | -0.054 |
be | -0.045 |
ah | -0.041 |
y | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
a | +0.022 |
ah | +0.019 |
of | +0.019 |
- | +0.019 |
be | +0.018 |
Neg logit contributions | |
disl | -0.024 |
array | -0.023 |
ados | -0.022 |
vitamins | -0.022 |
avocado | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
disl | +0.014 |
ados | +0.014 |
array | +0.013 |
vitamins | +0.013 |
Mickey | +0.013 |
Neg logit contributions | |
a | -0.013 |
- | -0.011 |
ah | -0.011 |
be | -0.011 |
ch | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
disl | +0.014 |
ados | +0.013 |
vitamins | +0.013 |
Mickey | +0.013 |
avocado | +0.012 |
Neg logit contributions | |
a | -0.012 |
- | -0.011 |
ah | -0.010 |
be | -0.010 |
less | -0.010 |
Token | av |
Token ID | 1196 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
a | +0.034 |
- | +0.034 |
be | +0.029 |
ah | +0.029 |
of | +0.029 |
Neg logit contributions | |
disl | -0.044 |
array | -0.043 |
vitamins | -0.039 |
ados | -0.038 |
Bruce | -0.035 |
Token | oc |
Token ID | 420 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
disl | +0.447 |
ados | +0.436 |
vitamins | +0.422 |
array | +0.419 |
Mickey | +0.416 |
Neg logit contributions | |
a | -0.300 |
- | -0.252 |
ah | -0.241 |
be | -0.240 |
ch | -0.218 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
- | +0.073 |
a | +0.067 |
man | +0.067 |
fly | +0.065 |
ah | +0.065 |
Neg logit contributions | |
array | -0.016 |
disl | -0.014 |
vitamins | -0.014 |
mischief | -0.013 |
Mickey | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
disl | +0.361 |
ados | +0.357 |
avocado | +0.346 |
Mickey | +0.345 |
vitamins | +0.340 |
Neg logit contributions | |
a | -0.353 |
- | -0.304 |
ah | -0.297 |
be | -0.291 |
ch | -0.288 |
Token | shared |
Token ID | 4888 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
disl | +0.004 |
ados | +0.004 |
vitamins | +0.004 |
avocado | +0.004 |
Mickey | +0.004 |
Neg logit contributions | |
a | -0.004 |
- | -0.003 |
ah | -0.003 |
be | -0.003 |
ch | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
disl | +0.069 |
ados | +0.067 |
vitamins | +0.065 |
array | +0.065 |
Mickey | +0.064 |
Neg logit contributions | |
a | -0.034 |
- | -0.028 |
ah | -0.026 |
be | -0.026 |
ch | -0.023 |
Token | so |
Token ID | 523 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Mickey | +0.023 |
array | +0.023 |
avocado | +0.023 |
disl | +0.023 |
Bruce | +0.022 |
Neg logit contributions | |
a | -0.026 |
ah | -0.025 |
- | -0.023 |
ch | -0.023 |
iest | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
disl | +0.098 |
ados | +0.093 |
vitamins | +0.090 |
array | +0.090 |
Mickey | +0.089 |
Neg logit contributions | |
a | -0.074 |
ah | -0.065 |
- | -0.064 |
be | -0.062 |
ch | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
a | +0.026 |
ah | +0.022 |
be | +0.021 |
ch | +0.019 |
passenger | +0.019 |
Neg logit contributions | |
disl | -0.038 |
ados | -0.037 |
array | -0.035 |
Mickey | -0.035 |
avocado | -0.034 |
Token | have |
Token ID | 423 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
disl | +0.008 |
ados | +0.008 |
vitamins | +0.008 |
array | +0.008 |
Mickey | +0.008 |
Neg logit contributions | |
a | -0.007 |
- | -0.006 |
be | -0.006 |
ah | -0.006 |
ch | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
a | +0.110 |
- | +0.098 |
be | +0.092 |
ah | +0.092 |
ch | +0.086 |
Neg logit contributions | |
disl | -0.111 |
ados | -0.107 |
vitamins | -0.103 |
array | -0.102 |
avocado | -0.099 |
Token | av |
Token ID | 1196 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
- | +0.001 |
a | +0.001 |
be | +0.001 |
ah | +0.001 |
of | +0.001 |
Neg logit contributions | |
disl | -0.001 |
array | -0.001 |
vitamins | -0.001 |
iveness | -0.000 |
ados | -0.000 |
Token | oc |
Token ID | 420 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
disl | +0.447 |
ados | +0.436 |
vitamins | +0.422 |
array | +0.419 |
Mickey | +0.415 |
Neg logit contributions | |
a | -0.300 |
- | -0.253 |
ah | -0.242 |
be | -0.241 |
ch | -0.219 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
- | +0.076 |
man | +0.068 |
a | +0.068 |
ah | +0.067 |
be | +0.066 |
Neg logit contributions | |
disl | -0.016 |
array | -0.015 |
vitamins | -0.013 |
mischief | -0.013 |
Bruce | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ados | +0.400 |
avocado | +0.398 |
av | +0.395 |
Mickey | +0.393 |
court | +0.391 |
Neg logit contributions | |
a | -0.310 |
ah | -0.272 |
be | -0.270 |
ch | -0.260 |
- | -0.234 |
Token | She |
Token ID | 1375 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
- | +0.012 |
and | +0.011 |
to | +0.010 |
of | +0.010 |
too | +0.010 |
Neg logit contributions | |
affles | -0.019 |
disl | -0.019 |
vitamins | -0.019 |
handed | -0.018 |
ados | -0.018 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ados | +0.037 |
disl | +0.036 |
array | +0.034 |
vitamins | +0.034 |
iveness | +0.032 |
Neg logit contributions | |
a | -0.027 |
- | -0.024 |
ah | -0.021 |
be | -0.021 |
ch | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
a | +0.021 |
of | +0.019 |
ch | +0.017 |
be | +0.017 |
- | +0.017 |
Neg logit contributions | |
disl | -0.024 |
vitamins | -0.023 |
array | -0.022 |
ados | -0.021 |
av | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
disl | +0.017 |
ados | +0.017 |
vitamins | +0.017 |
array | +0.016 |
avocado | +0.016 |
Neg logit contributions | |
a | -0.015 |
- | -0.013 |
be | -0.012 |
ah | -0.012 |
ch | -0.011 |
Token | At |
Token ID | 2953 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
disl | +0.017 |
ados | +0.016 |
vitamins | +0.016 |
array | +0.016 |
Mickey | +0.016 |
Neg logit contributions | |
a | -0.013 |
- | -0.012 |
ah | -0.011 |
be | -0.011 |
fly | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
a | +0.064 |
- | +0.055 |
be | +0.054 |
ah | +0.053 |
ch | +0.049 |
Neg logit contributions | |
ados | -0.067 |
disl | -0.066 |
Mickey | -0.066 |
avocado | -0.064 |
Bruce | -0.064 |
Token | or |
Token ID | 393 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
disl | +0.008 |
ados | +0.008 |
vitamins | +0.008 |
array | +0.007 |
Mickey | +0.007 |
Neg logit contributions | |
a | -0.006 |
- | -0.005 |
ah | -0.005 |
be | -0.005 |
ch | -0.004 |
Token | chard |
Token ID | 30215 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
disl | +0.034 |
ados | +0.033 |
Mickey | +0.030 |
vitamins | +0.030 |
array | +0.030 |
Neg logit contributions | |
a | -0.084 |
- | -0.077 |
ah | -0.076 |
be | -0.075 |
ch | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
disl | +0.465 |
ados | +0.455 |
Mickey | +0.444 |
array | +0.441 |
vitamins | +0.438 |
Neg logit contributions | |
a | -0.268 |
- | -0.221 |
ah | -0.217 |
be | -0.213 |
ch | -0.201 |
Token | they |
Token ID | 484 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ados | +0.020 |
Mickey | +0.019 |
disl | +0.019 |
avocado | +0.019 |
Bruce | +0.019 |
Neg logit contributions | |
a | -0.019 |
ah | -0.017 |
be | -0.017 |
- | -0.016 |
ch | -0.015 |
Token | picked |
Token ID | 6497 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
a | +0.038 |
- | +0.033 |
ah | +0.032 |
be | +0.032 |
ch | +0.030 |
Neg logit contributions | |
disl | -0.042 |
ados | -0.041 |
vitamins | -0.039 |
array | -0.039 |
Mickey | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
disl | +0.123 |
array | +0.116 |
vitamins | +0.108 |
ados | +0.105 |
courtroom | +0.104 |
Neg logit contributions | |
a | -0.089 |
- | -0.082 |
ah | -0.071 |
closer | -0.070 |
y | -0.066 |
Token | many |
Token ID | 867 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
disl | +0.042 |
ados | +0.041 |
vitamins | +0.040 |
avocado | +0.039 |
Mickey | +0.039 |
Neg logit contributions | |
a | -0.061 |
- | -0.054 |
be | -0.054 |
ah | -0.054 |
ch | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
a | +0.034 |
fly | +0.027 |
ah | +0.027 |
iest | +0.026 |
be | +0.026 |
Neg logit contributions | |
court | -0.030 |
ados | -0.028 |
avocado | -0.028 |
array | -0.026 |
oranges | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
a | +0.007 |
- | +0.006 |
be | +0.006 |
ch | +0.006 |
ah | +0.006 |
Neg logit contributions | |
ados | -0.005 |
disl | -0.005 |
Mickey | -0.005 |
av | -0.005 |
array | -0.005 |
Token | forget |
Token ID | 6044 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
disl | +0.070 |
ados | +0.066 |
vitamins | +0.065 |
array | +0.064 |
Mickey | +0.064 |
Neg logit contributions | |
a | -0.064 |
- | -0.056 |
be | -0.053 |
ah | -0.053 |
ch | -0.049 |
Token | about |
Token ID | 546 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
a | +0.061 |
- | +0.053 |
ah | +0.052 |
be | +0.051 |
ch | +0.048 |
Neg logit contributions | |
disl | -0.062 |
ados | -0.059 |
vitamins | -0.058 |
array | -0.057 |
Mickey | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
a | +0.050 |
- | +0.044 |
ah | +0.040 |
be | +0.040 |
ch | +0.036 |
Neg logit contributions | |
disl | -0.074 |
ados | -0.073 |
array | -0.071 |
vitamins | -0.070 |
Mickey | -0.069 |
Token | av |
Token ID | 1196 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
disl | +0.022 |
ados | +0.021 |
array | +0.020 |
Mickey | +0.020 |
vitamins | +0.020 |
Neg logit contributions | |
a | -0.019 |
- | -0.017 |
ah | -0.016 |
be | -0.016 |
ch | -0.015 |
Token | oc |
Token ID | 420 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
disl | +0.428 |
ados | +0.420 |
vitamins | +0.405 |
Mickey | +0.402 |
array | +0.401 |
Neg logit contributions | |
a | -0.315 |
- | -0.260 |
be | -0.252 |
ah | -0.251 |
ch | -0.229 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
- | +0.074 |
man | +0.067 |
a | +0.066 |
be | +0.066 |
fly | +0.065 |
Neg logit contributions | |
array | -0.015 |
disl | -0.015 |
vitamins | -0.012 |
mischief | -0.012 |
Mickey | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ados | +0.386 |
court | +0.386 |
disl | +0.386 |
avocado | +0.381 |
vitamins | +0.377 |
Neg logit contributions | |
a | -0.308 |
ah | -0.275 |
be | -0.254 |
ch | -0.246 |
- | -0.243 |
Token | They |
Token ID | 1119 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
a | +0.008 |
- | +0.007 |
be | +0.007 |
ch | +0.007 |
ah | +0.007 |
Neg logit contributions | |
ados | -0.006 |
disl | -0.006 |
array | -0.005 |
Mickey | -0.005 |
av | -0.005 |
Token | just |
Token ID | 655 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
disl | +0.070 |
ados | +0.069 |
array | +0.066 |
vitamins | +0.066 |
Mickey | +0.065 |
Neg logit contributions | |
a | -0.059 |
- | -0.051 |
ah | -0.050 |
be | -0.049 |
ch | -0.045 |
Token | away |
Token ID | 1497 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
disl | +0.140 |
ados | +0.136 |
vitamins | +0.133 |
array | +0.132 |
Mickey | +0.130 |
Neg logit contributions | |
a | -0.065 |
- | -0.053 |
ah | -0.049 |
be | -0.049 |
ch | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
a | +0.034 |
ah | +0.029 |
be | +0.027 |
- | +0.026 |
ch | +0.026 |
Neg logit contributions | |
disl | -0.052 |
ados | -0.051 |
avocado | -0.050 |
Mickey | -0.049 |
array | -0.049 |
Token | She |
Token ID | 1375 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
a | +0.016 |
- | +0.015 |
of | +0.015 |
and | +0.014 |
ch | +0.012 |
Neg logit contributions | |
vitamins | -0.033 |
ados | -0.032 |
disl | -0.032 |
av | -0.032 |
array | -0.031 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
disl | +0.033 |
ados | +0.033 |
vitamins | +0.031 |
array | +0.031 |
Mickey | +0.031 |
Neg logit contributions | |
a | -0.025 |
- | -0.022 |
ah | -0.021 |
be | -0.020 |
ch | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
disl | +0.141 |
array | +0.141 |
ados | +0.141 |
vitamins | +0.137 |
Mickey | +0.133 |
Neg logit contributions | |
a | -0.068 |
- | -0.061 |
of | -0.049 |
be | -0.046 |
closer | -0.046 |
Token | av |
Token ID | 1196 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
a | +0.001 |
- | +0.001 |
of | +0.001 |
on | +0.001 |
closer | +0.001 |
Neg logit contributions | |
disl | -0.001 |
ados | -0.001 |
array | -0.001 |
courtroom | -0.001 |
handed | -0.001 |
Token | oc |
Token ID | 420 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
disl | +0.458 |
ados | +0.445 |
vitamins | +0.431 |
array | +0.431 |
Mickey | +0.423 |
Neg logit contributions | |
a | -0.291 |
- | -0.246 |
ah | -0.235 |
be | -0.232 |
ch | -0.210 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
- | +0.065 |
ah | +0.056 |
man | +0.056 |
a | +0.056 |
rot | +0.054 |
Neg logit contributions | |
array | -0.019 |
mischief | -0.016 |
disl | -0.016 |
vitamins | -0.013 |
Afterwards | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
disl | +0.408 |
ados | +0.395 |
vitamins | +0.383 |
array | +0.377 |
Mickey | +0.377 |
Neg logit contributions | |
a | -0.322 |
- | -0.275 |
ah | -0.270 |
be | -0.265 |
ch | -0.245 |
Token | good |
Token ID | 922 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
a | +0.097 |
ah | +0.085 |
- | +0.084 |
be | +0.083 |
ch | +0.076 |
Neg logit contributions | |
disl | -0.097 |
ados | -0.093 |
vitamins | -0.093 |
Mickey | -0.091 |
avocado | -0.089 |
Token | for |
Token ID | 329 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
disl | +0.031 |
ados | +0.031 |
vitamins | +0.030 |
array | +0.030 |
Mickey | +0.030 |
Neg logit contributions | |
a | -0.015 |
ah | -0.011 |
- | -0.011 |
be | -0.011 |
ch | -0.010 |
Token | something |
Token ID | 1223 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
disl | +0.118 |
ados | +0.115 |
array | +0.114 |
vitamins | +0.111 |
Mickey | +0.109 |
Neg logit contributions | |
a | -0.087 |
- | -0.076 |
ah | -0.067 |
be | -0.064 |
closer | -0.062 |
Token | new |
Token ID | 649 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
disl | +0.070 |
ados | +0.068 |
vitamins | +0.066 |
avocado | +0.065 |
Mickey | +0.065 |
Neg logit contributions | |
a | -0.060 |
be | -0.053 |
ah | -0.053 |
- | -0.051 |
ch | -0.049 |
Token | ! |
Token ID | 0 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
disl | +0.031 |
ados | +0.030 |
vitamins | +0.029 |
avocado | +0.029 |
court | +0.028 |
Neg logit contributions | |
a | -0.023 |
be | -0.022 |
ch | -0.021 |
ah | -0.020 |
passenger | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
disl | +0.007 |
array | +0.007 |
ados | +0.006 |
vitamins | +0.006 |
av | +0.006 |
Neg logit contributions | |
a | -0.010 |
- | -0.008 |
ah | -0.008 |
of | -0.008 |
be | -0.008 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
disl | +0.030 |
ados | +0.030 |
array | +0.029 |
vitamins | +0.028 |
Mickey | +0.027 |
Neg logit contributions | |
a | -0.022 |
- | -0.019 |
ah | -0.018 |
be | -0.018 |
ch | -0.016 |
Token | av |
Token ID | 1196 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
disl | +0.072 |
ados | +0.070 |
vitamins | +0.068 |
array | +0.068 |
Mickey | +0.067 |
Neg logit contributions | |
a | -0.059 |
- | -0.051 |
ah | -0.049 |
be | -0.049 |
ch | -0.045 |
Token | oc |
Token ID | 420 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
disl | +0.455 |
ados | +0.443 |
vitamins | +0.429 |
array | +0.428 |
Mickey | +0.422 |
Neg logit contributions | |
a | -0.292 |
- | -0.247 |
ah | -0.236 |
be | -0.233 |
ch | -0.211 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
- | +0.074 |
a | +0.069 |
ah | +0.066 |
man | +0.064 |
fly | +0.064 |
Neg logit contributions | |
array | -0.018 |
mischief | -0.014 |
disl | -0.014 |
vitamins | -0.013 |
court | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
disl | +0.368 |
ados | +0.356 |
vitamins | +0.344 |
Mickey | +0.342 |
avocado | +0.339 |
Neg logit contributions | |
a | -0.357 |
be | -0.308 |
- | -0.307 |
ah | -0.304 |
ch | -0.292 |
Token | the |
Token ID | 262 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
disl | +0.002 |
ados | +0.002 |
array | +0.002 |
vitamins | +0.002 |
Mickey | +0.002 |
Neg logit contributions | |
a | -0.002 |
- | -0.001 |
ah | -0.001 |
be | -0.001 |
ch | -0.001 |
Token | most |
Token ID | 749 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
disl | +0.005 |
ados | +0.005 |
array | +0.004 |
vitamins | +0.004 |
Mickey | +0.004 |
Neg logit contributions | |
a | -0.003 |
- | -0.003 |
ah | -0.002 |
be | -0.002 |
ch | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
disl | +0.016 |
Mickey | +0.016 |
ados | +0.016 |
avocado | +0.015 |
Bruce | +0.015 |
Neg logit contributions | |
a | -0.019 |
- | -0.017 |
be | -0.017 |
ah | -0.017 |
ch | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
court | +0.099 |
Bruce | +0.094 |
ados | +0.094 |
Mickey | +0.093 |
Freddy | +0.090 |
Neg logit contributions | |
a | -0.093 |
ah | -0.083 |
be | -0.079 |
iest | -0.078 |
fly | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ados | +0.002 |
vitamins | +0.002 |
disl | +0.002 |
array | +0.002 |
iveness | +0.002 |
Neg logit contributions | |
a | -0.001 |
- | -0.001 |
closer | -0.001 |
ah | -0.001 |
be | -0.001 |
Token | closest |
Token ID | 11706 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
disl | +0.007 |
ados | +0.007 |
vitamins | +0.007 |
array | +0.007 |
Mickey | +0.006 |
Neg logit contributions | |
a | -0.010 |
- | -0.009 |
be | -0.008 |
ah | -0.008 |
ch | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
a | +0.094 |
ah | +0.085 |
be | +0.082 |
- | +0.080 |
ch | +0.079 |
Neg logit contributions | |
ados | -0.069 |
court | -0.068 |
Mickey | -0.067 |
avocado | -0.067 |
disl | -0.066 |
Token | chard |
Token ID | 30215 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
disl | +0.035 |
ados | +0.033 |
vitamins | +0.031 |
Mickey | +0.031 |
array | +0.030 |
Neg logit contributions | |
a | -0.082 |
- | -0.076 |
ah | -0.074 |
be | -0.074 |
ch | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ados | +0.436 |
Mickey | +0.434 |
avocado | +0.432 |
disl | +0.432 |
court | +0.432 |
Neg logit contributions | |
a | -0.261 |
ah | -0.235 |
ch | -0.233 |
be | -0.222 |
- | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
a | +0.021 |
of | +0.019 |
ch | +0.017 |
be | +0.017 |
- | +0.017 |
Neg logit contributions | |
disl | -0.024 |
vitamins | -0.023 |
array | -0.022 |
ados | -0.021 |
av | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
disl | +0.017 |
ados | +0.017 |
vitamins | +0.017 |
array | +0.016 |
avocado | +0.016 |
Neg logit contributions | |
a | -0.015 |
- | -0.013 |
be | -0.012 |
ah | -0.012 |
ch | -0.011 |
Token | At |
Token ID | 2953 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
disl | +0.017 |
ados | +0.016 |
vitamins | +0.016 |
array | +0.016 |
Mickey | +0.016 |
Neg logit contributions | |
a | -0.013 |
- | -0.012 |
ah | -0.011 |
be | -0.011 |
fly | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
a | +0.064 |
- | +0.055 |
be | +0.054 |
ah | +0.053 |
ch | +0.049 |
Neg logit contributions | |
ados | -0.067 |
disl | -0.066 |
Mickey | -0.066 |
avocado | -0.064 |
Bruce | -0.064 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
disl | +0.103 |
ados | +0.101 |
array | +0.098 |
vitamins | +0.097 |
Mickey | +0.095 |
Neg logit contributions | |
a | -0.073 |
- | -0.062 |
be | -0.059 |
ah | -0.058 |
ch | -0.052 |
Token | that |
Token ID | 326 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
a | +0.028 |
ah | +0.024 |
be | +0.024 |
ch | +0.021 |
passenger | +0.021 |
Neg logit contributions | |
disl | -0.034 |
ados | -0.033 |
vitamins | -0.032 |
Mickey | -0.032 |
avocado | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
disl | +0.004 |
ados | +0.004 |
array | +0.004 |
vitamins | +0.004 |
avocado | +0.003 |
Neg logit contributions | |
a | -0.003 |
- | -0.002 |
ah | -0.002 |
be | -0.002 |
ch | -0.002 |
Token | produced |
Token ID | 4635 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
disl | +0.051 |
ados | +0.049 |
vitamins | +0.048 |
Mickey | +0.048 |
array | +0.047 |
Neg logit contributions | |
a | -0.035 |
- | -0.029 |
ah | -0.029 |
be | -0.028 |
ch | -0.026 |
Token | more |
Token ID | 517 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
a | +0.054 |
- | +0.047 |
be | +0.043 |
ah | +0.043 |
ch | +0.039 |
Neg logit contributions | |
disl | -0.074 |
ados | -0.070 |
array | -0.070 |
vitamins | -0.067 |
Mickey | -0.066 |
Token | av |
Token ID | 1196 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
disl | +0.002 |
array | +0.002 |
ados | +0.001 |
Mickey | +0.001 |
courtroom | +0.001 |
Neg logit contributions | |
- | -0.002 |
a | -0.002 |
of | -0.002 |
be | -0.002 |
iest | -0.002 |
Token | oc |
Token ID | 420 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
disl | +0.473 |
ados | +0.450 |
array | +0.445 |
vitamins | +0.443 |
Mickey | +0.430 |
Neg logit contributions | |
a | -0.278 |
- | -0.241 |
be | -0.223 |
ah | -0.222 |
ch | -0.198 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
- | +0.079 |
a | +0.072 |
be | +0.069 |
ah | +0.068 |
man | +0.066 |
Neg logit contributions | |
array | -0.017 |
disl | -0.016 |
mischief | -0.012 |
vitamins | -0.011 |
court | -0.010 |
Token | than |
Token ID | 621 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ados | +0.445 |
disl | +0.443 |
Mickey | +0.431 |
avocado | +0.428 |
vitamins | +0.426 |
Neg logit contributions | |
a | -0.274 |
ah | -0.233 |
be | -0.223 |
- | -0.214 |
ch | -0.211 |
Token | ever |
Token ID | 1683 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
a | +0.011 |
- | +0.010 |
ah | +0.009 |
be | +0.009 |
ch | +0.008 |
Neg logit contributions | |
disl | -0.014 |
ados | -0.013 |
array | -0.013 |
vitamins | -0.013 |
Mickey | -0.012 |
Token | before |
Token ID | 878 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
a | +0.116 |
- | +0.096 |
ah | +0.093 |
be | +0.093 |
ch | +0.085 |
Neg logit contributions | |
disl | -0.180 |
ados | -0.175 |
vitamins | -0.172 |
array | -0.169 |
Mickey | -0.167 |
Token | on |
Token ID | 319 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ados | +0.013 |
Mickey | +0.012 |
vitamins | +0.012 |
avocado | +0.012 |
array | +0.012 |
Neg logit contributions | |
a | -0.005 |
fly | -0.003 |
- | -0.003 |
be | -0.003 |
ah | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
a | +0.019 |
be | +0.016 |
ah | +0.016 |
- | +0.015 |
ch | +0.014 |
Neg logit contributions | |
ados | -0.035 |
disl | -0.035 |
Mickey | -0.034 |
vitamins | -0.033 |
array | -0.033 |
Token | whenever |
Token ID | 8797 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
disl | +0.014 |
ados | +0.014 |
vitamins | +0.013 |
Mickey | +0.013 |
array | +0.013 |
Neg logit contributions | |
a | -0.018 |
- | -0.016 |
ah | -0.015 |
be | -0.015 |
ch | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
disl | +0.142 |
ados | +0.138 |
vitamins | +0.133 |
array | +0.133 |
avocado | +0.126 |
Neg logit contributions | |
a | -0.132 |
- | -0.116 |
ah | -0.109 |
be | -0.108 |
ch | -0.102 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
a | +0.040 |
- | +0.036 |
ah | +0.035 |
be | +0.033 |
y | +0.033 |
Neg logit contributions | |
disl | -0.066 |
ados | -0.064 |
vitamins | -0.062 |
array | -0.061 |
Mickey | -0.059 |
Token | av |
Token ID | 1196 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
disl | +0.220 |
array | +0.214 |
vitamins | +0.205 |
ados | +0.205 |
iveness | +0.194 |
Neg logit contributions | |
- | -0.073 |
a | -0.070 |
of | -0.058 |
closer | -0.053 |
be | -0.049 |
Token | oc |
Token ID | 420 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
disl | +0.468 |
ados | +0.446 |
vitamins | +0.439 |
array | +0.439 |
Mickey | +0.424 |
Neg logit contributions | |
a | -0.281 |
- | -0.244 |
ah | -0.230 |
be | -0.225 |
ch | -0.203 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
- | +0.085 |
ah | +0.071 |
be | +0.071 |
a | +0.071 |
man | +0.070 |
Neg logit contributions | |
array | -0.027 |
disl | -0.023 |
mischief | -0.022 |
vitamins | -0.020 |
Penny | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
disl | +0.455 |
ados | +0.453 |
Mickey | +0.439 |
avocado | +0.434 |
av | +0.427 |
Neg logit contributions | |
a | -0.264 |
ah | -0.214 |
be | -0.212 |
- | -0.207 |
ch | -0.190 |
Token | they |
Token ID | 484 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
disl | +0.018 |
ados | +0.017 |
vitamins | +0.016 |
Mickey | +0.016 |
array | +0.016 |
Neg logit contributions | |
a | -0.016 |
- | -0.014 |
ah | -0.013 |
be | -0.013 |
ch | -0.012 |
Token | would |
Token ID | 561 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
a | +0.035 |
- | +0.028 |
ah | +0.027 |
be | +0.026 |
ch | +0.023 |
Neg logit contributions | |
disl | -0.068 |
ados | -0.067 |
array | -0.065 |
vitamins | -0.065 |
Mickey | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
a | +0.119 |
ah | +0.101 |
- | +0.099 |
be | +0.097 |
ch | +0.094 |
Neg logit contributions | |
disl | -0.159 |
ados | -0.156 |
array | -0.151 |
vitamins | -0.151 |
Mickey | -0.149 |
Token | her |
Token ID | 607 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
a | +0.023 |
- | +0.022 |
of | +0.020 |
be | +0.019 |
ah | +0.019 |
Neg logit contributions | |
disl | -0.024 |
vitamins | -0.023 |
array | -0.022 |
ados | -0.021 |
Bruce | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
a | +0.001 |
- | +0.001 |
of | +0.001 |
be | +0.001 |
friend | +0.001 |
Neg logit contributions | |
disl | -0.002 |
array | -0.002 |
vitamins | -0.002 |
ados | -0.002 |
iveness | -0.002 |
Token | sorted |
Token ID | 23243 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
a | +0.011 |
ah | +0.009 |
- | +0.009 |
be | +0.009 |
fly | +0.009 |
Neg logit contributions | |
ados | -0.009 |
disl | -0.009 |
array | -0.008 |
Mickey | -0.008 |
vitamins | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
a | +0.046 |
- | +0.041 |
be | +0.036 |
ah | +0.035 |
closer | +0.033 |
Neg logit contributions | |
disl | -0.072 |
ados | -0.066 |
vitamins | -0.066 |
array | -0.066 |
Mickey | -0.063 |
Token | av |
Token ID | 1196 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
disl | +0.009 |
array | +0.007 |
Afterwards | +0.007 |
irs | +0.006 |
Bruce | +0.006 |
Neg logit contributions | |
- | -0.014 |
a | -0.013 |
of | -0.013 |
be | -0.012 |
in | -0.012 |
Token | oc |
Token ID | 420 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
disl | +0.464 |
array | +0.425 |
ados | +0.425 |
vitamins | +0.424 |
Bruce | +0.410 |
Neg logit contributions | |
a | -0.298 |
- | -0.267 |
be | -0.242 |
ah | -0.238 |
ch | -0.215 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
- | +0.060 |
a | +0.053 |
man | +0.052 |
ah | +0.051 |
be | +0.051 |
Neg logit contributions | |
disl | -0.017 |
array | -0.016 |
mischief | -0.013 |
vitamins | -0.013 |
Afterwards | -0.011 |
Token | into |
Token ID | 656 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ados | +0.481 |
disl | +0.472 |
vitamins | +0.458 |
Mickey | +0.457 |
avocado | +0.457 |
Neg logit contributions | |
a | -0.241 |
ah | -0.202 |
be | -0.187 |
- | -0.186 |
ch | -0.175 |
Token | piles |
Token ID | 30935 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
disl | +0.194 |
ados | +0.182 |
vitamins | +0.177 |
array | +0.177 |
Mickey | +0.169 |
Neg logit contributions | |
a | -0.128 |
- | -0.108 |
be | -0.101 |
ah | -0.093 |
closer | -0.090 |
Token | according |
Token ID | 1864 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ados | +0.259 |
avocado | +0.248 |
av | +0.242 |
vitamins | +0.240 |
disl | +0.235 |
Neg logit contributions | |
a | -0.193 |
ah | -0.179 |
ch | -0.166 |
be | -0.160 |
fly | -0.158 |
Token | from |
Token ID | 422 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
ados | +0.166 |
disl | +0.165 |
Mickey | +0.165 |
court | +0.161 |
avocado | +0.160 |
Neg logit contributions | |
a | -0.111 |
ah | -0.096 |
- | -0.091 |
be | -0.089 |
ch | -0.085 |
Token | disturbing |
Token ID | 14851 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
disl | +0.236 |
ados | +0.227 |
vitamins | +0.220 |
array | +0.219 |
Mickey | +0.212 |
Neg logit contributions | |
a | -0.183 |
- | -0.161 |
be | -0.150 |
ah | -0.148 |
ch | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
a | +0.118 |
- | +0.104 |
be | +0.098 |
ah | +0.097 |
ch | +0.091 |
Neg logit contributions | |
disl | -0.132 |
ados | -0.127 |
vitamins | -0.123 |
array | -0.123 |
Mickey | -0.120 |
Token | cherry |
Token ID | 23612 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
disl | +0.007 |
ados | +0.007 |
array | +0.007 |
vitamins | +0.007 |
Mickey | +0.006 |
Neg logit contributions | |
a | -0.008 |
- | -0.007 |
be | -0.007 |
ah | -0.007 |
ch | -0.007 |
Token | or |
Token ID | 393 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
disl | +0.020 |
ados | +0.020 |
Mickey | +0.019 |
vitamins | +0.019 |
avocado | +0.019 |
Neg logit contributions | |
a | -0.015 |
- | -0.013 |
ah | -0.012 |
be | -0.012 |
ch | -0.011 |
Token | chard |
Token ID | 30215 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
disl | +0.060 |
ados | +0.058 |
array | +0.056 |
vitamins | +0.056 |
Mickey | +0.054 |
Neg logit contributions | |
a | -0.051 |
- | -0.044 |
be | -0.042 |
ah | -0.040 |
closer | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
disl | +0.451 |
ados | +0.447 |
Mickey | +0.435 |
avocado | +0.431 |
vitamins | +0.430 |
Neg logit contributions | |
a | -0.275 |
ah | -0.232 |
be | -0.224 |
- | -0.220 |
ch | -0.214 |
Token | Had |
Token ID | 11161 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
a | +0.030 |
- | +0.025 |
ah | +0.025 |
be | +0.024 |
of | +0.024 |
Neg logit contributions | |
disl | -0.036 |
array | -0.035 |
ados | -0.034 |
vitamins | -0.034 |
avocado | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
a | +0.053 |
- | +0.046 |
ah | +0.044 |
be | +0.044 |
ch | +0.040 |
Neg logit contributions | |
disl | -0.059 |
ados | -0.057 |
vitamins | -0.055 |
array | -0.054 |
Mickey | -0.054 |
Token | not |
Token ID | 407 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
disl | +0.007 |
ados | +0.007 |
vitamins | +0.007 |
array | +0.007 |
Mickey | +0.007 |
Neg logit contributions | |
a | -0.006 |
- | -0.005 |
ah | -0.005 |
be | -0.005 |
ch | -0.004 |
Token | been |
Token ID | 587 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
disl | +0.058 |
ados | +0.056 |
vitamins | +0.054 |
array | +0.053 |
Mickey | +0.053 |
Neg logit contributions | |
a | -0.062 |
- | -0.054 |
ah | -0.053 |
be | -0.052 |
ch | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
disl | +0.077 |
ados | +0.075 |
vitamins | +0.073 |
avocado | +0.073 |
Mickey | +0.073 |
Neg logit contributions | |
a | -0.050 |
ah | -0.043 |
be | -0.041 |
ch | -0.039 |
- | -0.039 |
Token | shared |
Token ID | 4888 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
a | +0.020 |
- | +0.018 |
ah | +0.017 |
be | +0.017 |
y | +0.015 |
Neg logit contributions | |
disl | -0.029 |
ados | -0.028 |
array | -0.028 |
vitamins | -0.027 |
Mickey | -0.026 |
Token | everything |
Token ID | 2279 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
disl | +0.057 |
array | +0.056 |
ados | +0.054 |
vitamins | +0.054 |
Mickey | +0.052 |
Neg logit contributions | |
a | -0.038 |
- | -0.035 |
be | -0.028 |
ah | -0.028 |
of | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
disl | +0.034 |
ados | +0.034 |
avocado | +0.032 |
vitamins | +0.032 |
Mickey | +0.032 |
Neg logit contributions | |
a | -0.019 |
ah | -0.017 |
be | -0.016 |
- | -0.015 |
ch | -0.015 |
Token | including |
Token ID | 1390 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
disl | +0.024 |
ados | +0.024 |
array | +0.023 |
vitamins | +0.023 |
Mickey | +0.022 |
Neg logit contributions | |
a | -0.016 |
- | -0.014 |
ah | -0.013 |
be | -0.013 |
ch | -0.011 |
Token | av |
Token ID | 1196 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
a | +0.004 |
- | +0.004 |
be | +0.004 |
ah | +0.004 |
of | +0.003 |
Neg logit contributions | |
disl | -0.005 |
array | -0.004 |
ados | -0.004 |
vitamins | -0.004 |
Mickey | -0.004 |
Token | oc |
Token ID | 420 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
disl | +0.475 |
ados | +0.453 |
array | +0.448 |
vitamins | +0.445 |
Mickey | +0.432 |
Neg logit contributions | |
a | -0.273 |
- | -0.239 |
ah | -0.221 |
be | -0.220 |
ch | -0.193 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
- | +0.066 |
be | +0.055 |
man | +0.054 |
a | +0.054 |
ah | +0.053 |
Neg logit contributions | |
array | -0.019 |
mischief | -0.019 |
court | -0.016 |
disl | -0.016 |
vitamins | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
disl | +0.449 |
ados | +0.447 |
vitamins | +0.430 |
avocado | +0.429 |
Mickey | +0.425 |
Neg logit contributions | |
a | -0.276 |
ah | -0.232 |
be | -0.224 |
- | -0.217 |
ch | -0.213 |
Token | They |
Token ID | 1119 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
a | +0.027 |
of | +0.025 |
- | +0.025 |
ch | +0.025 |
ah | +0.025 |
Neg logit contributions | |
ados | -0.026 |
disl | -0.026 |
array | -0.025 |
av | -0.024 |
handed | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
disl | +0.052 |
ados | +0.051 |
array | +0.051 |
vitamins | +0.048 |
mischief | +0.047 |
Neg logit contributions | |
a | -0.033 |
ah | -0.028 |
- | -0.026 |
be | -0.025 |
y | -0.024 |
Token | every |
Token ID | 790 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ados | +0.102 |
disl | +0.100 |
Mickey | +0.099 |
avocado | +0.098 |
court | +0.096 |
Neg logit contributions | |
a | -0.077 |
ah | -0.064 |
be | -0.063 |
- | -0.062 |
ch | -0.060 |
Token | day |
Token ID | 1110 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
ados | +0.051 |
disl | +0.051 |
avocado | +0.051 |
Mickey | +0.050 |
vitamins | +0.049 |
Neg logit contributions | |
a | -0.050 |
be | -0.042 |
- | -0.041 |
ah | -0.041 |
ch | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
a | +0.039 |
ah | +0.032 |
be | +0.030 |
- | +0.029 |
ch | +0.029 |
Neg logit contributions | |
ados | -0.061 |
disl | -0.059 |
Mickey | -0.059 |
avocado | -0.058 |
vitamins | -0.058 |
Token | supply |
Token ID | 5127 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ados | +0.006 |
array | +0.006 |
disl | +0.005 |
vitamins | +0.005 |
Mickey | +0.005 |
Neg logit contributions | |
a | -0.005 |
- | -0.004 |
ah | -0.004 |
closer | -0.004 |
of | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
a | +0.113 |
- | +0.108 |
of | +0.091 |
be | +0.087 |
closer | +0.084 |
Neg logit contributions | |
disl | -0.158 |
array | -0.153 |
vitamins | -0.141 |
ados | -0.140 |
courtroom | -0.135 |
Token | av |
Token ID | 1196 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
disl | +0.011 |
array | +0.010 |
Afterwards | +0.009 |
ados | +0.009 |
vitamins | +0.009 |
Neg logit contributions | |
a | -0.011 |
- | -0.011 |
be | -0.010 |
of | -0.009 |
closer | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
disl | +0.491 |
array | +0.463 |
ados | +0.459 |
vitamins | +0.456 |
Mickey | +0.438 |
Neg logit contributions | |
a | -0.265 |
- | -0.234 |
be | -0.209 |
ah | -0.207 |
y | -0.183 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
- | +0.082 |
a | +0.075 |
man | +0.073 |
be | +0.072 |
fly | +0.072 |
Neg logit contributions | |
disl | -0.018 |
array | -0.017 |
vitamins | -0.014 |
mischief | -0.013 |
Bruce | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ados | +0.450 |
disl | +0.447 |
avocado | +0.433 |
vitamins | +0.433 |
Mickey | +0.430 |
Neg logit contributions | |
a | -0.266 |
ah | -0.227 |
be | -0.218 |
- | -0.213 |
ch | -0.208 |
Token | And |
Token ID | 843 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
a | +0.023 |
ah | +0.022 |
of | +0.021 |
ch | +0.021 |
- | +0.021 |
Neg logit contributions | |
disl | -0.017 |
array | -0.016 |
ados | -0.015 |
vitamins | -0.015 |
av | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
a | +0.066 |
ah | +0.057 |
- | +0.057 |
be | +0.057 |
ch | +0.054 |
Neg logit contributions | |
disl | -0.070 |
ados | -0.068 |
vitamins | -0.066 |
Mickey | -0.066 |
avocado | -0.065 |
Token | weather |
Token ID | 6193 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
disl | +0.009 |
array | +0.008 |
vitamins | +0.007 |
ados | +0.007 |
Bruce | +0.007 |
Neg logit contributions | |
a | -0.009 |
- | -0.009 |
be | -0.009 |
ah | -0.008 |
closer | -0.008 |
Token | before |
Token ID | 878 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ados | +0.059 |
Mickey | +0.058 |
avocado | +0.057 |
disl | +0.056 |
av | +0.055 |
Neg logit contributions | |
a | -0.043 |
be | -0.036 |
ah | -0.035 |
- | -0.032 |
ch | -0.031 |
Token | he |
Token ID | 339 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
disl | +0.125 |
ados | +0.118 |
vitamins | +0.115 |
array | +0.113 |
avocado | +0.109 |
Neg logit contributions | |
a | -0.101 |
- | -0.099 |
be | -0.090 |
ah | -0.089 |
ch | -0.088 |
Token | picked |
Token ID | 6497 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
disl | +0.009 |
ados | +0.009 |
vitamins | +0.008 |
array | +0.008 |
Mickey | +0.008 |
Neg logit contributions | |
a | -0.007 |
- | -0.007 |
ah | -0.006 |
be | -0.006 |
ch | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
disl | +0.127 |
array | +0.121 |
vitamins | +0.113 |
ados | +0.111 |
courtroom | +0.109 |
Neg logit contributions | |
- | -0.077 |
a | -0.077 |
ah | -0.062 |
closer | -0.061 |
on | -0.059 |
Token | av |
Token ID | 1196 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
- | +0.049 |
a | +0.045 |
closer | +0.041 |
on | +0.041 |
ah | +0.041 |
Neg logit contributions | |
disl | -0.030 |
array | -0.030 |
vitamins | -0.026 |
Bruce | -0.024 |
iveness | -0.023 |
Token | oc |
Token ID | 420 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
disl | +0.469 |
ados | +0.449 |
vitamins | +0.441 |
array | +0.439 |
Mickey | +0.427 |
Neg logit contributions | |
a | -0.278 |
- | -0.241 |
ah | -0.227 |
be | -0.222 |
ch | -0.200 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
- | +0.067 |
ah | +0.058 |
a | +0.057 |
man | +0.057 |
be | +0.056 |
Neg logit contributions | |
array | -0.016 |
disl | -0.015 |
vitamins | -0.012 |
mischief | -0.012 |
Bruce | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
disl | +0.468 |
ados | +0.464 |
vitamins | +0.447 |
Mickey | +0.446 |
array | +0.444 |
Neg logit contributions | |
a | -0.258 |
- | -0.207 |
ah | -0.205 |
be | -0.202 |
ch | -0.182 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
a | +0.030 |
- | +0.030 |
ah | +0.028 |
be | +0.028 |
ch | +0.027 |
Neg logit contributions | |
disl | -0.027 |
array | -0.027 |
ados | -0.026 |
vitamins | -0.025 |
av | -0.024 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
a | +0.110 |
- | +0.097 |
ah | +0.095 |
be | +0.095 |
ch | +0.088 |
Neg logit contributions | |
disl | -0.091 |
ados | -0.088 |
vitamins | -0.084 |
array | -0.084 |
Mickey | -0.083 |
Token | says |
Token ID | 1139 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
a | +0.023 |
- | +0.021 |
ah | +0.020 |
be | +0.020 |
y | +0.019 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.016 |
vitamins | -0.015 |
array | -0.015 |
Mickey | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ados | +0.065 |
disl | +0.064 |
vitamins | +0.063 |
avocado | +0.062 |
Mickey | +0.062 |
Neg logit contributions | |
a | -0.040 |
ah | -0.033 |
- | -0.033 |
be | -0.032 |
ch | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
a | +0.015 |
be | +0.012 |
- | +0.012 |
ah | +0.011 |
closer | +0.010 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.036 |
array | -0.035 |
vitamins | -0.034 |
Mickey | -0.033 |
Token | av |
Token ID | 1196 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
a | +0.080 |
- | +0.070 |
be | +0.066 |
ah | +0.065 |
ch | +0.061 |
Neg logit contributions | |
disl | -0.087 |
ados | -0.083 |
array | -0.081 |
vitamins | -0.080 |
Mickey | -0.078 |
Token | oc |
Token ID | 420 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
ados | +0.418 |
disl | +0.414 |
vitamins | +0.400 |
Mickey | +0.397 |
array | +0.394 |
Neg logit contributions | |
a | -0.323 |
- | -0.267 |
ah | -0.262 |
be | -0.261 |
ch | -0.244 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
- | +0.055 |
a | +0.053 |
ah | +0.050 |
be | +0.049 |
man | +0.048 |
Neg logit contributions | |
disl | -0.010 |
array | -0.009 |
mischief | -0.007 |
vitamins | -0.007 |
Mickey | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ados | +0.415 |
Mickey | +0.404 |
disl | +0.401 |
avocado | +0.400 |
vitamins | +0.399 |
Neg logit contributions | |
a | -0.292 |
ah | -0.264 |
be | -0.263 |
ch | -0.246 |
- | -0.239 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
a | +0.013 |
- | +0.011 |
of | +0.011 |
be | +0.010 |
closer | +0.010 |
Neg logit contributions | |
disl | -0.019 |
array | -0.018 |
Mickey | -0.018 |
ados | -0.017 |
vitamins | -0.017 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
a | +0.075 |
- | +0.066 |
be | +0.058 |
ah | +0.058 |
y | +0.055 |
Neg logit contributions | |
disl | -0.089 |
ados | -0.088 |
Mickey | -0.083 |
Bruce | -0.081 |
array | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
disl | +0.283 |
array | +0.274 |
ados | +0.255 |
mischief | +0.250 |
vitamins | +0.249 |
Neg logit contributions | |
a | -0.065 |
- | -0.060 |
closer | -0.048 |
of | -0.047 |
be | -0.042 |
Token | try |
Token ID | 1949 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
array | +0.012 |
ados | +0.011 |
disl | +0.011 |
vitamins | +0.011 |
Bruce | +0.010 |
Neg logit contributions | |
a | -0.009 |
- | -0.008 |
of | -0.008 |
ah | -0.008 |
be | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
disl | +0.119 |
ados | +0.116 |
Mickey | +0.112 |
vitamins | +0.111 |
avocado | +0.109 |
Neg logit contributions | |
a | -0.119 |
be | -0.101 |
ah | -0.101 |
- | -0.099 |
ch | -0.092 |
Token | had |
Token ID | 550 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
a | +0.031 |
ah | +0.028 |
- | +0.028 |
ch | +0.027 |
be | +0.026 |
Neg logit contributions | |
disl | -0.036 |
Mickey | -0.036 |
vitamins | -0.035 |
ados | -0.035 |
Bruce | -0.035 |
Token | never |
Token ID | 1239 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
a | +0.019 |
- | +0.016 |
be | +0.015 |
ah | +0.015 |
ch | +0.014 |
Neg logit contributions | |
disl | -0.021 |
ados | -0.020 |
array | -0.019 |
vitamins | -0.019 |
Mickey | -0.019 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
a | +0.068 |
- | +0.059 |
ah | +0.057 |
be | +0.056 |
ch | +0.052 |
Neg logit contributions | |
disl | -0.071 |
ados | -0.069 |
vitamins | -0.067 |
array | -0.066 |
Mickey | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
a | +0.071 |
- | +0.069 |
ah | +0.059 |
closer | +0.058 |
of | +0.057 |
Neg logit contributions | |
disl | -0.139 |
array | -0.135 |
vitamins | -0.126 |
ados | -0.122 |
courtroom | -0.121 |
Token | av |
Token ID | 1196 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
disl | +0.010 |
ados | +0.010 |
array | +0.009 |
vitamins | +0.009 |
Mickey | +0.009 |
Neg logit contributions | |
a | -0.010 |
- | -0.009 |
ah | -0.008 |
be | -0.008 |
ch | -0.008 |
Token | oc |
Token ID | 420 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
disl | +0.450 |
ados | +0.437 |
vitamins | +0.425 |
array | +0.422 |
Mickey | +0.416 |
Neg logit contributions | |
a | -0.292 |
- | -0.247 |
ah | -0.236 |
be | -0.234 |
ch | -0.212 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
- | +0.088 |
a | +0.082 |
ah | +0.081 |
be | +0.080 |
man | +0.080 |
Neg logit contributions | |
disl | -0.021 |
array | -0.020 |
vitamins | -0.019 |
mischief | -0.015 |
Mickey | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
avocado | +0.410 |
ados | +0.409 |
court | +0.399 |
disl | +0.398 |
Mickey | +0.397 |
Neg logit contributions | |
a | -0.296 |
ah | -0.245 |
be | -0.237 |
- | -0.234 |
ch | -0.226 |
Token | They |
Token ID | 1119 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
a | +0.017 |
- | +0.015 |
be | +0.014 |
passenger | +0.014 |
too | +0.013 |
Neg logit contributions | |
ados | -0.019 |
av | -0.019 |
avocado | -0.018 |
disl | -0.017 |
vitamins | -0.017 |
Token | wished |
Token ID | 16555 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
disl | +0.048 |
ados | +0.047 |
vitamins | +0.044 |
array | +0.043 |
avocado | +0.042 |
Neg logit contributions | |
a | -0.067 |
- | -0.059 |
be | -0.058 |
ah | -0.057 |
ch | -0.053 |
Token | sun |
Token ID | 4252 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
disl | +0.003 |
avocado | +0.003 |
ados | +0.003 |
array | +0.003 |
Mickey | +0.003 |
Neg logit contributions | |
a | -0.004 |
ah | -0.003 |
- | -0.003 |
be | -0.003 |
ba | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
a | +0.027 |
ah | +0.021 |
vy | +0.020 |
ch | +0.020 |
racer | +0.020 |
Neg logit contributions | |
ados | -0.033 |
Mickey | -0.032 |
avocado | -0.031 |
array | -0.030 |
yard | -0.030 |
Token | Boris |
Token ID | 25026 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
a | +0.006 |
- | +0.005 |
ah | +0.005 |
be | +0.005 |
ch | +0.005 |
Neg logit contributions | |
disl | -0.007 |
ados | -0.006 |
Mickey | -0.006 |
vitamins | -0.006 |
avocado | -0.006 |
Token | knew |
Token ID | 2993 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
disl | +0.006 |
Mickey | +0.005 |
array | +0.005 |
vitamins | +0.005 |
Bruce | +0.005 |
Neg logit contributions | |
a | -0.005 |
ah | -0.004 |
ch | -0.004 |
less | -0.004 |
- | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
a | +0.006 |
be | +0.005 |
ah | +0.005 |
- | +0.005 |
ch | +0.005 |
Neg logit contributions | |
disl | -0.005 |
ados | -0.004 |
Mickey | -0.004 |
Bruce | -0.004 |
vitamins | -0.004 |
Token | 'd |
Token ID | 1549 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
a | +0.003 |
be | +0.003 |
ch | +0.003 |
ah | +0.003 |
passenger | +0.003 |
Neg logit contributions | |
Mickey | -0.004 |
disl | -0.004 |
vitamins | -0.004 |
Bruce | -0.003 |
avocado | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
a | +0.323 |
- | +0.286 |
be | +0.273 |
ah | +0.273 |
ch | +0.261 |
Neg logit contributions | |
disl | -0.327 |
vitamins | -0.306 |
array | -0.290 |
Mickey | -0.289 |
avocado | -0.289 |
Token | a |
Token ID | 257 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ados | +0.040 |
disl | +0.039 |
vitamins | +0.039 |
Mickey | +0.039 |
avocado | +0.039 |
Neg logit contributions | |
a | -0.044 |
be | -0.041 |
ah | -0.039 |
- | -0.037 |
ch | -0.036 |
Token | true |
Token ID | 2081 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
a | +0.040 |
be | +0.036 |
ah | +0.035 |
- | +0.035 |
as | +0.035 |
Neg logit contributions | |
avocado | -0.035 |
Mickey | -0.035 |
disl | -0.035 |
Bruce | -0.032 |
av | -0.032 |
Token | companion |
Token ID | 15185 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
avocado | +0.000 |
av | +0.000 |
Mickey | +0.000 |
vitamins | +0.000 |
Bruce | +0.000 |
Neg logit contributions | |
a | -0.000 |
be | -0.000 |
as | -0.000 |
Rex | -0.000 |
z | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
a | +0.136 |
be | +0.119 |
ch | +0.119 |
ah | +0.116 |
- | +0.107 |
Neg logit contributions | |
Bruce | -0.162 |
ados | -0.157 |
Mickey | -0.157 |
avocado | -0.153 |
court | -0.151 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
a | +0.062 |
- | +0.054 |
be | +0.054 |
ah | +0.053 |
less | +0.052 |
Neg logit contributions | |
disl | -0.063 |
ados | -0.061 |
Mickey | -0.060 |
avocado | -0.059 |
array | -0.059 |
Token | about |
Token ID | 546 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
disl | +0.078 |
ados | +0.077 |
vitamins | +0.076 |
Mickey | +0.076 |
avocado | +0.075 |
Neg logit contributions | |
a | -0.062 |
be | -0.056 |
ah | -0.050 |
fly | -0.049 |
- | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
a | +0.062 |
- | +0.054 |
ah | +0.051 |
be | +0.049 |
ch | +0.046 |
Neg logit contributions | |
disl | -0.081 |
ados | -0.080 |
array | -0.078 |
vitamins | -0.077 |
Mickey | -0.074 |
Token | for |
Token ID | 329 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Mickey | +0.048 |
ados | +0.048 |
disl | +0.047 |
avocado | +0.047 |
vitamins | +0.046 |
Neg logit contributions | |
a | -0.032 |
be | -0.027 |
ah | -0.025 |
- | -0.024 |
ch | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
disl | +0.035 |
ados | +0.035 |
Mickey | +0.033 |
vitamins | +0.033 |
array | +0.033 |
Neg logit contributions | |
a | -0.027 |
- | -0.023 |
be | -0.022 |
ah | -0.022 |
ch | -0.020 |
Token | moment |
Token ID | 2589 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
a | +0.019 |
- | +0.016 |
be | +0.016 |
as | +0.015 |
web | +0.015 |
Neg logit contributions | |
disl | -0.033 |
Mickey | -0.032 |
Bruce | -0.032 |
avocado | -0.032 |
court | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
a | +0.291 |
ah | +0.247 |
be | +0.247 |
passenger | +0.241 |
ch | +0.238 |
Neg logit contributions | |
avocado | -0.301 |
ados | -0.296 |
Mickey | -0.291 |
disl | -0.290 |
court | -0.289 |
Token | realized |
Token ID | 6939 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
a | +0.007 |
- | +0.006 |
be | +0.006 |
ah | +0.006 |
ch | +0.005 |
Neg logit contributions | |
disl | -0.007 |
ados | -0.007 |
vitamins | -0.006 |
Mickey | -0.006 |
array | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
disl | +0.104 |
ados | +0.101 |
vitamins | +0.097 |
Mickey | +0.096 |
array | +0.095 |
Neg logit contributions | |
a | -0.093 |
- | -0.079 |
be | -0.079 |
ah | -0.078 |
ch | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
a | +0.004 |
- | +0.004 |
ah | +0.004 |
be | +0.003 |
ch | +0.003 |
Neg logit contributions | |
disl | -0.005 |
ados | -0.005 |
array | -0.005 |
vitamins | -0.005 |
Mickey | -0.005 |
Token | frog |
Token ID | 21264 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
disl | +0.013 |
ados | +0.012 |
vitamins | +0.012 |
avocado | +0.012 |
array | +0.012 |
Neg logit contributions | |
a | -0.011 |
- | -0.009 |
ah | -0.009 |
be | -0.009 |
ch | -0.008 |
Token | immer |
Token ID | 10957 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
a | +0.039 |
plane | +0.036 |
racer | +0.035 |
be | +0.035 |
cloud | +0.035 |
Neg logit contributions | |
disl | -0.041 |
ados | -0.041 |
array | -0.037 |
iveness | -0.036 |
issors | -0.035 |
Token | ing |
Token ID | 278 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
a | +0.124 |
passenger | +0.114 |
be | +0.110 |
ah | +0.109 |
fly | +0.108 |
Neg logit contributions | |
ados | -0.146 |
av | -0.139 |
avocado | -0.134 |
oranges | -0.126 |
onions | -0.125 |
Token | in |
Token ID | 287 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ados | +0.002 |
avocado | +0.002 |
av | +0.002 |
array | +0.002 |
Mickey | +0.002 |
Neg logit contributions | |
a | -0.002 |
be | -0.001 |
ah | -0.001 |
as | -0.001 |
ber | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
a | +0.010 |
- | +0.009 |
be | +0.009 |
ah | +0.009 |
ch | +0.008 |
Neg logit contributions | |
disl | -0.010 |
ados | -0.010 |
Mickey | -0.010 |
array | -0.010 |
vitamins | -0.010 |
Token | moon |
Token ID | 8824 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
disl | +0.002 |
ados | +0.002 |
array | +0.002 |
vitamins | +0.002 |
avocado | +0.002 |
Neg logit contributions | |
a | -0.003 |
- | -0.002 |
ah | -0.002 |
be | -0.002 |
ch | -0.002 |
Token | light |
Token ID | 2971 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
a | +0.097 |
vy | +0.077 |
ah | +0.076 |
ber | +0.075 |
racer | +0.072 |
Neg logit contributions | |
ados | -0.124 |
avocado | -0.121 |
array | -0.121 |
Mickey | -0.116 |
disl | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
a | +0.339 |
ah | +0.287 |
ber | +0.283 |
racer | +0.280 |
ang | +0.274 |
Neg logit contributions | |
disl | -0.325 |
array | -0.317 |
ados | -0.315 |
vitamins | -0.304 |
avocado | -0.304 |
Token | It |
Token ID | 632 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
a | +0.035 |
- | +0.033 |
be | +0.031 |
of | +0.030 |
ah | +0.029 |
Neg logit contributions | |
disl | -0.034 |
vitamins | -0.033 |
ados | -0.033 |
array | -0.030 |
avocado | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
a | +0.035 |
be | +0.029 |
less | +0.029 |
- | +0.028 |
ah | +0.028 |
Neg logit contributions | |
disl | -0.042 |
Mickey | -0.042 |
ados | -0.040 |
avocado | -0.039 |
av | -0.039 |
Token | so |
Token ID | 523 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
disl | +0.015 |
Mickey | +0.015 |
ados | +0.015 |
avocado | +0.015 |
vitamins | +0.015 |
Neg logit contributions | |
a | -0.014 |
be | -0.012 |
- | -0.012 |
ah | -0.012 |
mer | -0.011 |
Token | quiet |
Token ID | 5897 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ados | +0.103 |
disl | +0.101 |
array | +0.099 |
vitamins | +0.098 |
Mickey | +0.093 |
Neg logit contributions | |
a | -0.062 |
- | -0.052 |
ah | -0.046 |
be | -0.046 |
ch | -0.044 |
Token | world |
Token ID | 995 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
a | +0.002 |
- | +0.002 |
ah | +0.002 |
be | +0.002 |
ch | +0.002 |
Neg logit contributions | |
disl | -0.003 |
ados | -0.003 |
vitamins | -0.003 |
array | -0.003 |
Mickey | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
Mickey | +0.026 |
Bruce | +0.026 |
ados | +0.026 |
disl | +0.026 |
court | +0.026 |
Neg logit contributions | |
a | -0.022 |
be | -0.018 |
ah | -0.018 |
ch | -0.016 |
as | -0.016 |
Token | promised |
Token ID | 8072 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
a | +0.003 |
less | +0.003 |
be | +0.003 |
ah | +0.003 |
- | +0.003 |
Neg logit contributions | |
Mickey | -0.003 |
disl | -0.003 |
Bruce | -0.003 |
array | -0.003 |
court | -0.003 |
Token | himself |
Token ID | 2241 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
disl | +0.105 |
ados | +0.102 |
Mickey | +0.098 |
vitamins | +0.097 |
array | +0.096 |
Neg logit contributions | |
a | -0.087 |
ah | -0.072 |
be | -0.072 |
- | -0.069 |
ch | -0.067 |
Token | he |
Token ID | 339 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
disl | +0.224 |
ados | +0.221 |
Bruce | +0.216 |
Mickey | +0.215 |
vitamins | +0.215 |
Neg logit contributions | |
a | -0.184 |
be | -0.167 |
ah | -0.163 |
ch | -0.159 |
fly | -0.151 |
Token | 'd |
Token ID | 1549 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
a | +0.004 |
be | +0.004 |
ch | +0.003 |
ah | +0.003 |
- | +0.003 |
Neg logit contributions | |
disl | -0.006 |
vitamins | -0.006 |
Mickey | -0.006 |
Bruce | -0.006 |
ados | -0.006 |
Token | come |
Token ID | 1282 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
a | +0.321 |
- | +0.280 |
be | +0.269 |
ah | +0.264 |
ch | +0.258 |
Neg logit contributions | |
disl | -0.326 |
vitamins | -0.306 |
court | -0.289 |
array | -0.288 |
Mickey | -0.287 |
Token | back |
Token ID | 736 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
a | +0.167 |
ah | +0.149 |
mer | +0.130 |
be | +0.129 |
ch | +0.128 |
Neg logit contributions | |
Mickey | -0.182 |
Bruce | -0.180 |
ados | -0.175 |
disl | -0.173 |
herself | -0.172 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
a | +0.052 |
ah | +0.045 |
be | +0.044 |
ch | +0.041 |
- | +0.039 |
Neg logit contributions | |
disl | -0.074 |
ados | -0.074 |
Mickey | -0.073 |
court | -0.072 |
Bruce | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
a | +0.096 |
ah | +0.078 |
be | +0.075 |
- | +0.073 |
ch | +0.072 |
Neg logit contributions | |
disl | -0.137 |
ados | -0.136 |
vitamins | -0.132 |
array | -0.131 |
avocado | -0.130 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
a | +0.016 |
ah | +0.014 |
- | +0.014 |
of | +0.013 |
ch | +0.013 |
Neg logit contributions | |
disl | -0.029 |
vitamins | -0.029 |
ados | -0.028 |
array | -0.028 |
avocado | -0.027 |
Token | shapes |
Token ID | 15268 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
a | +0.017 |
- | +0.015 |
be | +0.014 |
ah | +0.014 |
ch | +0.013 |
Neg logit contributions | |
disl | -0.020 |
ados | -0.019 |
array | -0.019 |
vitamins | -0.018 |
Mickey | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
avocado | +0.090 |
ados | +0.088 |
vitamins | +0.087 |
disl | +0.087 |
av | +0.084 |
Neg logit contributions | |
a | -0.071 |
ah | -0.060 |
be | -0.057 |
ch | -0.056 |
- | -0.054 |
Token | After |
Token ID | 2293 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
a | +0.018 |
- | +0.017 |
be | +0.016 |
of | +0.016 |
ah | +0.015 |
Neg logit contributions | |
disl | -0.024 |
ados | -0.021 |
array | -0.020 |
vitamins | -0.020 |
Mickey | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
disl | +0.231 |
ados | +0.225 |
vitamins | +0.217 |
array | +0.216 |
Mickey | +0.214 |
Neg logit contributions | |
a | -0.176 |
- | -0.150 |
ah | -0.144 |
be | -0.144 |
ch | -0.131 |
Token | few |
Token ID | 1178 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
a | +0.036 |
as | +0.030 |
web | +0.029 |
ac | +0.029 |
be | +0.029 |
Neg logit contributions | |
Mickey | -0.046 |
disl | -0.045 |
Bruce | -0.044 |
avocado | -0.044 |
Freddy | -0.044 |
Token | minutes |
Token ID | 2431 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
a | +0.146 |
be | +0.120 |
ah | +0.118 |
fly | +0.115 |
ba | +0.113 |
Neg logit contributions | |
vitamins | -0.187 |
disl | -0.187 |
ados | -0.185 |
array | -0.181 |
avocado | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
a | +0.250 |
ah | +0.191 |
be | +0.191 |
- | +0.189 |
fly | +0.177 |
Neg logit contributions | |
ados | -0.405 |
disl | -0.400 |
Mickey | -0.390 |
avocado | -0.389 |
array | -0.389 |
Token | he |
Token ID | 339 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
disl | +0.017 |
ados | +0.016 |
vitamins | +0.016 |
array | +0.015 |
Mickey | +0.015 |
Neg logit contributions | |
a | -0.021 |
- | -0.019 |
ah | -0.018 |
be | -0.018 |
ch | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
disl | +0.009 |
array | +0.009 |
Mickey | +0.009 |
avocado | +0.009 |
ados | +0.009 |
Neg logit contributions | |
a | -0.009 |
ah | -0.008 |
- | -0.008 |
be | -0.008 |
ch | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
a | +0.054 |
- | +0.047 |
ah | +0.044 |
be | +0.044 |
ch | +0.040 |
Neg logit contributions | |
disl | -0.070 |
ados | -0.068 |
array | -0.066 |
vitamins | -0.066 |
Mickey | -0.064 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
a | +0.043 |
ah | +0.038 |
be | +0.037 |
- | +0.037 |
iest | +0.036 |
Neg logit contributions | |
avocado | -0.044 |
av | -0.042 |
Mickey | -0.041 |
disl | -0.041 |
court | -0.041 |
Token | up |
Token ID | 510 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
a | +0.239 |
ah | +0.213 |
be | +0.212 |
ch | +0.204 |
iest | +0.197 |
Neg logit contributions | |
disl | -0.178 |
ados | -0.174 |
Mickey | -0.166 |
Bruce | -0.164 |
array | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
disl | +0.232 |
ados | +0.223 |
array | +0.216 |
Mickey | +0.214 |
vitamins | +0.213 |
Neg logit contributions | |
a | -0.175 |
- | -0.144 |
be | -0.144 |
ah | -0.144 |
ch | -0.132 |
Token | adventure |
Token ID | 8855 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
disl | +0.002 |
ados | +0.002 |
array | +0.002 |
vitamins | +0.002 |
avocado | +0.002 |
Neg logit contributions | |
a | -0.003 |
- | -0.003 |
ah | -0.003 |
be | -0.002 |
fly | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
court | +0.044 |
ados | +0.042 |
disl | +0.042 |
Mickey | +0.042 |
Bruce | +0.041 |
Neg logit contributions | |
a | -0.034 |
ah | -0.029 |
fly | -0.027 |
be | -0.027 |
ba | -0.025 |
Token | one |
Token ID | 530 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
disl | +0.120 |
ados | +0.117 |
vitamins | +0.112 |
array | +0.112 |
Mickey | +0.110 |
Neg logit contributions | |
a | -0.107 |
- | -0.093 |
ah | -0.090 |
be | -0.089 |
ch | -0.082 |
Token | final |
Token ID | 2457 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
a | +0.072 |
ba | +0.068 |
be | +0.066 |
ilot | +0.060 |
ah | +0.060 |
Neg logit contributions | |
avocado | -0.089 |
court | -0.084 |
av | -0.078 |
oranges | -0.078 |
handed | -0.076 |
Token | zoom |
Token ID | 19792 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
a | +0.247 |
ba | +0.218 |
fly | +0.208 |
web | +0.198 |
as | +0.197 |
Neg logit contributions | |
disl | -0.239 |
courtroom | -0.212 |
court | -0.212 |
array | -0.211 |
mischief | -0.210 |
Token | ! |
Token ID | 0 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
a | +0.078 |
spe | +0.064 |
be | +0.064 |
fly | +0.062 |
ah | +0.060 |
Neg logit contributions | |
ados | -0.111 |
court | -0.106 |
disl | -0.106 |
Everyone | -0.099 |
Bruce | -0.098 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
vitamins | +0.012 |
ados | +0.012 |
disl | +0.012 |
array | +0.011 |
av | +0.011 |
Neg logit contributions | |
a | -0.014 |
of | -0.013 |
- | -0.013 |
ch | -0.013 |
be | -0.013 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
a | +0.120 |
- | +0.106 |
ah | +0.104 |
be | +0.104 |
ch | +0.096 |
Neg logit contributions | |
disl | -0.086 |
ados | -0.085 |
Mickey | -0.082 |
array | -0.081 |
vitamins | -0.081 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
a | +0.023 |
be | +0.018 |
- | +0.018 |
ah | +0.018 |
ch | +0.016 |
Neg logit contributions | |
disl | -0.050 |
ados | -0.049 |
Mickey | -0.048 |
vitamins | -0.047 |
avocado | -0.047 |
Token | gone |
Token ID | 3750 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
a | +0.020 |
- | +0.018 |
ah | +0.017 |
be | +0.017 |
fly | +0.017 |
Neg logit contributions | |
vitamins | -0.018 |
disl | -0.018 |
Mickey | -0.017 |
array | -0.017 |
Bruce | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
a | +0.115 |
ah | +0.105 |
be | +0.103 |
ch | +0.096 |
fly | +0.090 |
Neg logit contributions | |
Bruce | -0.132 |
Mickey | -0.131 |
ados | -0.131 |
disl | -0.130 |
court | -0.128 |
Token | an |
Token ID | 281 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
a | +0.035 |
be | +0.030 |
ah | +0.030 |
- | +0.029 |
ch | +0.027 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.035 |
vitamins | -0.035 |
Mickey | -0.034 |
array | -0.034 |
Token | adventure |
Token ID | 8855 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
disl | +0.013 |
vitamins | +0.013 |
ados | +0.012 |
array | +0.012 |
avocado | +0.012 |
Neg logit contributions | |
a | -0.017 |
- | -0.015 |
be | -0.015 |
ah | -0.015 |
fly | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
court | +0.043 |
Bruce | +0.042 |
Mickey | +0.042 |
ados | +0.041 |
Jack | +0.041 |
Neg logit contributions | |
a | -0.036 |
be | -0.031 |
ah | -0.030 |
ch | -0.029 |
ba | -0.029 |
Token | rocked |
Token ID | 36872 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
a | +0.022 |
- | +0.019 |
ah | +0.019 |
be | +0.019 |
ch | +0.017 |
Neg logit contributions | |
disl | -0.026 |
ados | -0.024 |
vitamins | -0.024 |
Mickey | -0.024 |
array | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
a | +0.089 |
be | +0.078 |
ah | +0.074 |
fly | +0.068 |
ch | +0.066 |
Neg logit contributions | |
ados | -0.091 |
Mickey | -0.089 |
Bruce | -0.089 |
Jerry | -0.085 |
disl | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
a | +0.037 |
be | +0.032 |
ah | +0.031 |
- | +0.030 |
ch | +0.028 |
Neg logit contributions | |
disl | -0.035 |
ados | -0.035 |
Mickey | -0.033 |
vitamins | -0.033 |
avocado | -0.033 |
Token | big |
Token ID | 1263 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
disl | +0.004 |
vitamins | +0.004 |
ados | +0.004 |
array | +0.004 |
Mickey | +0.004 |
Neg logit contributions | |
a | -0.005 |
ah | -0.004 |
- | -0.004 |
be | -0.004 |
fly | -0.004 |
Token | white |
Token ID | 2330 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
disl | +0.037 |
ados | +0.036 |
vitamins | +0.035 |
avocado | +0.035 |
Mickey | +0.035 |
Neg logit contributions | |
a | -0.039 |
ah | -0.031 |
be | -0.031 |
- | -0.030 |
as | -0.029 |
Token | sail |
Token ID | 14936 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
disl | +0.045 |
ados | +0.043 |
vitamins | +0.043 |
Bruce | +0.043 |
avocado | +0.042 |
Neg logit contributions | |
a | -0.064 |
ah | -0.054 |
be | -0.052 |
- | -0.050 |
fly | -0.050 |
Token | ily |
Token ID | 813 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
disl | +0.033 |
ados | +0.032 |
vitamins | +0.031 |
array | +0.030 |
Mickey | +0.030 |
Neg logit contributions | |
a | -0.044 |
- | -0.039 |
ah | -0.038 |
be | -0.038 |
ch | -0.036 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
a | +0.077 |
- | +0.066 |
ah | +0.064 |
be | +0.064 |
ch | +0.060 |
Neg logit contributions | |
disl | -0.094 |
ados | -0.092 |
vitamins | -0.088 |
array | -0.088 |
Mickey | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
a | +0.039 |
ah | +0.035 |
ch | +0.032 |
be | +0.032 |
iest | +0.031 |
Neg logit contributions | |
ados | -0.047 |
avocado | -0.046 |
Mickey | -0.045 |
From | -0.044 |
av | -0.044 |
Token | said |
Token ID | 531 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
a | +0.017 |
- | +0.015 |
be | +0.014 |
ah | +0.014 |
ch | +0.013 |
Neg logit contributions | |
disl | -0.020 |
ados | -0.019 |
array | -0.019 |
vitamins | -0.019 |
avocado | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
a | +0.001 |
ah | +0.001 |
be | +0.001 |
- | +0.001 |
ch | +0.001 |
Neg logit contributions | |
ados | -0.002 |
disl | -0.002 |
avocado | -0.002 |
vitamins | -0.002 |
Mickey | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
disl | +0.023 |
ados | +0.022 |
vitamins | +0.021 |
Mickey | +0.021 |
array | +0.021 |
Neg logit contributions | |
a | -0.025 |
- | -0.022 |
ah | -0.021 |
be | -0.021 |
ch | -0.019 |
Token | Che |
Token ID | 7376 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
a | +0.177 |
- | +0.157 |
ah | +0.152 |
be | +0.151 |
ch | +0.141 |
Neg logit contributions | |
disl | -0.147 |
ados | -0.141 |
vitamins | -0.136 |
array | -0.134 |
Mickey | -0.133 |
Token | ese |
Token ID | 2771 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
a | +0.063 |
closer | +0.057 |
fly | +0.056 |
be | +0.056 |
ch | +0.055 |
Neg logit contributions | |
ados | -0.092 |
disl | -0.083 |
vitamins | -0.082 |
avocado | -0.080 |
av | -0.078 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
a | +0.078 |
be | +0.068 |
- | +0.067 |
ah | +0.065 |
less | +0.062 |
Neg logit contributions | |
disl | -0.100 |
ados | -0.098 |
vitamins | -0.095 |
avocado | -0.093 |
Mickey | -0.092 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
disl | +0.199 |
array | +0.186 |
vitamins | +0.184 |
ados | +0.178 |
courtroom | +0.173 |
Neg logit contributions | |
a | -0.108 |
- | -0.104 |
of | -0.102 |
and | -0.088 |
on | -0.087 |
Token | S |
Token ID | 50 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
a | +0.103 |
- | +0.091 |
ah | +0.088 |
be | +0.088 |
ch | +0.082 |
Neg logit contributions | |
disl | -0.094 |
ados | -0.090 |
vitamins | -0.086 |
array | -0.086 |
Mickey | -0.084 |
Token | hands |
Token ID | 2832 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
a | +0.093 |
- | +0.087 |
be | +0.081 |
ah | +0.076 |
ch | +0.074 |
Neg logit contributions | |
disl | -0.085 |
ados | -0.082 |
Mickey | -0.080 |
Bruce | -0.078 |
vitamins | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ados | +0.117 |
Mickey | +0.115 |
disl | +0.115 |
array | +0.111 |
avocado | +0.110 |
Neg logit contributions | |
a | -0.091 |
ah | -0.080 |
be | -0.070 |
fly | -0.070 |
- | -0.069 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
disl | +0.018 |
ados | +0.017 |
vitamins | +0.017 |
array | +0.016 |
Mickey | +0.016 |
Neg logit contributions | |
a | -0.024 |
- | -0.021 |
be | -0.021 |
ah | -0.020 |
ch | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
a | +0.016 |
mer | +0.014 |
ah | +0.014 |
souven | +0.014 |
fly | +0.014 |
Neg logit contributions | |
Mickey | -0.008 |
array | -0.008 |
ados | -0.008 |
avocado | -0.008 |
av | -0.007 |
Token | tried |
Token ID | 3088 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Mickey | +0.013 |
disl | +0.012 |
ados | +0.012 |
array | +0.012 |
avocado | +0.012 |
Neg logit contributions | |
a | -0.014 |
ah | -0.013 |
be | -0.012 |
- | -0.012 |
fly | -0.012 |
Token | one |
Token ID | 530 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
disl | +0.063 |
ados | +0.061 |
vitamins | +0.059 |
array | +0.058 |
Mickey | +0.058 |
Neg logit contributions | |
a | -0.032 |
- | -0.027 |
be | -0.024 |
ah | -0.024 |
ch | -0.021 |
Token | more |
Token ID | 517 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
a | +0.074 |
ilot | +0.072 |
fly | +0.071 |
be | +0.069 |
ba | +0.068 |
Neg logit contributions | |
avocado | -0.089 |
oranges | -0.081 |
broccoli | -0.080 |
squash | -0.078 |
Mickey | -0.078 |
Token | time |
Token ID | 640 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
a | +0.001 |
be | +0.001 |
ah | +0.001 |
- | +0.001 |
fly | +0.001 |
Neg logit contributions | |
disl | -0.002 |
ados | -0.002 |
vitamins | -0.002 |
array | -0.001 |
avocado | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
a | +0.070 |
ah | +0.064 |
fly | +0.057 |
ch | +0.056 |
be | +0.055 |
Neg logit contributions | |
disl | -0.106 |
ados | -0.102 |
vitamins | -0.101 |
array | -0.100 |
court | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
a | +0.028 |
ah | +0.025 |
- | +0.024 |
be | +0.024 |
fly | +0.023 |
Neg logit contributions | |
disl | -0.021 |
Mickey | -0.020 |
ados | -0.020 |
array | -0.019 |
avocado | -0.019 |
Token | door |
Token ID | 3420 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
disl | +0.007 |
array | +0.006 |
vitamins | +0.006 |
ados | +0.006 |
avocado | +0.006 |
Neg logit contributions | |
a | -0.010 |
ah | -0.009 |
- | -0.009 |
fly | -0.008 |
be | -0.008 |
Token | One |
Token ID | 1881 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
ah | +0.014 |
- | +0.013 |
of | +0.013 |
passenger | +0.013 |
too | +0.012 |
Neg logit contributions | |
disl | -0.013 |
ados | -0.012 |
vitamins | -0.012 |
affles | -0.011 |
av | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
avocado | +0.041 |
disl | +0.037 |
Mickey | +0.036 |
court | +0.036 |
array | +0.035 |
Neg logit contributions | |
a | -0.054 |
be | -0.050 |
fly | -0.048 |
ist | -0.047 |
ah | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
a | +0.039 |
- | +0.034 |
ah | +0.030 |
be | +0.030 |
ch | +0.027 |
Neg logit contributions | |
disl | -0.088 |
ados | -0.085 |
vitamins | -0.084 |
array | -0.082 |
avocado | -0.080 |
Token | he |
Token ID | 339 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
disl | +0.014 |
ados | +0.013 |
vitamins | +0.013 |
array | +0.012 |
avocado | +0.012 |
Neg logit contributions | |
a | -0.018 |
- | -0.016 |
ah | -0.015 |
be | -0.015 |
ch | -0.015 |
Token | stumbled |
Token ID | 24241 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
disl | +0.001 |
ados | +0.001 |
vitamins | +0.001 |
array | +0.001 |
Mickey | +0.001 |
Neg logit contributions | |
a | -0.001 |
- | -0.001 |
be | -0.001 |
ah | -0.001 |
ch | -0.001 |
Token | across |
Token ID | 1973 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
avocado | +0.091 |
ados | +0.091 |
array | +0.090 |
court | +0.090 |
Mickey | +0.089 |
Neg logit contributions | |
a | -0.058 |
spe | -0.052 |
ah | -0.052 |
fly | -0.052 |
be | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
a | +0.071 |
- | +0.062 |
ah | +0.056 |
be | +0.056 |
ch | +0.051 |
Neg logit contributions | |
disl | -0.124 |
ados | -0.120 |
vitamins | -0.116 |
array | -0.115 |
Mickey | -0.113 |
Token | big |
Token ID | 1263 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
a | +0.038 |
ah | +0.033 |
be | +0.033 |
- | +0.033 |
less | +0.030 |
Neg logit contributions | |
disl | -0.038 |
avocado | -0.038 |
Mickey | -0.037 |
ados | -0.037 |
array | -0.037 |
Token | box |
Token ID | 3091 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
disl | +0.037 |
ados | +0.036 |
array | +0.035 |
Mickey | +0.034 |
avocado | +0.034 |
Neg logit contributions | |
a | -0.037 |
- | -0.031 |
be | -0.031 |
ah | -0.031 |
ch | -0.028 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
a | +0.029 |
ah | +0.024 |
be | +0.022 |
ch | +0.022 |
- | +0.021 |
Neg logit contributions | |
avocado | -0.042 |
array | -0.041 |
court | -0.041 |
Mickey | -0.040 |
av | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
disl | +0.008 |
ados | +0.008 |
vitamins | +0.008 |
array | +0.008 |
Mickey | +0.008 |
Neg logit contributions | |
a | -0.006 |
- | -0.005 |
ah | -0.005 |
be | -0.005 |
ch | -0.005 |
Token | bright |
Token ID | 6016 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
disl | +0.011 |
ados | +0.011 |
avocado | +0.011 |
array | +0.010 |
vitamins | +0.010 |
Neg logit contributions | |
a | -0.013 |
ah | -0.011 |
be | -0.011 |
- | -0.010 |
ba | -0.010 |
Token | pattern |
Token ID | 3912 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
a | +0.059 |
be | +0.048 |
ah | +0.048 |
ba | +0.047 |
ber | +0.046 |
Neg logit contributions | |
avocado | -0.047 |
ados | -0.045 |
disl | -0.045 |
array | -0.043 |
vitamins | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ados | +0.018 |
avocado | +0.018 |
av | +0.017 |
disl | +0.017 |
vitamins | +0.017 |
Neg logit contributions | |
a | -0.012 |
ah | -0.011 |
be | -0.011 |
passenger | -0.010 |
fly | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
a | +0.001 |
- | +0.001 |
ah | +0.001 |
be | +0.001 |
ch | +0.001 |
Neg logit contributions | |
disl | -0.002 |
ados | -0.002 |
vitamins | -0.002 |
array | -0.001 |
Mickey | -0.001 |
Token | milk |
Token ID | 7545 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
disl | +0.004 |
ados | +0.004 |
array | +0.004 |
avocado | +0.004 |
vitamins | +0.004 |
Neg logit contributions | |
a | -0.005 |
- | -0.005 |
ah | -0.005 |
be | -0.004 |
fly | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ados | +0.032 |
avocado | +0.031 |
array | +0.031 |
Mickey | +0.030 |
disl | +0.030 |
Neg logit contributions | |
a | -0.023 |
ah | -0.019 |
be | -0.019 |
- | -0.019 |
ch | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
a | +0.022 |
of | +0.019 |
- | +0.018 |
be | +0.017 |
less | +0.017 |
Neg logit contributions | |
ados | -0.027 |
disl | -0.026 |
array | -0.026 |
vitamins | -0.026 |
av | -0.025 |
Token | feels |
Token ID | 5300 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
disl | +0.033 |
ados | +0.032 |
vitamins | +0.031 |
array | +0.030 |
Mickey | +0.030 |
Neg logit contributions | |
a | -0.031 |
- | -0.027 |
ah | -0.026 |
be | -0.026 |
ch | -0.024 |
Token | so |
Token ID | 523 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
disl | +0.140 |
vitamins | +0.130 |
ados | +0.130 |
avocado | +0.128 |
Mickey | +0.128 |
Neg logit contributions | |
a | -0.112 |
ah | -0.101 |
- | -0.097 |
be | -0.096 |
ch | -0.089 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ados | +0.108 |
disl | +0.102 |
array | +0.102 |
Mickey | +0.101 |
vitamins | +0.100 |
Neg logit contributions | |
a | -0.068 |
- | -0.058 |
be | -0.053 |
ah | -0.047 |
closer | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
a | +0.026 |
ah | +0.022 |
be | +0.021 |
ch | +0.019 |
- | +0.019 |
Neg logit contributions | |
disl | -0.038 |
ados | -0.037 |
avocado | -0.035 |
vitamins | -0.035 |
array | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
disl | +0.045 |
ados | +0.044 |
array | +0.042 |
vitamins | +0.042 |
Mickey | +0.041 |
Neg logit contributions | |
a | -0.036 |
- | -0.033 |
ah | -0.029 |
be | -0.029 |
ch | -0.027 |
Token | homework |
Token ID | 26131 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
a | +0.035 |
- | +0.034 |
ah | +0.032 |
be | +0.031 |
ch | +0.029 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.017 |
Mickey | -0.015 |
array | -0.015 |
vitamins | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
disl | +0.007 |
ados | +0.007 |
vitamins | +0.007 |
array | +0.007 |
Mickey | +0.007 |
Neg logit contributions | |
a | -0.004 |
ah | -0.004 |
- | -0.004 |
be | -0.004 |
ch | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
- | +0.015 |
a | +0.014 |
too | +0.013 |
be | +0.012 |
driver | +0.012 |
Neg logit contributions | |
disl | -0.022 |
irs | -0.021 |
vitamins | -0.019 |
ados | -0.019 |
Mic | -0.019 |
Token | went |
Token ID | 1816 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
disl | +0.034 |
ados | +0.033 |
vitamins | +0.032 |
array | +0.031 |
Mickey | +0.031 |
Neg logit contributions | |
a | -0.036 |
- | -0.032 |
ah | -0.031 |
be | -0.030 |
ch | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
court | +0.116 |
Mickey | +0.115 |
ados | +0.114 |
array | +0.113 |
disl | +0.111 |
Neg logit contributions | |
a | -0.091 |
ah | -0.077 |
be | -0.076 |
fly | -0.068 |
iest | -0.068 |
Token | his |
Token ID | 465 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
ados | +0.007 |
disl | +0.007 |
vitamins | +0.007 |
array | +0.007 |
Eating | +0.007 |
Neg logit contributions | |
a | -0.004 |
- | -0.004 |
closer | -0.003 |
of | -0.003 |
faster | -0.003 |
Token | room |
Token ID | 2119 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
a | +0.026 |
- | +0.023 |
be | +0.021 |
ah | +0.021 |
ch | +0.019 |
Neg logit contributions | |
disl | -0.028 |
ados | -0.027 |
vitamins | -0.026 |
array | -0.025 |
Mickey | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
a | +0.006 |
ah | +0.005 |
be | +0.005 |
ch | +0.005 |
fly | +0.004 |
Neg logit contributions | |
array | -0.010 |
ados | -0.010 |
court | -0.010 |
disl | -0.010 |
avocado | -0.010 |
Token | played |
Token ID | 2826 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
a | +0.014 |
- | +0.012 |
be | +0.011 |
ah | +0.011 |
ch | +0.010 |
Neg logit contributions | |
disl | -0.016 |
ados | -0.015 |
vitamins | -0.015 |
array | -0.014 |
avocado | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
disl | +0.085 |
ados | +0.084 |
vitamins | +0.080 |
Mickey | +0.080 |
array | +0.080 |
Neg logit contributions | |
a | -0.059 |
ah | -0.049 |
be | -0.048 |
- | -0.046 |
fly | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
disl | +0.029 |
ados | +0.028 |
array | +0.027 |
vitamins | +0.027 |
Mickey | +0.026 |
Neg logit contributions | |
a | -0.028 |
- | -0.024 |
be | -0.023 |
ah | -0.023 |
ch | -0.021 |
Token | They |
Token ID | 2990 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
disl | +0.030 |
ados | +0.029 |
vitamins | +0.028 |
array | +0.028 |
Mickey | +0.028 |
Neg logit contributions | |
a | -0.024 |
- | -0.021 |
ah | -0.021 |
be | -0.020 |
ch | -0.019 |
Token | keep |
Token ID | 1394 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
a | +0.020 |
- | +0.017 |
ah | +0.017 |
be | +0.017 |
ch | +0.015 |
Neg logit contributions | |
disl | -0.020 |
ados | -0.019 |
vitamins | -0.018 |
array | -0.018 |
Mickey | -0.018 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
disl | +0.053 |
vitamins | +0.049 |
ados | +0.049 |
array | +0.048 |
Bruce | +0.047 |
Neg logit contributions | |
a | -0.041 |
- | -0.038 |
be | -0.035 |
ah | -0.033 |
closer | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ados | +0.089 |
disl | +0.088 |
avocado | +0.088 |
court | +0.086 |
av | +0.084 |
Neg logit contributions | |
a | -0.059 |
ah | -0.052 |
be | -0.047 |
ch | -0.044 |
fly | -0.043 |
Token | clay |
Token ID | 21558 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disl | +0.122 |
ados | +0.119 |
vitamins | +0.115 |
array | +0.114 |
Mickey | +0.113 |
Neg logit contributions | |
a | -0.100 |
- | -0.086 |
ah | -0.084 |
be | -0.083 |
ch | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ados | +0.095 |
disl | +0.091 |
avocado | +0.090 |
vitamins | +0.090 |
court | +0.088 |
Neg logit contributions | |
a | -0.056 |
ah | -0.049 |
be | -0.044 |
ch | -0.044 |
- | -0.041 |
Token | making |
Token ID | 1642 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
a | +0.018 |
- | +0.016 |
ah | +0.016 |
be | +0.016 |
ch | +0.015 |
Neg logit contributions | |
disl | -0.017 |
ados | -0.017 |
vitamins | -0.016 |
array | -0.016 |
Mickey | -0.016 |
Token | different |
Token ID | 1180 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
a | +0.040 |
- | +0.035 |
be | +0.032 |
ah | +0.032 |
ch | +0.030 |
Neg logit contributions | |
disl | -0.050 |
ados | -0.049 |
array | -0.048 |
vitamins | -0.047 |
Mickey | -0.047 |
Token | things |
Token ID | 1243 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
a | +0.079 |
- | +0.072 |
be | +0.066 |
ah | +0.066 |
y | +0.062 |
Neg logit contributions | |
disl | -0.077 |
ados | -0.074 |
array | -0.072 |
Mickey | -0.072 |
vitamins | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
disl | +0.172 |
ados | +0.166 |
avocado | +0.164 |
vitamins | +0.161 |
Mickey | +0.158 |
Neg logit contributions | |
a | -0.137 |
ah | -0.126 |
be | -0.112 |
ch | -0.105 |
- | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
a | +0.070 |
be | +0.060 |
ah | +0.058 |
- | +0.057 |
ch | +0.053 |
Neg logit contributions | |
disl | -0.111 |
ados | -0.108 |
Mickey | -0.106 |
avocado | -0.103 |
Bruce | -0.103 |
Token | there |
Token ID | 612 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Mickey | +0.019 |
avocado | +0.018 |
Freddy | +0.018 |
Bruce | +0.018 |
disl | +0.018 |
Neg logit contributions | |
a | -0.012 |
be | -0.012 |
ah | -0.012 |
- | -0.011 |
ch | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
a | +0.020 |
- | +0.016 |
be | +0.016 |
ah | +0.016 |
ch | +0.014 |
Neg logit contributions | |
disl | -0.040 |
ados | -0.039 |
vitamins | -0.038 |
array | -0.038 |
Mickey | -0.037 |
Token | two |
Token ID | 734 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
disl | +0.003 |
ados | +0.003 |
array | +0.003 |
vitamins | +0.003 |
courtroom | +0.003 |
Neg logit contributions | |
a | -0.002 |
be | -0.002 |
- | -0.002 |
ch | -0.002 |
ah | -0.002 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ados | +0.030 |
disl | +0.030 |
Mickey | +0.029 |
vitamins | +0.029 |
array | +0.029 |
Neg logit contributions | |
a | -0.033 |
ah | -0.028 |
- | -0.028 |
be | -0.028 |
ch | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Mickey | +0.144 |
ados | +0.136 |
disl | +0.136 |
array | +0.132 |
court | +0.131 |
Neg logit contributions | |
a | -0.149 |
ah | -0.130 |
ch | -0.125 |
be | -0.125 |
iest | -0.123 |
Token | One |
Token ID | 1881 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
a | +0.033 |
ah | +0.030 |
- | +0.029 |
y | +0.029 |
be | +0.029 |
Neg logit contributions | |
disl | -0.024 |
ados | -0.024 |
vitamins | -0.022 |
array | -0.021 |
av | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
disl | +0.038 |
avocado | +0.037 |
Freddy | +0.036 |
Mickey | +0.035 |
Her | +0.034 |
Neg logit contributions | |
a | -0.043 |
be | -0.041 |
cher | -0.040 |
ba | -0.040 |
ah | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
a | +0.040 |
ah | +0.033 |
be | +0.032 |
- | +0.030 |
fly | +0.029 |
Neg logit contributions | |
ados | -0.061 |
disl | -0.060 |
Mickey | -0.058 |
avocado | -0.057 |
vitamins | -0.057 |
Token | they |
Token ID | 484 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Mickey | +0.013 |
ados | +0.013 |
disl | +0.013 |
Freddy | +0.012 |
avocado | +0.012 |
Neg logit contributions | |
a | -0.022 |
be | -0.020 |
ah | -0.019 |
- | -0.019 |
ist | -0.018 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
a | +0.035 |
- | +0.029 |
be | +0.028 |
ah | +0.027 |
y | +0.026 |
Neg logit contributions | |
disl | -0.051 |
ados | -0.049 |
vitamins | -0.047 |
array | -0.047 |
avocado | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
a | +0.067 |
ah | +0.067 |
iest | +0.065 |
ch | +0.065 |
ilot | +0.064 |
Neg logit contributions | |
avocado | -0.064 |
Mickey | -0.063 |
court | -0.062 |
disl | -0.061 |
ados | -0.060 |
Token | always |
Token ID | 1464 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
disl | +0.035 |
ados | +0.034 |
Mickey | +0.034 |
avocado | +0.034 |
vitamins | +0.033 |
Neg logit contributions | |
a | -0.020 |
be | -0.016 |
- | -0.016 |
ah | -0.015 |
ch | -0.014 |
Token | running |
Token ID | 2491 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
a | +0.168 |
ah | +0.153 |
- | +0.145 |
be | +0.144 |
ch | +0.140 |
Neg logit contributions | |
disl | -0.142 |
array | -0.128 |
ados | -0.128 |
vitamins | -0.127 |
Mickey | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
a | +0.034 |
ah | +0.031 |
be | +0.030 |
fly | +0.029 |
iest | +0.027 |
Neg logit contributions | |
ados | -0.033 |
disl | -0.033 |
court | -0.031 |
Mickey | -0.031 |
array | -0.031 |
Token | jumping |
Token ID | 14284 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
a | +0.014 |
- | +0.013 |
be | +0.012 |
ah | +0.012 |
ch | +0.011 |
Neg logit contributions | |
disl | -0.013 |
ados | -0.013 |
vitamins | -0.012 |
array | -0.012 |
Mickey | -0.012 |
Token | around |
Token ID | 1088 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
a | +0.048 |
be | +0.041 |
ah | +0.041 |
fly | +0.036 |
- | +0.036 |
Neg logit contributions | |
ados | -0.066 |
disl | -0.063 |
avocado | -0.062 |
Mickey | -0.061 |
array | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ados | +0.026 |
disl | +0.026 |
Mickey | +0.025 |
avocado | +0.025 |
array | +0.025 |
Neg logit contributions | |
a | -0.018 |
ah | -0.015 |
be | -0.014 |
- | -0.014 |
ch | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
a | +0.013 |
- | +0.011 |
of | +0.011 |
ah | +0.010 |
ch | +0.010 |
Neg logit contributions | |
disl | -0.024 |
ados | -0.023 |
array | -0.023 |
vitamins | -0.022 |
av | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
disl | +0.021 |
ados | +0.020 |
vitamins | +0.019 |
Mickey | +0.019 |
array | +0.019 |
Neg logit contributions | |
a | -0.027 |
- | -0.024 |
ah | -0.023 |
be | -0.023 |
ch | -0.022 |
Token | One |
Token ID | 3198 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
disl | +0.023 |
ados | +0.022 |
vitamins | +0.021 |
array | +0.021 |
Mickey | +0.021 |
Neg logit contributions | |
a | -0.025 |
- | -0.022 |
ah | -0.021 |
be | -0.021 |
fly | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
fly | +0.044 |
be | +0.043 |
a | +0.043 |
ist | +0.042 |
cher | +0.042 |
Neg logit contributions | |
avocado | -0.024 |
disl | -0.023 |
broccoli | -0.020 |
court | -0.020 |
Mickey | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Mickey | +0.015 |
disl | +0.015 |
ados | +0.015 |
Bruce | +0.014 |
array | +0.014 |
Neg logit contributions | |
a | -0.021 |
ah | -0.018 |
- | -0.018 |
be | -0.018 |
iest | -0.017 |
Token | Let |
Token ID | 5756 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
a | +0.183 |
- | +0.170 |
ah | +0.155 |
be | +0.153 |
less | +0.145 |
Neg logit contributions | |
disl | -0.144 |
ados | -0.133 |
vitamins | -0.130 |
array | -0.130 |
Mickey | -0.128 |
Token | 's |
Token ID | 338 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
a | +0.026 |
- | +0.023 |
be | +0.022 |
ah | +0.022 |
ch | +0.020 |
Neg logit contributions | |
disl | -0.033 |
ados | -0.033 |
vitamins | -0.032 |
array | -0.031 |
avocado | -0.031 |
Token | take |
Token ID | 1011 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
vitamins | +0.059 |
ados | +0.058 |
disl | +0.057 |
array | +0.055 |
av | +0.051 |
Neg logit contributions | |
a | -0.037 |
- | -0.032 |
closer | -0.030 |
be | -0.029 |
of | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
disl | +0.087 |
ados | +0.083 |
array | +0.082 |
vitamins | +0.081 |
Mickey | +0.079 |
Neg logit contributions | |
a | -0.066 |
- | -0.058 |
be | -0.054 |
ah | -0.053 |
ch | -0.050 |
Token | home |
Token ID | 1363 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ados | +0.041 |
Mickey | +0.040 |
disl | +0.039 |
avocado | +0.039 |
array | +0.039 |
Neg logit contributions | |
a | -0.037 |
ah | -0.032 |
be | -0.032 |
- | -0.030 |
fly | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ados | +0.161 |
court | +0.160 |
disl | +0.159 |
Mickey | +0.158 |
avocado | +0.157 |
Neg logit contributions | |
a | -0.126 |
ah | -0.122 |
ch | -0.116 |
be | -0.112 |
fly | -0.106 |
Token | show |
Token ID | 905 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
a | +0.018 |
- | +0.016 |
closer | +0.016 |
be | +0.015 |
of | +0.015 |
Neg logit contributions | |
ados | -0.024 |
disl | -0.023 |
vitamins | -0.023 |
array | -0.023 |
iveness | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
a | +0.062 |
- | +0.055 |
be | +0.050 |
ah | +0.049 |
ch | +0.046 |
Neg logit contributions | |
disl | -0.077 |
ados | -0.073 |
array | -0.073 |
vitamins | -0.071 |
avocado | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
disl | +0.050 |
ados | +0.048 |
vitamins | +0.047 |
Mickey | +0.046 |
avocado | +0.045 |
Neg logit contributions | |
a | -0.030 |
ah | -0.026 |
be | -0.025 |
- | -0.025 |
ch | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
a | +0.003 |
- | +0.003 |
be | +0.003 |
ch | +0.003 |
ah | +0.003 |
Neg logit contributions | |
array | -0.004 |
disl | -0.004 |
ados | -0.004 |
vitamins | -0.004 |
av | -0.004 |
Token | opl |
Token ID | 20106 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
a | +0.032 |
- | +0.030 |
ah | +0.029 |
be | +0.029 |
ch | +0.028 |
Neg logit contributions | |
disl | -0.009 |
ados | -0.009 |
vitamins | -0.008 |
Mickey | -0.008 |
array | -0.008 |
Token | ane |
Token ID | 1531 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ados | +0.100 |
disl | +0.099 |
array | +0.090 |
avocado | +0.090 |
iveness | +0.089 |
Neg logit contributions | |
a | -0.088 |
ah | -0.074 |
- | -0.072 |
be | -0.070 |
closer | -0.069 |
Token | crashed |
Token ID | 14997 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
a | +0.125 |
less | +0.118 |
ah | +0.105 |
iest | +0.103 |
ac | +0.101 |
Neg logit contributions | |
disl | -0.075 |
cries | -0.074 |
ados | -0.070 |
avocado | -0.067 |
Mickey | -0.067 |
Token | on |
Token ID | 319 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
a | +0.131 |
ah | +0.118 |
be | +0.110 |
passenger | +0.104 |
iest | +0.103 |
Neg logit contributions | |
ados | -0.147 |
array | -0.131 |
Mickey | -0.128 |
av | -0.127 |
avocado | -0.125 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
a | +0.029 |
- | +0.025 |
ah | +0.024 |
be | +0.024 |
ch | +0.022 |
Neg logit contributions | |
disl | -0.037 |
ados | -0.036 |
vitamins | -0.035 |
array | -0.035 |
Mickey | -0.034 |
Token | floor |
Token ID | 4314 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
disl | +0.006 |
ados | +0.006 |
avocado | +0.006 |
array | +0.006 |
vitamins | +0.006 |
Neg logit contributions | |
a | -0.015 |
ah | -0.014 |
- | -0.014 |
be | -0.013 |
less | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ados | +0.210 |
disl | +0.209 |
array | +0.206 |
court | +0.206 |
vitamins | +0.200 |
Neg logit contributions | |
a | -0.205 |
ah | -0.183 |
ch | -0.168 |
be | -0.168 |
- | -0.161 |
Token | It |
Token ID | 632 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
a | +0.010 |
of | +0.009 |
ch | +0.009 |
- | +0.008 |
on | +0.008 |
Neg logit contributions | |
disl | -0.012 |
array | -0.012 |
ados | -0.011 |
av | -0.011 |
vitamins | -0.011 |
Token | broke |
Token ID | 6265 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
a | +0.036 |
less | +0.032 |
- | +0.031 |
be | +0.031 |
ah | +0.031 |
Neg logit contributions | |
disl | -0.029 |
ados | -0.027 |
Mickey | -0.027 |
avocado | -0.027 |
vitamins | -0.027 |
Token | into |
Token ID | 656 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
a | +0.016 |
ah | +0.014 |
be | +0.013 |
ch | +0.012 |
- | +0.012 |
Neg logit contributions | |
ados | -0.022 |
array | -0.020 |
Mickey | -0.020 |
avocado | -0.020 |
disl | -0.020 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
disl | +0.169 |
ados | +0.163 |
vitamins | +0.157 |
array | +0.156 |
Mickey | +0.154 |
Neg logit contributions | |
a | -0.164 |
- | -0.144 |
be | -0.138 |
ah | -0.138 |
ch | -0.128 |
Token | They |
Token ID | 1119 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
disl | +0.019 |
vitamins | +0.018 |
array | +0.018 |
court | +0.018 |
ados | +0.018 |
Neg logit contributions | |
a | -0.017 |
ah | -0.015 |
- | -0.014 |
be | -0.013 |
fly | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
disl | +0.076 |
ados | +0.072 |
vitamins | +0.070 |
array | +0.069 |
Mickey | +0.069 |
Neg logit contributions | |
a | -0.067 |
- | -0.060 |
ah | -0.057 |
be | -0.057 |
ch | -0.053 |
Token | fragile |
Token ID | 21049 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
a | +0.051 |
- | +0.044 |
ah | +0.044 |
be | +0.043 |
ch | +0.040 |
Neg logit contributions | |
disl | -0.058 |
ados | -0.056 |
vitamins | -0.055 |
Mickey | -0.054 |
array | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ados | +0.182 |
disl | +0.180 |
vitamins | +0.172 |
avocado | +0.170 |
array | +0.169 |
Neg logit contributions | |
a | -0.110 |
ah | -0.091 |
be | -0.084 |
- | -0.081 |
ch | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
disl | +0.033 |
ados | +0.031 |
vitamins | +0.031 |
Mickey | +0.030 |
avocado | +0.029 |
Neg logit contributions | |
a | -0.034 |
ah | -0.030 |
- | -0.030 |
be | -0.029 |
ch | -0.026 |
Token | ground |
Token ID | 2323 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
disl | +0.029 |
ados | +0.028 |
vitamins | +0.028 |
avocado | +0.027 |
Mickey | +0.027 |
Neg logit contributions | |
a | -0.030 |
- | -0.026 |
ah | -0.025 |
be | -0.025 |
ch | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
disl | +0.230 |
ados | +0.218 |
vitamins | +0.215 |
array | +0.215 |
avocado | +0.212 |
Neg logit contributions | |
a | -0.166 |
ah | -0.148 |
be | -0.136 |
- | -0.132 |
ch | -0.124 |
Token | hard |
Token ID | 1327 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
a | +0.011 |
ah | +0.010 |
- | +0.009 |
be | +0.009 |
iest | +0.009 |
Neg logit contributions | |
vitamins | -0.010 |
disl | -0.009 |
Mickey | -0.009 |
avocado | -0.009 |
ados | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
disl | +0.058 |
ados | +0.057 |
vitamins | +0.056 |
array | +0.056 |
Mickey | +0.054 |
Neg logit contributions | |
a | -0.032 |
ah | -0.026 |
- | -0.024 |
be | -0.024 |
ch | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
disl | +0.186 |
ados | +0.184 |
vitamins | +0.181 |
array | +0.178 |
avocado | +0.170 |
Neg logit contributions | |
a | -0.180 |
- | -0.155 |
be | -0.148 |
ah | -0.145 |
of | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
ados | +0.051 |
disl | +0.048 |
vitamins | +0.048 |
array | +0.047 |
avocado | +0.046 |
Neg logit contributions | |
a | -0.040 |
- | -0.034 |
be | -0.031 |
ah | -0.030 |
ch | -0.030 |
Token | pull |
Token ID | 2834 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
a | +0.001 |
of | +0.001 |
- | +0.001 |
be | +0.001 |
ah | +0.001 |
Neg logit contributions | |
ados | -0.002 |
vitamins | -0.002 |
disl | -0.002 |
array | -0.002 |
courtroom | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
disl | +0.016 |
array | +0.015 |
vitamins | +0.014 |
ados | +0.014 |
Mickey | +0.014 |
Neg logit contributions | |
a | -0.009 |
- | -0.008 |
ah | -0.007 |
be | -0.007 |
closer | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
ados | +0.047 |
disl | +0.046 |
Mickey | +0.046 |
avocado | +0.045 |
array | +0.045 |
Neg logit contributions | |
a | -0.035 |
be | -0.029 |
ah | -0.029 |
- | -0.028 |
ch | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
a | +0.047 |
ah | +0.040 |
be | +0.038 |
rot | +0.036 |
fly | +0.036 |
Neg logit contributions | |
ados | -0.067 |
avocado | -0.065 |
Mickey | -0.065 |
av | -0.063 |
vitamins | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
a | +0.082 |
- | +0.076 |
ah | +0.070 |
closer | +0.066 |
ch | +0.064 |
Neg logit contributions | |
disl | -0.144 |
ados | -0.138 |
vitamins | -0.135 |
array | -0.133 |
iveness | -0.125 |
Token | ground |
Token ID | 2323 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
disl | +0.013 |
vitamins | +0.010 |
array | +0.010 |
ados | +0.010 |
quit | +0.010 |
Neg logit contributions | |
a | -0.012 |
- | -0.011 |
closer | -0.011 |
y | -0.010 |
be | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ados | +0.275 |
disl | +0.271 |
array | +0.268 |
avocado | +0.266 |
Mickey | +0.265 |
Neg logit contributions | |
a | -0.182 |
ah | -0.153 |
be | -0.150 |
- | -0.143 |
ch | -0.141 |
Token | take |
Token ID | 1011 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
a | +0.019 |
- | +0.017 |
closer | +0.016 |
be | +0.015 |
ah | +0.015 |
Neg logit contributions | |
ados | -0.025 |
vitamins | -0.025 |
disl | -0.025 |
array | -0.024 |
iveness | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
disl | +0.096 |
array | +0.090 |
ados | +0.090 |
vitamins | +0.088 |
Mickey | +0.084 |
Neg logit contributions | |
a | -0.056 |
- | -0.053 |
be | -0.045 |
ah | -0.045 |
ch | -0.045 |
Token | home |
Token ID | 1363 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
disl | +0.054 |
ados | +0.053 |
vitamins | +0.051 |
array | +0.051 |
Mickey | +0.051 |
Neg logit contributions | |
a | -0.030 |
- | -0.024 |
ah | -0.024 |
be | -0.024 |
ch | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
disl | +0.191 |
ados | +0.190 |
avocado | +0.184 |
Mickey | +0.183 |
array | +0.181 |
Neg logit contributions | |
a | -0.123 |
ah | -0.107 |
be | -0.101 |
ch | -0.097 |
- | -0.096 |
Token | zoom |
Token ID | 19792 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
disl | +0.013 |
ados | +0.012 |
vitamins | +0.012 |
array | +0.012 |
Mickey | +0.012 |
Neg logit contributions | |
a | -0.012 |
- | -0.011 |
ah | -0.010 |
be | -0.010 |
ch | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
a | +0.092 |
be | +0.079 |
ah | +0.076 |
fly | +0.075 |
less | +0.072 |
Neg logit contributions | |
disl | -0.110 |
ados | -0.108 |
Mickey | -0.099 |
vitamins | -0.098 |
court | -0.098 |
Token | crash |
Token ID | 7014 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
a | +0.019 |
- | +0.016 |
ah | +0.015 |
be | +0.015 |
less | +0.014 |
Neg logit contributions | |
disl | -0.020 |
ados | -0.019 |
vitamins | -0.019 |
array | -0.018 |
Mickey | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
a | +0.093 |
ah | +0.077 |
be | +0.075 |
- | +0.070 |
fly | +0.067 |
Neg logit contributions | |
ados | -0.149 |
disl | -0.148 |
Mickey | -0.141 |
vitamins | -0.141 |
array | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
a | +0.029 |
- | +0.025 |
ah | +0.024 |
be | +0.024 |
ch | +0.022 |
Neg logit contributions | |
disl | -0.035 |
ados | -0.034 |
vitamins | -0.033 |
array | -0.033 |
Mickey | -0.032 |
Token | floor |
Token ID | 4314 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
disl | +0.005 |
ados | +0.005 |
vitamins | +0.005 |
array | +0.005 |
avocado | +0.005 |
Neg logit contributions | |
a | -0.013 |
- | -0.011 |
ah | -0.011 |
be | -0.011 |
fly | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
disl | +0.227 |
ados | +0.226 |
vitamins | +0.225 |
court | +0.222 |
avocado | +0.220 |
Neg logit contributions | |
a | -0.193 |
ah | -0.171 |
be | -0.162 |
ch | -0.160 |
- | -0.158 |
Token | He |
Token ID | 679 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ah | +0.025 |
ch | +0.023 |
of | +0.022 |
a | +0.022 |
- | +0.022 |
Neg logit contributions | |
ados | -0.021 |
disl | -0.021 |
array | -0.020 |
vitamins | -0.019 |
handed | -0.019 |
Token | also |
Token ID | 635 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
disl | +0.025 |
vitamins | +0.024 |
array | +0.023 |
avocado | +0.023 |
Mickey | +0.023 |
Neg logit contributions | |
a | -0.022 |
less | -0.021 |
- | -0.020 |
ch | -0.019 |
be | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
a | +0.062 |
- | +0.055 |
ah | +0.051 |
be | +0.050 |
less | +0.048 |
Neg logit contributions | |
disl | -0.082 |
vitamins | -0.076 |
array | -0.075 |
ados | -0.074 |
Mickey | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
a | +0.016 |
- | +0.014 |
ah | +0.014 |
be | +0.013 |
fly | +0.013 |
Neg logit contributions | |
disl | -0.019 |
ados | -0.018 |
vitamins | -0.018 |
array | -0.018 |
Mickey | -0.018 |