Token | . |
Token ID | 13 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
nam | +0.021 |
Once | +0.020 |
| +0.019 |
refreshed | +0.019 |
Dad | +0.018 |
Neg logit contributions | |
gy | -0.025 |
en | -0.023 |
ook | -0.022 |
rap | -0.022 |
ree | -0.022 |
Token | So |
Token ID | 1406 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ready | +0.018 |
nam | +0.018 |
so | +0.018 |
refreshed | +0.018 |
he | +0.017 |
Neg logit contributions | |
gy | -0.038 |
ree | -0.037 |
eth | -0.035 |
ucks | -0.035 |
eware | -0.035 |
Token | one |
Token ID | 530 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
refreshed | +0.024 |
nam | +0.021 |
unatt | +0.021 |
so | +0.021 |
ready | +0.020 |
Neg logit contributions | |
gy | -0.033 |
enery | -0.029 |
rap | -0.029 |
ree | -0.028 |
eware | -0.028 |
Token | day |
Token ID | 1110 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
| +0.012 |
so | +0.011 |
nam | +0.010 |
refreshed | +0.010 |
he | +0.009 |
Neg logit contributions | |
gy | -0.028 |
ind | -0.028 |
ree | -0.028 |
eware | -0.027 |
rito | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
so | +0.026 |
| +0.024 |
ready | +0.022 |
nam | +0.022 |
refreshed | +0.021 |
Neg logit contributions | |
gy | -0.055 |
enery | -0.052 |
eware | -0.052 |
ree | -0.052 |
ocol | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
refreshed | +0.019 |
| +0.017 |
Once | +0.017 |
so | +0.017 |
ready | +0.016 |
Neg logit contributions | |
gy | -0.043 |
eware | -0.041 |
ree | -0.041 |
oses | -0.040 |
enery | -0.040 |
Token | tw |
Token ID | 665 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
| +0.082 |
he | +0.081 |
Jack | +0.080 |
so | +0.078 |
James | +0.077 |
Neg logit contributions | |
ind | -0.095 |
enery | -0.091 |
rito | -0.089 |
igg | -0.087 |
rap | -0.086 |
Token | ig |
Token ID | 328 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
so | +0.045 |
he | +0.042 |
very | +0.041 |
| +0.041 |
next | +0.040 |
Neg logit contributions | |
gy | -0.034 |
enery | -0.029 |
eware | -0.029 |
ind | -0.029 |
oses | -0.028 |
Token | dropped |
Token ID | 5710 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
so | +0.006 |
he | +0.005 |
| +0.005 |
ready | +0.005 |
very | +0.005 |
Neg logit contributions | |
ind | -0.010 |
gy | -0.010 |
rap | -0.010 |
enery | -0.010 |
ocol | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Once | +0.012 |
| +0.011 |
nam | +0.011 |
refreshed | +0.011 |
he | +0.010 |
Neg logit contributions | |
gy | -0.018 |
en | -0.018 |
enery | -0.017 |
ocol | -0.017 |
OO | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
Once | +0.016 |
so | +0.015 |
| +0.015 |
he | +0.015 |
ready | +0.014 |
Neg logit contributions | |
gy | -0.046 |
ind | -0.044 |
enery | -0.043 |
rap | -0.042 |
ocol | -0.042 |
Token | ig |
Token ID | 328 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
gy | +0.011 |
eware | +0.010 |
rito | +0.010 |
ples | +0.010 |
enery | +0.010 |
Neg logit contributions | |
so | -0.013 |
he | -0.013 |
very | -0.013 |
next | -0.013 |
she | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
gy | +0.039 |
ind | +0.039 |
enery | +0.038 |
rap | +0.038 |
rito | +0.038 |
Neg logit contributions | |
so | -0.025 |
he | -0.024 |
| -0.023 |
very | -0.022 |
ready | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
so | +0.028 |
ready | +0.027 |
refreshed | +0.026 |
he | +0.025 |
very | +0.025 |
Neg logit contributions | |
gy | -0.029 |
ree | -0.027 |
eware | -0.026 |
rap | -0.025 |
ocol | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
nam | +0.027 |
so | +0.025 |
ready | +0.024 |
| +0.023 |
he | +0.022 |
Neg logit contributions | |
gy | -0.042 |
ind | -0.039 |
rito | -0.038 |
ook | -0.037 |
ree | -0.036 |
Token | an |
Token ID | 281 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
| +0.015 |
he | +0.014 |
nam | +0.012 |
refreshed | +0.012 |
Once | +0.012 |
Neg logit contributions | |
gy | -0.036 |
ind | -0.034 |
rap | -0.034 |
ook | -0.033 |
rito | -0.032 |
Token | amazing |
Token ID | 4998 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
| +0.017 |
he | +0.016 |
so | +0.015 |
ready | +0.014 |
Once | +0.014 |
Neg logit contributions | |
ind | -0.024 |
gy | -0.022 |
rap | -0.022 |
ubby | -0.022 |
ocol | -0.022 |
Token | tw |
Token ID | 665 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
| +0.069 |
he | +0.069 |
so | +0.067 |
nam | +0.064 |
ready | +0.062 |
Neg logit contributions | |
ind | -0.112 |
gy | -0.109 |
enery | -0.109 |
rap | -0.109 |
ree | -0.107 |
Token | ig |
Token ID | 328 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
so | +0.043 |
he | +0.041 |
very | +0.040 |
| +0.039 |
next | +0.038 |
Neg logit contributions | |
gy | -0.029 |
enery | -0.026 |
eware | -0.026 |
oses | -0.025 |
ree | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
so | +0.002 |
| +0.002 |
he | +0.002 |
ready | +0.001 |
nam | +0.001 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
ree | -0.004 |
rap | -0.004 |
enery | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ready | +0.038 |
so | +0.036 |
refreshed | +0.036 |
nam | +0.036 |
unatt | +0.035 |
Neg logit contributions | |
gy | -0.026 |
ree | -0.025 |
oses | -0.024 |
eware | -0.023 |
ook | -0.023 |
Token | tw |
Token ID | 665 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
he | +0.070 |
| +0.067 |
Jack | +0.067 |
nam | +0.066 |
so | +0.065 |
Neg logit contributions | |
ind | -0.097 |
enery | -0.091 |
rito | -0.090 |
rap | -0.090 |
igg | -0.089 |
Token | It |
Token ID | 1026 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
nam | +0.013 |
so | +0.012 |
ready | +0.012 |
he | +0.011 |
very | +0.011 |
Neg logit contributions | |
gy | -0.011 |
ind | -0.009 |
ucks | -0.009 |
ree | -0.009 |
rap | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
gy | +0.012 |
ind | +0.011 |
enery | +0.011 |
ree | +0.011 |
rap | +0.011 |
Neg logit contributions | |
so | -0.004 |
he | -0.004 |
| -0.004 |
ready | -0.004 |
very | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
he | +0.016 |
nam | +0.016 |
| +0.015 |
so | +0.013 |
refreshed | +0.013 |
Neg logit contributions | |
gy | -0.037 |
ind | -0.035 |
rap | -0.034 |
OO | -0.034 |
en | -0.033 |
Token | bright |
Token ID | 6016 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
| +0.028 |
so | +0.027 |
he | +0.027 |
nam | +0.026 |
refreshed | +0.024 |
Neg logit contributions | |
ind | -0.053 |
gy | -0.049 |
OO | -0.047 |
enery | -0.046 |
ubby | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
| +0.030 |
he | +0.029 |
nam | +0.029 |
so | +0.029 |
ready | +0.027 |
Neg logit contributions | |
gy | -0.066 |
ind | -0.065 |
enery | -0.062 |
ubby | -0.061 |
rito | -0.061 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
| +0.020 |
nam | +0.017 |
Once | +0.017 |
he | +0.016 |
refreshed | +0.016 |
Neg logit contributions | |
gy | -0.027 |
ind | -0.027 |
ubby | -0.024 |
ook | -0.024 |
OO | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
nam | +0.067 |
refreshed | +0.050 |
so | +0.049 |
ready | +0.048 |
| +0.047 |
Neg logit contributions | |
gy | -0.121 |
ind | -0.113 |
en | -0.110 |
enery | -0.107 |
OO | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
gy | +0.005 |
oses | +0.005 |
ind | +0.005 |
OO | +0.005 |
ree | +0.005 |
Neg logit contributions | |
nam | -0.004 |
| -0.003 |
refreshed | -0.003 |
so | -0.003 |
Once | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ready | +0.019 |
nam | +0.019 |
he | +0.019 |
so | +0.019 |
refreshed | +0.019 |
Neg logit contributions | |
gy | -0.026 |
ree | -0.025 |
OO | -0.024 |
eware | -0.023 |
oses | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
nam | +0.018 |
so | +0.017 |
ready | +0.016 |
he | +0.015 |
very | +0.013 |
Neg logit contributions | |
gy | -0.045 |
eth | -0.044 |
ree | -0.044 |
ind | -0.044 |
uth | -0.043 |
Token | Jim |
Token ID | 18050 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
so | +0.023 |
he | +0.022 |
ready | +0.021 |
nam | +0.020 |
very | +0.020 |
Neg logit contributions | |
ind | -0.035 |
gy | -0.035 |
ree | -0.035 |
eth | -0.034 |
uth | -0.033 |
Token | park |
Token ID | 3952 |
Feature activation | +2.20e-04 |
Pos logit contributions | |
he | +0.009 |
so | +0.009 |
| +0.009 |
ready | +0.008 |
nam | +0.008 |
Neg logit contributions | |
ind | -0.019 |
gy | -0.018 |
enery | -0.017 |
rap | -0.017 |
ree | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
nam | +0.000 |
refreshed | +0.000 |
ready | +0.000 |
so | +0.000 |
Once | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ree | -0.000 |
ook | -0.000 |
oses | -0.000 |
ind | -0.000 |
Token | It |
Token ID | 632 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.036 |
enery | +0.036 |
ree | +0.035 |
rap | +0.035 |
Neg logit contributions | |
so | -0.032 |
he | -0.030 |
ready | -0.029 |
| -0.029 |
very | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
nam | +0.020 |
so | +0.019 |
ready | +0.017 |
he | +0.016 |
| +0.016 |
Neg logit contributions | |
gy | -0.032 |
ind | -0.027 |
eth | -0.026 |
rito | -0.026 |
eware | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
he | +0.010 |
nam | +0.010 |
| +0.009 |
unatt | +0.008 |
refreshed | +0.008 |
Neg logit contributions | |
gy | -0.026 |
ind | -0.025 |
rap | -0.024 |
ook | -0.023 |
rito | -0.023 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
he | +0.027 |
| +0.027 |
so | +0.027 |
nam | +0.026 |
refreshed | +0.023 |
Neg logit contributions | |
ind | -0.045 |
gy | -0.043 |
OO | -0.042 |
ree | -0.041 |
enery | -0.040 |
Token | day |
Token ID | 1110 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
nam | +0.065 |
refreshed | +0.049 |
ready | +0.048 |
so | +0.048 |
he | +0.047 |
Neg logit contributions | |
gy | -0.124 |
ind | -0.116 |
ree | -0.111 |
enery | -0.110 |
en | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
nam | +0.010 |
| +0.009 |
Once | +0.008 |
refreshed | +0.008 |
narrative | +0.008 |
Neg logit contributions | |
gy | -0.010 |
oses | -0.010 |
ind | -0.010 |
ook | -0.010 |
OO | -0.010 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
gy | +0.049 |
ind | +0.048 |
enery | +0.045 |
rap | +0.044 |
en | +0.044 |
Neg logit contributions | |
so | -0.020 |
| -0.019 |
very | -0.018 |
right | -0.017 |
nam | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
nam | +0.003 |
| +0.003 |
ready | +0.003 |
kitchen | +0.003 |
pant | +0.003 |
Neg logit contributions | |
ind | -0.002 |
en | -0.002 |
aff | -0.002 |
ocol | -0.002 |
unn | -0.002 |
Token | children |
Token ID | 1751 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
| +0.013 |
he | +0.012 |
so | +0.012 |
nam | +0.012 |
Once | +0.011 |
Neg logit contributions | |
ind | -0.023 |
ocol | -0.022 |
enery | -0.021 |
ree | -0.021 |
cling | -0.021 |
Token | It |
Token ID | 1026 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
nam | +0.009 |
so | +0.009 |
ready | +0.008 |
he | +0.008 |
very | +0.007 |
Neg logit contributions | |
gy | -0.012 |
rap | -0.011 |
ree | -0.011 |
ind | -0.011 |
rito | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
gy | +0.009 |
ind | +0.009 |
enery | +0.009 |
rap | +0.009 |
ree | +0.009 |
Neg logit contributions | |
so | -0.004 |
he | -0.004 |
| -0.003 |
ready | -0.003 |
nam | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
nam | +0.015 |
he | +0.015 |
| +0.014 |
refreshed | +0.012 |
so | +0.012 |
Neg logit contributions | |
gy | -0.034 |
ind | -0.032 |
OO | -0.030 |
rap | -0.030 |
ook | -0.029 |
Token | bright |
Token ID | 6016 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
so | +0.024 |
| +0.023 |
he | +0.023 |
nam | +0.022 |
ready | +0.020 |
Neg logit contributions | |
ind | -0.046 |
gy | -0.043 |
OO | -0.041 |
enery | -0.040 |
ree | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
| +0.026 |
nam | +0.026 |
he | +0.026 |
so | +0.026 |
ready | +0.024 |
Neg logit contributions | |
gy | -0.061 |
ind | -0.060 |
enery | -0.057 |
ubby | -0.056 |
ree | -0.056 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
| +0.014 |
nam | +0.012 |
Once | +0.012 |
other | +0.011 |
refreshed | +0.011 |
Neg logit contributions | |
gy | -0.020 |
ind | -0.019 |
ook | -0.018 |
OO | -0.017 |
ubby | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | -9.45e-04 |
Pos logit contributions | |
nam | +0.068 |
so | +0.049 |
refreshed | +0.048 |
| +0.048 |
ready | +0.047 |
Neg logit contributions | |
gy | -0.122 |
ind | -0.116 |
en | -0.110 |
enery | -0.107 |
OO | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
gy | +0.002 |
oses | +0.002 |
ind | +0.002 |
OO | +0.002 |
ree | +0.002 |
Neg logit contributions | |
nam | -0.001 |
| -0.001 |
refreshed | -0.001 |
Once | -0.001 |
so | -0.001 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
nam | +0.022 |
ready | +0.021 |
refreshed | +0.021 |
so | +0.021 |
next | +0.020 |
Neg logit contributions | |
gy | -0.025 |
ree | -0.023 |
OO | -0.023 |
oses | -0.022 |
eware | -0.022 |
Token | my |
Token ID | 1820 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
so | +0.024 |
he | +0.022 |
| +0.022 |
ready | +0.020 |
very | +0.020 |
Neg logit contributions | |
gy | -0.044 |
ind | -0.043 |
rap | -0.041 |
enery | -0.041 |
ree | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
so | +0.006 |
he | +0.006 |
| +0.005 |
ready | +0.005 |
very | +0.005 |
Neg logit contributions | |
gy | -0.014 |
ind | -0.014 |
enery | -0.014 |
rap | -0.014 |
ree | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
so | +0.011 |
ready | +0.011 |
he | +0.010 |
very | +0.010 |
refreshed | +0.010 |
Neg logit contributions | |
gy | -0.012 |
ree | -0.011 |
rap | -0.011 |
enery | -0.010 |
eware | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
so | +0.026 |
ready | +0.025 |
nam | +0.025 |
he | +0.023 |
refreshed | +0.020 |
Neg logit contributions | |
gy | -0.077 |
ree | -0.076 |
rap | -0.075 |
ind | -0.075 |
ook | -0.074 |
Token | It |
Token ID | 1026 |
Feature activation | -6.27e-04 |
Pos logit contributions | |
so | +0.022 |
ready | +0.021 |
he | +0.020 |
nam | +0.019 |
| +0.019 |
Neg logit contributions | |
gy | -0.026 |
ind | -0.026 |
ree | -0.025 |
eware | -0.025 |
rap | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ind | +0.002 |
gy | +0.002 |
enery | +0.002 |
rap | +0.002 |
ocol | +0.002 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.000 |
very | -0.000 |
ready | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
| +0.009 |
he | +0.009 |
nam | +0.008 |
she | +0.008 |
refreshed | +0.008 |
Neg logit contributions | |
gy | -0.023 |
ind | -0.021 |
rap | -0.021 |
ubby | -0.021 |
ree | -0.020 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
| +0.028 |
so | +0.028 |
he | +0.028 |
nam | +0.026 |
refreshed | +0.026 |
Neg logit contributions | |
gy | -0.049 |
ind | -0.048 |
ree | -0.045 |
enery | -0.045 |
eth | -0.044 |
Token | day |
Token ID | 1110 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
nam | +0.069 |
so | +0.057 |
refreshed | +0.055 |
| +0.053 |
ready | +0.053 |
Neg logit contributions | |
gy | -0.123 |
ind | -0.114 |
ree | -0.107 |
enery | -0.105 |
aa | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
nam | +0.015 |
| +0.013 |
Once | +0.013 |
refreshed | +0.013 |
narrative | +0.012 |
Neg logit contributions | |
gy | -0.015 |
oses | -0.015 |
OO | -0.014 |
eware | -0.014 |
aa | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
nam | +0.018 |
| +0.018 |
Once | +0.017 |
refreshed | +0.016 |
unatt | +0.016 |
Neg logit contributions | |
gy | -0.029 |
OO | -0.027 |
ind | -0.027 |
oses | -0.027 |
ree | -0.026 |
Token | car |
Token ID | 1097 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
so | +0.048 |
| +0.048 |
she | +0.046 |
he | +0.045 |
nam | +0.045 |
Neg logit contributions | |
ind | -0.052 |
gy | -0.048 |
ubby | -0.047 |
enery | -0.045 |
cker | -0.041 |
Token | felt |
Token ID | 2936 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
nam | +0.016 |
so | +0.014 |
| +0.014 |
refreshed | +0.014 |
ready | +0.013 |
Neg logit contributions | |
gy | -0.024 |
cker | -0.020 |
ind | -0.020 |
oses | -0.020 |
ess | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
| +0.015 |
he | +0.014 |
nam | +0.012 |
refreshed | +0.012 |
Once | +0.012 |
Neg logit contributions | |
gy | -0.036 |
ind | -0.034 |
rap | -0.034 |
ook | -0.033 |
rito | -0.032 |
Token | amazing |
Token ID | 4998 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
| +0.017 |
he | +0.016 |
so | +0.015 |
ready | +0.014 |
Once | +0.014 |
Neg logit contributions | |
ind | -0.024 |
gy | -0.022 |
rap | -0.022 |
ubby | -0.022 |
ocol | -0.022 |
Token | tw |
Token ID | 665 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
| +0.069 |
he | +0.069 |
so | +0.067 |
nam | +0.064 |
ready | +0.062 |
Neg logit contributions | |
ind | -0.112 |
gy | -0.109 |
enery | -0.109 |
rap | -0.109 |
ree | -0.107 |
Token | ig |
Token ID | 328 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
so | +0.043 |
he | +0.041 |
very | +0.040 |
| +0.039 |
next | +0.038 |
Neg logit contributions | |
gy | -0.029 |
enery | -0.026 |
eware | -0.026 |
oses | -0.025 |
ree | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
so | +0.002 |
| +0.002 |
he | +0.002 |
ready | +0.001 |
nam | +0.001 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
ree | -0.004 |
rap | -0.004 |
enery | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ready | +0.038 |
so | +0.036 |
refreshed | +0.036 |
nam | +0.036 |
unatt | +0.035 |
Neg logit contributions | |
gy | -0.026 |
ree | -0.025 |
oses | -0.024 |
eware | -0.023 |
ook | -0.023 |
Token | tw |
Token ID | 665 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
he | +0.070 |
| +0.067 |
Jack | +0.067 |
nam | +0.066 |
so | +0.065 |
Neg logit contributions | |
ind | -0.097 |
enery | -0.091 |
rito | -0.090 |
rap | -0.090 |
igg | -0.089 |
Token | ig |
Token ID | 328 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
so | +0.056 |
he | +0.053 |
| +0.052 |
very | +0.051 |
ready | +0.050 |
Neg logit contributions | |
gy | -0.038 |
enery | -0.033 |
eware | -0.033 |
ind | -0.032 |
ree | -0.031 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
so | +0.021 |
nam | +0.020 |
| +0.019 |
he | +0.019 |
ready | +0.018 |
Neg logit contributions | |
gy | -0.049 |
ind | -0.046 |
ree | -0.045 |
enery | -0.045 |
rap | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
nam | +0.036 |
| +0.035 |
Once | +0.035 |
refreshed | +0.034 |
ready | +0.033 |
Neg logit contributions | |
eware | -0.028 |
ree | -0.026 |
ook | -0.026 |
gy | -0.025 |
rap | -0.025 |
Token | explore |
Token ID | 7301 |
Feature activation | +9.21e-03 |
Pos logit contributions | |
so | +0.023 |
he | +0.023 |
| +0.022 |
ready | +0.022 |
refreshed | +0.021 |
Neg logit contributions | |
rap | -0.025 |
gy | -0.025 |
ree | -0.024 |
rito | -0.022 |
enery | -0.022 |
Token | beach |
Token ID | 10481 |
Feature activation | +4.20e-04 |
Pos logit contributions | |
so | +0.008 |
he | +0.008 |
| +0.008 |
ready | +0.007 |
nam | +0.007 |
Neg logit contributions | |
ind | -0.015 |
gy | -0.015 |
enery | -0.014 |
ree | -0.014 |
rap | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-03 |
Pos logit contributions | |
| +0.000 |
Once | +0.000 |
so | +0.000 |
nam | +0.000 |
he | +0.000 |
Neg logit contributions | |
gy | -0.001 |
enery | -0.001 |
ind | -0.001 |
oses | -0.001 |
ree | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
gy | +0.003 |
enery | +0.003 |
ree | +0.003 |
ind | +0.003 |
OO | +0.003 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
nam | -0.003 |
very | -0.003 |
ready | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
so | +0.010 |
he | +0.009 |
| +0.009 |
nam | +0.008 |
ready | +0.008 |
Neg logit contributions | |
gy | -0.023 |
ind | -0.022 |
enery | -0.022 |
ree | -0.022 |
rito | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
| +0.012 |
nam | +0.011 |
he | +0.011 |
Once | +0.009 |
shop | +0.009 |
Neg logit contributions | |
gy | -0.032 |
ind | -0.031 |
rito | -0.030 |
enery | -0.029 |
rap | -0.029 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
| +0.026 |
so | +0.025 |
he | +0.024 |
nam | +0.023 |
Once | +0.021 |
Neg logit contributions | |
ind | -0.045 |
gy | -0.043 |
enery | -0.043 |
OO | -0.042 |
ree | -0.041 |
Token | day |
Token ID | 1110 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
nam | +0.054 |
so | +0.043 |
| +0.042 |
ready | +0.039 |
he | +0.038 |
Neg logit contributions | |
gy | -0.129 |
ind | -0.125 |
enery | -0.121 |
en | -0.118 |
ree | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
nam | +0.007 |
| +0.006 |
Once | +0.005 |
he | +0.005 |
refreshed | +0.005 |
Neg logit contributions | |
gy | -0.008 |
oses | -0.007 |
ind | -0.007 |
OO | -0.007 |
eware | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
gy | +0.012 |
ind | +0.011 |
enery | +0.011 |
ocol | +0.011 |
rap | +0.011 |
Neg logit contributions | |
so | -0.004 |
| -0.004 |
Once | -0.003 |
nam | -0.003 |
he | -0.003 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
nam | +0.022 |
| +0.021 |
so | +0.020 |
Once | +0.020 |
he | +0.020 |
Neg logit contributions | |
enery | -0.029 |
ind | -0.028 |
ubby | -0.026 |
aa | -0.025 |
en | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
nam | +0.018 |
| +0.018 |
so | +0.018 |
Once | +0.017 |
ready | +0.015 |
Neg logit contributions | |
gy | -0.033 |
enery | -0.031 |
ind | -0.030 |
oses | -0.029 |
rito | -0.029 |
Token | long |
Token ID | 890 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
nam | +0.019 |
| +0.017 |
refreshed | +0.017 |
ready | +0.017 |
unatt | +0.017 |
Neg logit contributions | |
gy | -0.020 |
ind | -0.019 |
ree | -0.019 |
oses | -0.018 |
eth | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
refreshed | +0.025 |
nam | +0.025 |
ready | +0.025 |
| +0.023 |
Once | +0.022 |
Neg logit contributions | |
oses | -0.025 |
en | -0.025 |
ind | -0.024 |
gy | -0.024 |
ant | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
gy | +0.029 |
ind | +0.028 |
rap | +0.028 |
enery | +0.028 |
ree | +0.028 |
Neg logit contributions | |
so | -0.010 |
he | -0.008 |
ready | -0.008 |
| -0.007 |
very | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
so | +0.035 |
| +0.034 |
he | +0.033 |
nam | +0.032 |
ready | +0.032 |
Neg logit contributions | |
gy | -0.055 |
ind | -0.054 |
ree | -0.053 |
rap | -0.051 |
enery | -0.051 |
Token | spin |
Token ID | 7906 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
so | +0.049 |
he | +0.047 |
| +0.046 |
ready | +0.044 |
nam | +0.042 |
Neg logit contributions | |
gy | -0.069 |
ind | -0.066 |
ree | -0.066 |
rap | -0.066 |
enery | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
so | +0.014 |
| +0.013 |
he | +0.013 |
ready | +0.012 |
nam | +0.012 |
Neg logit contributions | |
gy | -0.037 |
ind | -0.036 |
ree | -0.036 |
rap | -0.036 |
enery | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
nam | +0.063 |
refreshed | +0.057 |
ready | +0.056 |
| +0.051 |
he | +0.051 |
Neg logit contributions | |
en | -0.109 |
rap | -0.106 |
ind | -0.104 |
ree | -0.100 |
gy | -0.099 |
Token | morning |
Token ID | 3329 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
nam | +0.071 |
he | +0.069 |
yes | +0.062 |
so | +0.060 |
| +0.059 |
Neg logit contributions | |
ind | -0.095 |
igg | -0.091 |
ree | -0.091 |
en | -0.087 |
ubby | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
nam | +0.024 |
he | +0.021 |
| +0.020 |
nowhere | +0.019 |
yes | +0.019 |
Neg logit contributions | |
ree | -0.031 |
gy | -0.030 |
en | -0.029 |
ind | -0.028 |
rap | -0.028 |
Token | spin |
Token ID | 7906 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
gy | +0.002 |
ree | +0.002 |
enery | +0.002 |
ind | +0.002 |
rap | +0.002 |
Neg logit contributions | |
| -0.001 |
so | -0.001 |
nam | -0.001 |
Once | -0.001 |
he | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
so | +0.005 |
| +0.005 |
he | +0.005 |
ready | +0.004 |
nam | +0.004 |
Neg logit contributions | |
gy | -0.013 |
ind | -0.012 |
ree | -0.012 |
enery | -0.012 |
rap | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
so | +0.005 |
he | +0.005 |
| +0.005 |
ready | +0.005 |
very | +0.005 |
Neg logit contributions | |
gy | -0.008 |
ind | -0.007 |
rap | -0.007 |
ree | -0.007 |
enery | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
nam | +0.009 |
so | +0.008 |
ready | +0.008 |
very | +0.007 |
next | +0.007 |
Neg logit contributions | |
gy | -0.021 |
ree | -0.020 |
ook | -0.020 |
ucks | -0.020 |
enery | -0.019 |
Token | It |
Token ID | 1026 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
nam | +0.010 |
so | +0.009 |
ready | +0.009 |
he | +0.008 |
very | +0.008 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.008 |
ree | -0.008 |
rap | -0.008 |
ucks | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.013 |
enery | +0.013 |
rap | +0.013 |
ree | +0.013 |
Neg logit contributions | |
so | -0.005 |
he | -0.005 |
| -0.004 |
ready | -0.004 |
very | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
nam | +0.018 |
he | +0.018 |
| +0.017 |
unatt | +0.015 |
refreshed | +0.015 |
Neg logit contributions | |
gy | -0.038 |
ind | -0.036 |
OO | -0.034 |
rap | -0.034 |
ook | -0.033 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
so | +0.029 |
| +0.028 |
he | +0.027 |
nam | +0.027 |
refreshed | +0.024 |
Neg logit contributions | |
ind | -0.053 |
gy | -0.050 |
OO | -0.047 |
enery | -0.047 |
ubby | -0.047 |
Token | day |
Token ID | 1110 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
nam | +0.058 |
so | +0.045 |
| +0.045 |
he | +0.043 |
refreshed | +0.043 |
Neg logit contributions | |
gy | -0.125 |
ind | -0.120 |
en | -0.112 |
enery | -0.112 |
ree | -0.110 |
Token | in |
Token ID | 287 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
nam | +0.006 |
| +0.005 |
refreshed | +0.005 |
Once | +0.005 |
unatt | +0.005 |
Neg logit contributions | |
oses | -0.007 |
gy | -0.007 |
OO | -0.006 |
ind | -0.006 |
en | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
nam | +0.005 |
ready | +0.004 |
so | +0.004 |
he | +0.004 |
refreshed | +0.004 |
Neg logit contributions | |
gy | -0.011 |
ind | -0.011 |
en | -0.010 |
rap | -0.010 |
ocol | -0.009 |
Token | park |
Token ID | 3952 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
he | +0.037 |
so | +0.036 |
nam | +0.035 |
yes | +0.034 |
| +0.034 |
Neg logit contributions | |
ind | -0.059 |
gy | -0.056 |
enery | -0.049 |
ree | -0.049 |
rap | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
gy | +0.006 |
ook | +0.005 |
oses | +0.005 |
ind | +0.005 |
enery | +0.005 |
Neg logit contributions | |
nam | -0.004 |
refreshed | -0.003 |
ready | -0.003 |
| -0.003 |
so | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
nam | +0.024 |
| +0.023 |
so | +0.021 |
ready | +0.020 |
he | +0.020 |
Neg logit contributions | |
gy | -0.031 |
rap | -0.030 |
rito | -0.030 |
ind | -0.029 |
enery | -0.029 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
nam | +0.009 |
so | +0.008 |
ready | +0.008 |
next | +0.007 |
very | +0.007 |
Neg logit contributions | |
gy | -0.016 |
ree | -0.016 |
eth | -0.015 |
ucks | -0.015 |
ook | -0.015 |
Token | It |
Token ID | 1026 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
nam | +0.013 |
so | +0.012 |
ready | +0.012 |
he | +0.011 |
very | +0.011 |
Neg logit contributions | |
gy | -0.010 |
ind | -0.009 |
ucks | -0.009 |
ree | -0.009 |
rap | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
gy | +0.036 |
ind | +0.035 |
enery | +0.034 |
rap | +0.034 |
ree | +0.034 |
Neg logit contributions | |
so | -0.013 |
he | -0.012 |
| -0.012 |
ready | -0.011 |
very | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
he | +0.013 |
nam | +0.013 |
| +0.012 |
refreshed | +0.011 |
unatt | +0.011 |
Neg logit contributions | |
gy | -0.030 |
ind | -0.029 |
OO | -0.027 |
rap | -0.027 |
ook | -0.027 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
so | +0.028 |
| +0.027 |
he | +0.026 |
nam | +0.025 |
ready | +0.023 |
Neg logit contributions | |
ind | -0.053 |
gy | -0.050 |
enery | -0.047 |
OO | -0.047 |
ree | -0.046 |
Token | day |
Token ID | 1110 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
nam | +0.058 |
so | +0.046 |
| +0.045 |
refreshed | +0.043 |
ready | +0.043 |
Neg logit contributions | |
gy | -0.124 |
ind | -0.119 |
en | -0.111 |
enery | -0.111 |
ree | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
nam | +0.002 |
| +0.002 |
refreshed | +0.002 |
Once | +0.002 |
unatt | +0.002 |
Neg logit contributions | |
oses | -0.003 |
gy | -0.003 |
OO | -0.002 |
ind | -0.002 |
en | -0.002 |
Token | Mary |
Token ID | 5335 |
Feature activation | -5.72e-04 |
Pos logit contributions | |
so | +0.004 |
| +0.003 |
ready | +0.003 |
right | +0.003 |
Once | +0.003 |
Neg logit contributions | |
gy | -0.014 |
ind | -0.013 |
enery | -0.013 |
ocol | -0.012 |
ree | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -9.95e-04 |
Pos logit contributions | |
gy | +0.001 |
ind | +0.001 |
enery | +0.001 |
rap | +0.001 |
ree | +0.001 |
Neg logit contributions | |
so | -0.001 |
| -0.001 |
he | -0.001 |
ready | -0.001 |
nam | -0.001 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
ook | +0.002 |
rap | +0.002 |
OO | +0.002 |
Neg logit contributions | |
he | -0.001 |
nam | -0.001 |
| -0.001 |
so | -0.001 |
Once | -0.001 |
Token | tube |
Token ID | 12403 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
so | +0.035 |
he | +0.035 |
| +0.034 |
nam | +0.033 |
ready | +0.033 |
Neg logit contributions | |
gy | -0.048 |
ind | -0.047 |
enery | -0.045 |
ree | -0.045 |
OO | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
| +0.008 |
so | +0.007 |
he | +0.007 |
nam | +0.007 |
Once | +0.007 |
Neg logit contributions | |
gy | -0.015 |
ind | -0.014 |
enery | -0.014 |
rap | -0.014 |
oses | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
so | +0.024 |
| +0.023 |
he | +0.022 |
ready | +0.020 |
very | +0.020 |
Neg logit contributions | |
ind | -0.034 |
gy | -0.034 |
rap | -0.033 |
enery | -0.033 |
rito | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
so | +0.014 |
he | +0.012 |
| +0.012 |
ready | +0.011 |
very | +0.011 |
Neg logit contributions | |
gy | -0.033 |
ind | -0.032 |
ree | -0.032 |
rap | -0.032 |
enery | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
he | +0.010 |
| +0.010 |
so | +0.010 |
Once | +0.008 |
ready | +0.008 |
Neg logit contributions | |
gy | -0.034 |
ind | -0.033 |
rap | -0.032 |
enery | -0.032 |
rito | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
he | +0.038 |
so | +0.038 |
| +0.038 |
nam | +0.037 |
ready | +0.035 |
Neg logit contributions | |
gy | -0.050 |
ind | -0.050 |
enery | -0.048 |
ree | -0.048 |
OO | -0.047 |
Token | rare |
Token ID | 4071 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
| +0.072 |
so | +0.070 |
he | +0.070 |
Once | +0.069 |
ready | +0.066 |
Neg logit contributions | |
gy | -0.102 |
enery | -0.099 |
ind | -0.096 |
ree | -0.094 |
eware | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
so | +0.038 |
he | +0.036 |
| +0.035 |
ready | +0.034 |
nam | +0.032 |
Neg logit contributions | |
gy | -0.059 |
ind | -0.057 |
enery | -0.056 |
ree | -0.056 |
rap | -0.056 |
Token | too |
Token ID | 1165 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
he | +0.009 |
| +0.009 |
Once | +0.008 |
nam | +0.008 |
so | +0.008 |
Neg logit contributions | |
ree | -0.016 |
ind | -0.016 |
gy | -0.016 |
rap | -0.016 |
ocol | -0.016 |
Token | ." |
Token ID | 526 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
gy | +0.011 |
ind | +0.010 |
enery | +0.010 |
ree | +0.010 |
rap | +0.010 |
Neg logit contributions | |
so | -0.006 |
he | -0.006 |
| -0.006 |
very | -0.005 |
ready | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +6.51e-03 |
Pos logit contributions | |
nam | +0.015 |
he | +0.013 |
so | +0.012 |
ready | +0.012 |
very | +0.011 |
Neg logit contributions | |
ree | -0.034 |
gy | -0.033 |
ucks | -0.032 |
rap | -0.032 |
ook | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
so | +0.003 |
he | +0.003 |
ready | +0.003 |
| +0.003 |
nam | +0.003 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
ree | -0.007 |
enery | -0.007 |
rap | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.060 |
enery | +0.058 |
rap | +0.058 |
ree | +0.058 |
Neg logit contributions | |
so | -0.040 |
he | -0.037 |
| -0.037 |
ready | -0.034 |
very | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
so | +0.004 |
nam | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.004 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.008 |
ree | -0.008 |
rito | -0.008 |
enery | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
he | +0.003 |
| +0.003 |
nam | +0.003 |
shop | +0.003 |
ready | +0.002 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.008 |
rap | -0.008 |
ree | -0.008 |
ook | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
| +0.019 |
so | +0.019 |
he | +0.019 |
nam | +0.018 |
ready | +0.017 |
Neg logit contributions | |
ind | -0.035 |
gy | -0.035 |
OO | -0.034 |
ree | -0.033 |
enery | -0.033 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
so | +0.016 |
he | +0.015 |
| +0.015 |
ready | +0.013 |
very | +0.013 |
Neg logit contributions | |
gy | -0.038 |
ind | -0.037 |
enery | -0.036 |
rap | -0.036 |
ree | -0.036 |
Token | day |
Token ID | 1110 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
nam | +0.062 |
| +0.046 |
ready | +0.046 |
so | +0.046 |
refreshed | +0.045 |
Neg logit contributions | |
gy | -0.123 |
ind | -0.114 |
ree | -0.113 |
en | -0.111 |
enery | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
gy | +0.003 |
oses | +0.003 |
ind | +0.003 |
OO | +0.003 |
ree | +0.003 |
Neg logit contributions | |
nam | -0.003 |
| -0.003 |
Once | -0.002 |
refreshed | -0.002 |
he | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.058 |
ree | +0.058 |
enery | +0.057 |
rap | +0.057 |
Neg logit contributions | |
so | -0.021 |
| -0.020 |
he | -0.019 |
nam | -0.019 |
shop | -0.019 |
Token | were |
Token ID | 547 |
Feature activation | -7.96e-04 |
Pos logit contributions | |
so | +0.004 |
| +0.004 |
he | +0.004 |
next | +0.004 |
nam | +0.004 |
Neg logit contributions | |
gy | -0.006 |
ind | -0.006 |
ree | -0.006 |
ook | -0.006 |
OO | -0.006 |
Token | both |
Token ID | 1111 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
rap | +0.002 |
ree | +0.002 |
ook | +0.002 |
Neg logit contributions | |
he | -0.001 |
| -0.001 |
so | -0.001 |
nam | -0.001 |
Once | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
so | +0.009 |
he | +0.008 |
ready | +0.007 |
very | +0.007 |
nam | +0.007 |
Neg logit contributions | |
gy | -0.031 |
ree | -0.030 |
ind | -0.030 |
rap | -0.030 |
enery | -0.029 |
Token | It |
Token ID | 1026 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
nam | +0.010 |
so | +0.009 |
ready | +0.008 |
he | +0.008 |
very | +0.008 |
Neg logit contributions | |
gy | -0.009 |
ucks | -0.008 |
rap | -0.008 |
ree | -0.008 |
ind | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
gy | +0.019 |
ind | +0.019 |
enery | +0.018 |
rap | +0.018 |
ree | +0.018 |
Neg logit contributions | |
so | -0.007 |
he | -0.007 |
| -0.007 |
ready | -0.006 |
very | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
nam | +0.014 |
he | +0.014 |
| +0.014 |
so | +0.012 |
unatt | +0.012 |
Neg logit contributions | |
gy | -0.032 |
ind | -0.030 |
OO | -0.029 |
rap | -0.028 |
ook | -0.028 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
so | +0.025 |
| +0.025 |
he | +0.024 |
nam | +0.024 |
refreshed | +0.021 |
Neg logit contributions | |
ind | -0.047 |
gy | -0.044 |
OO | -0.042 |
enery | -0.041 |
ree | -0.041 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
so | +0.031 |
| +0.031 |
nam | +0.030 |
he | +0.030 |
ready | +0.028 |
Neg logit contributions | |
gy | -0.077 |
ind | -0.074 |
enery | -0.072 |
ree | -0.071 |
OO | -0.070 |
Token | day |
Token ID | 1110 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
nam | +0.064 |
so | +0.050 |
refreshed | +0.050 |
| +0.049 |
ready | +0.046 |
Neg logit contributions | |
gy | -0.116 |
ind | -0.110 |
en | -0.105 |
enery | -0.104 |
ree | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
nam | +0.002 |
| +0.001 |
refreshed | +0.001 |
Once | +0.001 |
he | +0.001 |
Neg logit contributions | |
gy | -0.002 |
oses | -0.002 |
ind | -0.002 |
OO | -0.002 |
ree | -0.002 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
so | +0.003 |
| +0.003 |
he | +0.003 |
Once | +0.003 |
ready | +0.003 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.009 |
enery | -0.009 |
ree | -0.009 |
ocol | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.003 |
enery | +0.003 |
ree | +0.003 |
rap | +0.003 |
Neg logit contributions | |
so | -0.002 |
| -0.002 |
he | -0.002 |
nam | -0.002 |
ready | -0.002 |
Token | feeling |
Token ID | 4203 |
Feature activation | +8.19e-04 |
Pos logit contributions | |
he | +0.001 |
nam | +0.001 |
| +0.001 |
so | +0.001 |
Once | +0.001 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.003 |
rap | -0.003 |
ook | -0.003 |
OO | -0.003 |
Token | soft |
Token ID | 2705 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
so | +0.040 |
| +0.037 |
he | +0.037 |
Once | +0.033 |
ready | +0.031 |
Neg logit contributions | |
ind | -0.080 |
gy | -0.078 |
enery | -0.076 |
rap | -0.076 |
rito | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
| +0.022 |
he | +0.020 |
so | +0.020 |
nam | +0.020 |
ready | +0.020 |
Neg logit contributions | |
gy | -0.046 |
ind | -0.045 |
enery | -0.043 |
rito | -0.042 |
rap | -0.042 |
Token | It |
Token ID | 632 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
ready | +0.028 |
refreshed | +0.027 |
unatt | +0.027 |
so | +0.027 |
very | +0.026 |
Neg logit contributions | |
gy | -0.018 |
ree | -0.018 |
oses | -0.017 |
eware | -0.016 |
OO | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
so | +0.036 |
| +0.035 |
nam | +0.035 |
he | +0.032 |
ready | +0.031 |
Neg logit contributions | |
gy | -0.062 |
rito | -0.058 |
ind | -0.057 |
ree | -0.053 |
eth | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
| +0.020 |
he | +0.020 |
nam | +0.016 |
Once | +0.016 |
so | +0.016 |
Neg logit contributions | |
gy | -0.053 |
ind | -0.051 |
rap | -0.050 |
rito | -0.050 |
ree | -0.048 |
Token | popular |
Token ID | 2968 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
| +0.041 |
he | +0.040 |
so | +0.039 |
nam | +0.038 |
refreshed | +0.035 |
Neg logit contributions | |
ind | -0.066 |
gy | -0.062 |
OO | -0.060 |
enery | -0.060 |
ree | -0.060 |
Token | seat |
Token ID | 5852 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
so | +0.071 |
| +0.070 |
he | +0.068 |
nam | +0.067 |
ready | +0.063 |
Neg logit contributions | |
gy | -0.101 |
ind | -0.101 |
enery | -0.100 |
rito | -0.097 |
ree | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
| +0.006 |
Once | +0.006 |
nam | +0.006 |
so | +0.006 |
refreshed | +0.005 |
Neg logit contributions | |
gy | -0.012 |
ind | -0.010 |
oses | -0.010 |
ree | -0.010 |
enery | -0.010 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
ready | +0.021 |
unatt | +0.021 |
nam | +0.020 |
refreshed | +0.020 |
so | +0.020 |
Neg logit contributions | |
ree | -0.021 |
gy | -0.020 |
oses | -0.020 |
eware | -0.019 |
ucks | -0.019 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
| +0.045 |
so | +0.045 |
refreshed | +0.042 |
Once | +0.041 |
nam | +0.041 |
Neg logit contributions | |
ind | -0.066 |
gy | -0.065 |
ook | -0.062 |
enery | -0.060 |
cker | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
refreshed | +0.024 |
nam | +0.024 |
Once | +0.024 |
| +0.023 |
immensely | +0.021 |
Neg logit contributions | |
oses | -0.015 |
ind | -0.014 |
ree | -0.014 |
eware | -0.014 |
en | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
nam | +0.009 |
| +0.009 |
Once | +0.008 |
ready | +0.008 |
refreshed | +0.008 |
Neg logit contributions | |
gy | -0.014 |
en | -0.013 |
ind | -0.013 |
enery | -0.013 |
rap | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
so | +0.007 |
nam | +0.007 |
ready | +0.007 |
very | +0.006 |
he | +0.006 |
Neg logit contributions | |
gy | -0.022 |
uth | -0.020 |
ook | -0.020 |
ree | -0.020 |
rap | -0.020 |
Token | It |
Token ID | 1026 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
nam | +0.009 |
so | +0.008 |
ready | +0.008 |
he | +0.007 |
very | +0.007 |
Neg logit contributions | |
gy | -0.008 |
ind | -0.007 |
ree | -0.007 |
rap | -0.007 |
ucks | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
enery | +0.029 |
rap | +0.029 |
ree | +0.029 |
Neg logit contributions | |
so | -0.012 |
he | -0.011 |
| -0.010 |
ready | -0.010 |
very | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
he | +0.012 |
| +0.011 |
nam | +0.011 |
so | +0.010 |
refreshed | +0.009 |
Neg logit contributions | |
gy | -0.027 |
ind | -0.026 |
OO | -0.025 |
rap | -0.025 |
ook | -0.024 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
so | +0.026 |
| +0.025 |
he | +0.025 |
nam | +0.024 |
ready | +0.022 |
Neg logit contributions | |
ind | -0.049 |
gy | -0.047 |
OO | -0.044 |
enery | -0.044 |
ree | -0.043 |
Token | morning |
Token ID | 3329 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
nam | +0.056 |
so | +0.044 |
| +0.043 |
he | +0.042 |
refreshed | +0.041 |
Neg logit contributions | |
gy | -0.123 |
ind | -0.118 |
en | -0.110 |
enery | -0.110 |
ree | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
gy | +0.007 |
ind | +0.006 |
oses | +0.006 |
ree | +0.006 |
OO | +0.006 |
Neg logit contributions | |
nam | -0.005 |
| -0.004 |
so | -0.004 |
refreshed | -0.004 |
Once | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
so | +0.001 |
| +0.001 |
Once | +0.001 |
ready | +0.001 |
nam | +0.001 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
enery | -0.004 |
ocol | -0.004 |
ree | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
so | +0.012 |
he | +0.012 |
nam | +0.011 |
| +0.011 |
nowhere | +0.010 |
Neg logit contributions | |
ind | -0.021 |
gy | -0.020 |
OO | -0.020 |
enery | -0.020 |
ree | -0.019 |
Token | girl |
Token ID | 2576 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
| +0.038 |
so | +0.037 |
he | +0.037 |
Once | +0.036 |
nam | +0.035 |
Neg logit contributions | |
gy | -0.055 |
ind | -0.053 |
enery | -0.052 |
ree | -0.050 |
OO | -0.049 |
Token | picture |
Token ID | 4286 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.004 |
very | +0.004 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.008 |
enery | -0.008 |
rap | -0.008 |
ree | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
nam | +0.047 |
refreshed | +0.043 |
| +0.043 |
ready | +0.041 |
so | +0.039 |
Neg logit contributions | |
gy | -0.045 |
oses | -0.042 |
ook | -0.042 |
ind | -0.041 |
OO | -0.040 |
Token | It |
Token ID | 632 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
so | +0.033 |
ready | +0.032 |
he | +0.032 |
nam | +0.031 |
very | +0.031 |
Neg logit contributions | |
gy | -0.031 |
ree | -0.028 |
eware | -0.028 |
rito | -0.027 |
rap | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
nam | +0.013 |
ready | +0.011 |
so | +0.011 |
| +0.011 |
refreshed | +0.011 |
Neg logit contributions | |
gy | -0.016 |
ind | -0.015 |
fly | -0.014 |
rito | -0.014 |
cker | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
| +0.014 |
he | +0.013 |
refreshed | +0.011 |
nam | +0.011 |
Once | +0.011 |
Neg logit contributions | |
gy | -0.029 |
rap | -0.027 |
ind | -0.027 |
ook | -0.026 |
oses | -0.025 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
| +0.028 |
he | +0.026 |
so | +0.025 |
refreshed | +0.024 |
nam | +0.024 |
Neg logit contributions | |
ind | -0.040 |
gy | -0.038 |
OO | -0.037 |
ree | -0.037 |
enery | -0.036 |
Token | day |
Token ID | 1110 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
nam | +0.074 |
refreshed | +0.060 |
he | +0.058 |
ready | +0.057 |
| +0.057 |
Neg logit contributions | |
gy | -0.106 |
ind | -0.097 |
ree | -0.092 |
en | -0.090 |
OO | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
nam | +0.013 |
| +0.012 |
Once | +0.012 |
refreshed | +0.011 |
narrative | +0.011 |
Neg logit contributions | |
oses | -0.011 |
gy | -0.011 |
OO | -0.010 |
ind | -0.010 |
ook | -0.010 |
Token | everything |
Token ID | 2279 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
Once | +0.012 |
| +0.012 |
court | +0.011 |
shop | +0.011 |
so | +0.011 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.022 |
enery | -0.020 |
ook | -0.020 |
OO | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
| +0.033 |
Once | +0.032 |
nam | +0.031 |
so | +0.030 |
court | +0.027 |
Neg logit contributions | |
ind | -0.044 |
gy | -0.043 |
en | -0.042 |
rito | -0.041 |
ook | -0.041 |
Token | bright |
Token ID | 6016 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
he | +0.006 |
| +0.006 |
nam | +0.005 |
court | +0.005 |
Once | +0.005 |
Neg logit contributions | |
gy | -0.016 |
ind | -0.016 |
rap | -0.015 |
oses | -0.014 |
ook | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
| +0.026 |
nam | +0.026 |
Once | +0.023 |
so | +0.022 |
refreshed | +0.022 |
Neg logit contributions | |
gy | -0.040 |
rito | -0.035 |
rap | -0.035 |
enery | -0.035 |
ind | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
so | +0.010 |
ready | +0.010 |
nam | +0.010 |
he | +0.010 |
very | +0.009 |
Neg logit contributions | |
gy | -0.029 |
ree | -0.028 |
rap | -0.027 |
ucks | -0.027 |
oc | -0.027 |
Token | It |
Token ID | 1026 |
Feature activation | +2.93e-04 |
Pos logit contributions | |
nam | +0.015 |
so | +0.013 |
ready | +0.012 |
he | +0.012 |
yes | +0.011 |
Neg logit contributions | |
gy | -0.023 |
ucks | -0.021 |
rap | -0.021 |
ree | -0.021 |
ind | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
so | +0.000 |
| +0.000 |
he | +0.000 |
very | +0.000 |
ready | +0.000 |
Neg logit contributions | |
gy | -0.001 |
ind | -0.001 |
enery | -0.001 |
ree | -0.001 |
rito | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
he | +0.013 |
| +0.012 |
nam | +0.012 |
so | +0.011 |
unatt | +0.010 |
Neg logit contributions | |
gy | -0.028 |
ind | -0.028 |
OO | -0.026 |
rap | -0.026 |
ubby | -0.026 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
so | +0.024 |
| +0.023 |
he | +0.022 |
nam | +0.020 |
ready | +0.019 |
Neg logit contributions | |
ind | -0.042 |
gy | -0.041 |
enery | -0.038 |
OO | -0.038 |
ubby | -0.038 |
Token | day |
Token ID | 1110 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
nam | +0.060 |
so | +0.050 |
| +0.049 |
refreshed | +0.049 |
he | +0.048 |
Neg logit contributions | |
gy | -0.119 |
ind | -0.111 |
enery | -0.104 |
ree | -0.103 |
ubby | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-04 |
Pos logit contributions | |
nam | +0.008 |
| +0.007 |
refreshed | +0.007 |
Once | +0.007 |
he | +0.006 |
Neg logit contributions | |
oses | -0.009 |
gy | -0.009 |
ind | -0.009 |
OO | -0.008 |
ubby | -0.008 |
Token | two |
Token ID | 734 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
so | +0.000 |
| +0.000 |
ready | +0.000 |
Once | +0.000 |
right | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ind | -0.000 |
enery | -0.000 |
OO | -0.000 |
ocol | -0.000 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
| +0.012 |
so | +0.011 |
he | +0.011 |
ready | +0.011 |
nam | +0.010 |
Neg logit contributions | |
ind | -0.020 |
gy | -0.020 |
ocol | -0.019 |
oses | -0.019 |
ubby | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
gy | +0.033 |
ind | +0.032 |
enery | +0.032 |
rap | +0.031 |
ree | +0.031 |
Neg logit contributions | |
so | -0.014 |
he | -0.013 |
| -0.012 |
ready | -0.012 |
very | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.004 |
very | +0.003 |
Neg logit contributions | |
gy | -0.010 |
ind | -0.010 |
enery | -0.010 |
ree | -0.010 |
rap | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
so | +0.009 |
he | +0.008 |
| +0.008 |
ready | +0.008 |
nam | +0.007 |
Neg logit contributions | |
gy | -0.023 |
ind | -0.022 |
ree | -0.021 |
enery | -0.021 |
rap | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
| +0.011 |
nam | +0.010 |
he | +0.010 |
shop | +0.009 |
refreshed | +0.008 |
Neg logit contributions | |
gy | -0.030 |
ind | -0.027 |
ook | -0.027 |
rap | -0.027 |
ree | -0.027 |
Token | regular |
Token ID | 3218 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
so | +0.022 |
| +0.021 |
he | +0.020 |
nam | +0.019 |
ready | +0.018 |
Neg logit contributions | |
gy | -0.041 |
ind | -0.041 |
ree | -0.039 |
OO | -0.039 |
enery | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
so | +0.026 |
| +0.024 |
he | +0.023 |
nam | +0.022 |
ready | +0.022 |
Neg logit contributions | |
gy | -0.068 |
ind | -0.065 |
ree | -0.065 |
enery | -0.064 |
OO | -0.063 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
| +0.003 |
Dad | +0.003 |
he | +0.003 |
nam | +0.003 |
Once | +0.003 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
ree | -0.004 |
rito | -0.004 |
cker | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
nam | +0.059 |
so | +0.047 |
ready | +0.044 |
he | +0.044 |
| +0.043 |
Neg logit contributions | |
gy | -0.126 |
ind | -0.116 |
ree | -0.113 |
OO | -0.110 |
enery | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
nam | +0.002 |
| +0.002 |
he | +0.002 |
so | +0.002 |
refreshed | +0.002 |
Neg logit contributions | |
gy | -0.003 |
OO | -0.003 |
ind | -0.003 |
ree | -0.003 |
oses | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
so | +0.013 |
he | +0.012 |
ready | +0.012 |
nam | +0.012 |
very | +0.012 |
Neg logit contributions | |
gy | -0.027 |
ree | -0.025 |
rap | -0.024 |
OO | -0.024 |
eware | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
so | +0.021 |
he | +0.019 |
| +0.019 |
ready | +0.018 |
nam | +0.018 |
Neg logit contributions | |
gy | -0.033 |
ind | -0.031 |
ree | -0.030 |
rap | -0.030 |
enery | -0.030 |
Token | his |
Token ID | 465 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
| +0.010 |
so | +0.009 |
ready | +0.009 |
nam | +0.009 |
Once | +0.008 |
Neg logit contributions | |
gy | -0.027 |
ind | -0.026 |
ree | -0.026 |
rap | -0.025 |
ucks | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
gy | +0.001 |
ook | +0.001 |
ind | +0.001 |
ree | +0.001 |
oses | +0.001 |
Neg logit contributions | |
nam | -0.000 |
so | -0.000 |
refreshed | -0.000 |
| -0.000 |
ready | -0.000 |
Token | It |
Token ID | 632 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
so | +0.003 |
he | +0.003 |
ready | +0.003 |
| +0.003 |
nam | +0.003 |
Neg logit contributions | |
gy | -0.004 |
ree | -0.004 |
rap | -0.004 |
enery | -0.004 |
ind | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
nam | +0.015 |
so | +0.014 |
ready | +0.013 |
| +0.012 |
he | +0.012 |
Neg logit contributions | |
gy | -0.024 |
ind | -0.021 |
ook | -0.020 |
ree | -0.020 |
enery | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
he | +0.018 |
| +0.017 |
nam | +0.017 |
refreshed | +0.014 |
shop | +0.014 |
Neg logit contributions | |
gy | -0.039 |
ind | -0.037 |
ook | -0.035 |
rap | -0.035 |
OO | -0.035 |
Token | bright |
Token ID | 6016 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
| +0.027 |
so | +0.026 |
he | +0.026 |
nam | +0.024 |
ready | +0.023 |
Neg logit contributions | |
ind | -0.047 |
gy | -0.045 |
enery | -0.043 |
OO | -0.043 |
ree | -0.043 |
Token | sunny |
Token ID | 27737 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
so | +0.027 |
he | +0.026 |
| +0.026 |
nam | +0.025 |
ready | +0.024 |
Neg logit contributions | |
gy | -0.062 |
ind | -0.061 |
enery | -0.059 |
ree | -0.058 |
rap | -0.057 |
Token | day |
Token ID | 1110 |
Feature activation | +5.42e-03 |
Pos logit contributions | |
nam | +0.061 |
so | +0.048 |
refreshed | +0.048 |
ready | +0.047 |
he | +0.046 |
Neg logit contributions | |
gy | -0.119 |
ind | -0.112 |
enery | -0.106 |
en | -0.105 |
ree | -0.105 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
nam | +0.009 |
| +0.008 |
refreshed | +0.007 |
Once | +0.007 |
he | +0.007 |
Neg logit contributions | |
gy | -0.009 |
oses | -0.009 |
ree | -0.008 |
eware | -0.008 |
OO | -0.008 |
Token | Molly |
Token ID | 30236 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
shop | +0.003 |
| +0.003 |
so | +0.003 |
nam | +0.003 |
Once | +0.003 |
Neg logit contributions | |
ind | -0.007 |
gy | -0.007 |
inating | -0.006 |
en | -0.006 |
ples | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
so | +0.013 |
nam | +0.013 |
| +0.012 |
he | +0.012 |
ready | +0.012 |
Neg logit contributions | |
gy | -0.018 |
ind | -0.017 |
ree | -0.016 |
enery | -0.016 |
OO | -0.015 |
Token | see |
Token ID | 766 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.004 |
very | +0.004 |
Neg logit contributions | |
gy | -0.005 |
ind | -0.004 |
ree | -0.004 |
rap | -0.004 |
enery | -0.004 |
Token | loyal |
Token ID | 9112 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
so | +0.003 |
he | +0.003 |
| +0.003 |
ready | +0.003 |
very | +0.003 |
Neg logit contributions | |
gy | -0.006 |
ind | -0.005 |
enery | -0.005 |
ree | -0.005 |
rap | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
so | +0.017 |
he | +0.016 |
| +0.016 |
ready | +0.015 |
very | +0.015 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.021 |
enery | -0.021 |
ree | -0.021 |
rap | -0.021 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
so | +0.040 |
| +0.038 |
he | +0.036 |
ready | +0.035 |
Once | +0.034 |
Neg logit contributions | |
gy | -0.051 |
ind | -0.050 |
enery | -0.048 |
ree | -0.047 |
rito | -0.046 |
Token | named |
Token ID | 3706 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
so | +0.005 |
he | +0.005 |
| +0.005 |
very | +0.004 |
ready | +0.004 |
Neg logit contributions | |
gy | -0.006 |
enery | -0.006 |
rap | -0.006 |
ind | -0.006 |
rito | -0.006 |
Token | L |
Token ID | 406 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.003 |
very | +0.003 |
Neg logit contributions | |
gy | -0.014 |
ind | -0.014 |
enery | -0.013 |
rap | -0.013 |
ree | -0.013 |
Token | ott |
Token ID | 1252 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
gy | +0.020 |
enery | +0.019 |
ind | +0.019 |
rito | +0.018 |
rap | +0.018 |
Neg logit contributions | |
so | -0.019 |
he | -0.018 |
| -0.018 |
ready | -0.017 |
very | -0.017 |
Token | ie |
Token ID | 494 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ocol | +0.122 |
enery | +0.119 |
eware | +0.119 |
ree | +0.115 |
ucks | +0.111 |
Neg logit contributions | |
so | -0.144 |
he | -0.140 |
very | -0.138 |
next | -0.136 |
other | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ocol | +0.065 |
rap | +0.065 |
enery | +0.064 |
rito | +0.063 |
ree | +0.063 |
Neg logit contributions | |
so | -0.014 |
he | -0.012 |
very | -0.011 |
| -0.011 |
next | -0.008 |
Token | Every |
Token ID | 3887 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
so | +0.021 |
he | +0.020 |
| +0.019 |
ready | +0.019 |
very | +0.018 |
Neg logit contributions | |
gy | -0.036 |
ind | -0.035 |
ree | -0.034 |
enery | -0.034 |
rap | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
gy | +0.012 |
OO | +0.012 |
ree | +0.012 |
ind | +0.012 |
aa | +0.012 |
Neg logit contributions | |
nam | -0.006 |
so | -0.005 |
he | -0.004 |
| -0.004 |
ready | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
so | +0.017 |
| +0.015 |
he | +0.015 |
ready | +0.015 |
nam | +0.014 |
Neg logit contributions | |
gy | -0.039 |
ree | -0.037 |
ind | -0.037 |
enery | -0.037 |
rap | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
gy | +0.013 |
ree | +0.013 |
ind | +0.013 |
rap | +0.012 |
rito | +0.012 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
ready | -0.003 |
nam | -0.003 |
very | -0.002 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gy | +0.039 |
ind | +0.038 |
enery | +0.037 |
rap | +0.037 |
ree | +0.036 |
Neg logit contributions | |
so | -0.028 |
he | -0.027 |
| -0.026 |
ready | -0.025 |
very | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
gy | +0.037 |
ind | +0.036 |
enery | +0.036 |
rap | +0.036 |
ree | +0.035 |
Neg logit contributions | |
so | -0.014 |
he | -0.012 |
| -0.012 |
ready | -0.011 |
very | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | +9.62e-04 |
Pos logit contributions | |
gy | +0.034 |
enery | +0.031 |
ree | +0.031 |
eware | +0.031 |
ind | +0.030 |
Neg logit contributions | |
so | -0.010 |
| -0.009 |
Once | -0.008 |
ready | -0.008 |
he | -0.008 |
Token | sp |
Token ID | 599 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
so | +0.002 |
he | +0.002 |
| +0.002 |
ready | +0.002 |
next | +0.001 |
Neg logit contributions | |
gy | -0.002 |
ind | -0.001 |
OO | -0.001 |
ree | -0.001 |
enery | -0.001 |
Token | ott |
Token ID | 1252 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
gy | +0.059 |
enery | +0.058 |
ree | +0.052 |
oc | +0.051 |
rito | +0.050 |
Neg logit contributions | |
so | -0.068 |
he | -0.063 |
ready | -0.060 |
very | -0.060 |
Once | -0.057 |
Token | led |
Token ID | 992 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
ocol | +0.138 |
enery | +0.125 |
eware | +0.121 |
ucks | +0.116 |
ucker | +0.112 |
Neg logit contributions | |
so | -0.131 |
next | -0.126 |
he | -0.124 |
very | -0.122 |
other | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
gy | +0.008 |
ind | +0.007 |
enery | +0.007 |
ree | +0.007 |
rito | +0.007 |
Neg logit contributions | |
| -0.004 |
so | -0.004 |
he | -0.004 |
Once | -0.004 |
nam | -0.004 |
Token | bicycle |
Token ID | 17026 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
gy | +0.015 |
ind | +0.015 |
enery | +0.015 |
ree | +0.015 |
OO | +0.014 |
Neg logit contributions | |
so | -0.011 |
he | -0.010 |
| -0.010 |
ready | -0.010 |
nam | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
gy | +0.054 |
ind | +0.049 |
ree | +0.049 |
enery | +0.048 |
oses | +0.048 |
Neg logit contributions | |
| -0.033 |
so | -0.032 |
nam | -0.031 |
ready | -0.029 |
Once | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
gy | +0.025 |
ree | +0.024 |
ind | +0.023 |
enery | +0.023 |
rap | +0.023 |
Neg logit contributions | |
so | -0.021 |
he | -0.020 |
| -0.019 |
ready | -0.019 |
very | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
so | +0.003 |
he | +0.002 |
ready | +0.002 |
nam | +0.002 |
| +0.002 |
Neg logit contributions | |
gy | -0.010 |
ind | -0.010 |
ree | -0.010 |
rap | -0.010 |
enery | -0.010 |
Token | One |
Token ID | 3198 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
gy | +0.008 |
enery | +0.008 |
rito | +0.008 |
ocol | +0.008 |
ind | +0.008 |
Neg logit contributions | |
so | -0.006 |
| -0.006 |
he | -0.006 |
very | -0.006 |
Once | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
ind | +0.018 |
gy | +0.018 |
ree | +0.017 |
ubby | +0.017 |
aa | +0.017 |
Neg logit contributions | |
| -0.006 |
so | -0.006 |
nam | -0.006 |
he | -0.005 |
ready | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
rito | -0.004 |
rap | -0.004 |
enery | -0.004 |
Token | L |
Token ID | 406 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
so | +0.007 |
he | +0.007 |
| +0.007 |
ready | +0.006 |
very | +0.006 |
Neg logit contributions | |
gy | -0.011 |
ind | -0.011 |
ree | -0.011 |
enery | -0.011 |
rap | -0.011 |
Token | ott |
Token ID | 1252 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
enery | +0.002 |
ree | +0.002 |
rap | +0.002 |
Neg logit contributions | |
so | -0.002 |
he | -0.002 |
| -0.002 |
ready | -0.002 |
very | -0.002 |
Token | ie |
Token ID | 494 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
ocol | +0.131 |
enery | +0.124 |
eware | +0.123 |
ues | +0.115 |
oses | +0.115 |
Neg logit contributions | |
so | -0.122 |
next | -0.119 |
very | -0.115 |
he | -0.115 |
day | -0.110 |
Token | 's |
Token ID | 338 |
Feature activation | -9.29e-04 |
Pos logit contributions | |
gy | +0.048 |
ind | +0.047 |
enery | +0.046 |
rap | +0.046 |
ree | +0.046 |
Neg logit contributions | |
so | -0.021 |
he | -0.019 |
| -0.019 |
ready | -0.017 |
very | -0.017 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
ree | +0.002 |
rap | +0.002 |
eware | +0.002 |
Neg logit contributions | |
| -0.001 |
he | -0.001 |
so | -0.001 |
nam | -0.001 |
ready | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
so | +0.003 |
he | +0.002 |
| +0.002 |
ready | +0.002 |
very | +0.002 |
Neg logit contributions | |
gy | -0.005 |
ind | -0.005 |
rap | -0.005 |
enery | -0.005 |
ree | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
enery | +0.003 |
ree | +0.003 |
rap | +0.003 |
Neg logit contributions | |
so | -0.002 |
he | -0.002 |
| -0.002 |
ready | -0.001 |
very | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Once | +0.000 |
| +0.000 |
refreshed | +0.000 |
nam | +0.000 |
immensely | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ifi | -0.000 |
eware | -0.000 |
ook | -0.000 |
oses | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | +5.77e-04 |
Pos logit contributions | |
gy | +0.022 |
ind | +0.021 |
ree | +0.020 |
enery | +0.020 |
rap | +0.020 |
Neg logit contributions | |
so | -0.018 |
he | -0.018 |
| -0.018 |
nam | -0.017 |
ready | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.001 |
ind | -0.001 |
rap | -0.001 |
enery | -0.001 |
ocol | -0.001 |
Token | my |
Token ID | 616 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
| +0.003 |
so | +0.003 |
nam | +0.003 |
ready | +0.003 |
he | +0.003 |
Neg logit contributions | |
gy | -0.006 |
ree | -0.006 |
rap | -0.006 |
enery | -0.006 |
ind | -0.006 |
Token | d |
Token ID | 288 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
gy | +0.027 |
ind | +0.026 |
enery | +0.026 |
ree | +0.025 |
rap | +0.025 |
Neg logit contributions | |
so | -0.020 |
| -0.020 |
he | -0.020 |
ready | -0.018 |
Once | -0.018 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
gy | +0.009 |
enery | +0.007 |
ind | +0.007 |
rito | +0.007 |
rap | +0.007 |
Neg logit contributions | |
so | -0.018 |
he | -0.016 |
ready | -0.016 |
very | -0.016 |
| -0.016 |
Token | ings |
Token ID | 654 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
ind | +0.085 |
gy | +0.085 |
enery | +0.080 |
ocol | +0.080 |
rito | +0.079 |
Neg logit contributions | |
so | -0.163 |
he | -0.161 |
| -0.156 |
ready | -0.149 |
very | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
gy | +0.006 |
ind | +0.005 |
rap | +0.005 |
ree | +0.005 |
rito | +0.005 |
Neg logit contributions | |
nam | -0.004 |
so | -0.004 |
| -0.004 |
he | -0.004 |
ready | -0.004 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
so | +0.020 |
he | +0.019 |
| +0.018 |
ready | +0.018 |
very | +0.018 |
Neg logit contributions | |
gy | -0.031 |
ind | -0.030 |
ree | -0.030 |
enery | -0.030 |
rap | -0.030 |
Token | your |
Token ID | 534 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
gy | +0.043 |
ind | +0.041 |
ree | +0.041 |
enery | +0.041 |
rap | +0.040 |
Neg logit contributions | |
so | -0.027 |
he | -0.025 |
| -0.024 |
ready | -0.023 |
very | -0.023 |
Token | lunch |
Token ID | 9965 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
gy | +0.012 |
ind | +0.012 |
ocol | +0.012 |
enery | +0.012 |
rap | +0.011 |
Neg logit contributions | |
so | -0.008 |
| -0.008 |
he | -0.008 |
Once | -0.008 |
nam | -0.007 |
Token | like |
Token ID | 588 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.004 |
oses | +0.004 |
ocol | +0.004 |
rito | +0.004 |
Neg logit contributions | |
| -0.003 |
Once | -0.002 |
nam | -0.002 |
refreshed | -0.002 |
so | -0.002 |
Token | lettuce |
Token ID | 39406 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
| +0.002 |
Once | +0.002 |
refreshed | +0.002 |
so | +0.002 |
ready | +0.002 |
Neg logit contributions | |
ind | -0.004 |
gy | -0.004 |
ocol | -0.004 |
oses | -0.003 |
enery | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
gy | +0.057 |
rito | +0.053 |
ind | +0.053 |
rap | +0.053 |
enery | +0.052 |
Neg logit contributions | |
| -0.030 |
nam | -0.028 |
so | -0.028 |
Once | -0.026 |
ready | -0.026 |
Token | tomatoes |
Token ID | 23972 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gy | +0.060 |
ind | +0.058 |
ocol | +0.057 |
enery | +0.056 |
rito | +0.056 |
Neg logit contributions | |
| -0.041 |
so | -0.041 |
ready | -0.039 |
he | -0.039 |
Once | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
gy | +0.031 |
rap | +0.029 |
rito | +0.029 |
ind | +0.029 |
oses | +0.028 |
Neg logit contributions | |
| -0.017 |
nam | -0.017 |
so | -0.016 |
ready | -0.015 |
he | -0.015 |
Token | cuc |
Token ID | 38421 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
gy | +0.066 |
ind | +0.065 |
enery | +0.063 |
rap | +0.063 |
ree | +0.062 |
Neg logit contributions | |
so | -0.049 |
he | -0.046 |
| -0.046 |
ready | -0.043 |
very | -0.042 |
Token | umbers |
Token ID | 17024 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
gy | +0.116 |
ind | +0.103 |
ree | +0.103 |
enery | +0.103 |
eware | +0.100 |
Neg logit contributions | |
so | -0.137 |
he | -0.132 |
ready | -0.128 |
| -0.126 |
very | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
gy | +0.073 |
ind | +0.070 |
rap | +0.070 |
enery | +0.069 |
rito | +0.069 |
Neg logit contributions | |
so | -0.030 |
| -0.029 |
he | -0.028 |
ready | -0.026 |
nam | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
gy | +0.014 |
ree | +0.014 |
ind | +0.013 |
rap | +0.013 |
oses | +0.013 |
Neg logit contributions | |
so | -0.010 |
ready | -0.009 |
very | -0.009 |
he | -0.009 |
nam | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
gy | +0.062 |
ind | +0.061 |
ree | +0.060 |
enery | +0.060 |
rap | +0.059 |
Neg logit contributions | |
so | -0.038 |
he | -0.036 |
| -0.034 |
ready | -0.032 |
very | -0.032 |
Token | as |
Token ID | 355 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
gy | +0.015 |
ind | +0.015 |
enery | +0.014 |
rap | +0.014 |
ree | +0.014 |
Neg logit contributions | |
so | -0.006 |
| -0.006 |
he | -0.006 |
nam | -0.006 |
ready | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
nam | +0.013 |
| +0.013 |
refreshed | +0.011 |
he | +0.011 |
so | +0.011 |
Neg logit contributions | |
gy | -0.020 |
ind | -0.019 |
enery | -0.019 |
en | -0.018 |
rap | -0.018 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
gy | +0.020 |
ree | +0.019 |
oses | +0.019 |
ind | +0.018 |
enery | +0.018 |
Neg logit contributions | |
nam | -0.009 |
| -0.009 |
refreshed | -0.008 |
Once | -0.008 |
ready | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
gy | +0.042 |
ind | +0.040 |
enery | +0.040 |
rap | +0.039 |
ree | +0.039 |
Neg logit contributions | |
so | -0.020 |
| -0.019 |
he | -0.018 |
ready | -0.017 |
nam | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
gy | +0.023 |
ree | +0.022 |
uth | +0.021 |
oses | +0.020 |
rap | +0.020 |
Neg logit contributions | |
ready | -0.011 |
so | -0.011 |
nam | -0.011 |
very | -0.010 |
he | -0.010 |
Token | G |
Token ID | 38 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
gy | +0.002 |
rap | +0.002 |
ree | +0.002 |
ind | +0.002 |
rito | +0.002 |
Neg logit contributions | |
nam | -0.001 |
so | -0.001 |
ready | -0.001 |
he | -0.001 |
very | -0.001 |
Token | lor |
Token ID | 4685 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
eware | +0.067 |
enery | +0.065 |
ree | +0.064 |
rito | +0.064 |
gy | +0.064 |
Neg logit contributions | |
| -0.114 |
he | -0.107 |
so | -0.106 |
Once | -0.099 |
very | -0.098 |
Token | ia |
Token ID | 544 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
gy | +0.103 |
enery | +0.103 |
ocol | +0.102 |
rito | +0.102 |
ind | +0.099 |
Neg logit contributions | |
so | -0.140 |
he | -0.134 |
| -0.133 |
very | -0.123 |
other | -0.123 |
Token | was |
Token ID | 373 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
gy | +0.035 |
ind | +0.034 |
rap | +0.033 |
ree | +0.033 |
enery | +0.032 |
Neg logit contributions | |
so | -0.016 |
he | -0.015 |
| -0.014 |
ready | -0.014 |
nam | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
gy | +0.009 |
ind | +0.009 |
rap | +0.008 |
ree | +0.008 |
ubby | +0.008 |
Neg logit contributions | |
he | -0.003 |
| -0.003 |
so | -0.003 |
nam | -0.003 |
shop | -0.002 |
Token | graceful |
Token ID | 44363 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
enery | +0.002 |
ree | +0.002 |
rap | +0.002 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
ready | -0.001 |
very | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.76e-04 |
Pos logit contributions | |
so | +0.017 |
he | +0.016 |
| +0.016 |
ready | +0.015 |
very | +0.015 |
Neg logit contributions | |
gy | -0.023 |
ind | -0.023 |
enery | -0.022 |
ree | -0.022 |
rap | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +8.38e-04 |
Pos logit contributions | |
he | +0.000 |
| +0.000 |
so | +0.000 |
nam | +0.000 |
ready | +0.000 |
Neg logit contributions | |
gy | -0.001 |
ind | -0.001 |
rap | -0.001 |
ree | -0.001 |
OO | -0.001 |
Token | good |
Token ID | 922 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.002 |
ind | -0.002 |
enery | -0.002 |
ree | -0.002 |
rap | -0.002 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.71e-04 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.004 |
very | +0.003 |
Neg logit contributions | |
gy | -0.006 |
ind | -0.006 |
enery | -0.006 |
ree | -0.006 |
rap | -0.006 |
Token | named |
Token ID | 3706 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
gy | +0.000 |
ind | +0.000 |
ree | +0.000 |
enery | +0.000 |
rap | +0.000 |
Neg logit contributions | |
so | -0.000 |
he | -0.000 |
| -0.000 |
ready | -0.000 |
very | -0.000 |
Token | D |
Token ID | 360 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
so | +0.012 |
nam | +0.010 |
he | +0.010 |
ready | +0.010 |
| +0.010 |
Neg logit contributions | |
gy | -0.030 |
ree | -0.028 |
ind | -0.028 |
eware | -0.027 |
rap | -0.027 |
Token | ott |
Token ID | 1252 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
gy | +0.018 |
ind | +0.017 |
enery | +0.017 |
rap | +0.017 |
rito | +0.016 |
Neg logit contributions | |
so | -0.020 |
he | -0.019 |
| -0.019 |
ready | -0.018 |
very | -0.018 |
Token | ie |
Token ID | 494 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ocol | +0.100 |
enery | +0.097 |
eware | +0.094 |
ree | +0.091 |
ucks | +0.090 |
Neg logit contributions | |
so | -0.137 |
he | -0.135 |
very | -0.131 |
next | -0.128 |
other | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ocol | +0.055 |
rap | +0.055 |
enery | +0.054 |
rito | +0.054 |
ree | +0.053 |
Neg logit contributions | |
so | -0.013 |
he | -0.011 |
very | -0.010 |
| -0.010 |
next | -0.008 |
Token | D |
Token ID | 360 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
so | +0.023 |
he | +0.022 |
| +0.021 |
ready | +0.020 |
very | +0.020 |
Neg logit contributions | |
gy | -0.032 |
ind | -0.031 |
enery | -0.031 |
rap | -0.031 |
ree | -0.030 |
Token | ott |
Token ID | 1252 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
so | +0.019 |
he | +0.018 |
| +0.017 |
very | +0.017 |
ready | +0.017 |
Neg logit contributions | |
gy | -0.019 |
ind | -0.018 |
enery | -0.018 |
rito | -0.017 |
rap | -0.017 |
Token | ie |
Token ID | 494 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
ocol | +0.093 |
enery | +0.092 |
eware | +0.089 |
ree | +0.084 |
ues | +0.083 |
Neg logit contributions | |
so | -0.112 |
very | -0.106 |
he | -0.105 |
| -0.101 |
next | -0.100 |
Token | monkeys |
Token ID | 26697 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
gy | +0.051 |
ind | +0.050 |
enery | +0.048 |
rap | +0.048 |
ree | +0.048 |
Neg logit contributions | |
so | -0.051 |
he | -0.049 |
| -0.048 |
ready | -0.046 |
very | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
gy | +0.050 |
ind | +0.047 |
ree | +0.046 |
rap | +0.046 |
enery | +0.046 |
Neg logit contributions | |
so | -0.021 |
| -0.019 |
he | -0.019 |
ready | -0.018 |
nam | -0.018 |
Token | elephants |
Token ID | 25368 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
gy | +0.053 |
ind | +0.051 |
enery | +0.050 |
ree | +0.049 |
rap | +0.049 |
Neg logit contributions | |
so | -0.050 |
he | -0.048 |
| -0.048 |
ready | -0.046 |
very | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
gy | +0.045 |
ind | +0.043 |
ree | +0.042 |
oses | +0.042 |
enery | +0.042 |
Neg logit contributions | |
so | -0.021 |
| -0.019 |
he | -0.019 |
nam | -0.019 |
ready | -0.018 |
Token | gir |
Token ID | 37370 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
gy | +0.055 |
ind | +0.053 |
enery | +0.052 |
ree | +0.051 |
rap | +0.051 |
Neg logit contributions | |
so | -0.051 |
| -0.049 |
he | -0.049 |
ready | -0.047 |
very | -0.045 |
Token | aff |
Token ID | 2001 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
gy | +0.042 |
enery | +0.041 |
rap | +0.039 |
rito | +0.038 |
ind | +0.037 |
Neg logit contributions | |
so | -0.138 |
he | -0.136 |
| -0.129 |
very | -0.128 |
other | -0.123 |
Token | es |
Token ID | 274 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
enery | +0.123 |
rito | +0.116 |
ree | +0.115 |
gy | +0.115 |
rap | +0.114 |
Neg logit contributions | |
so | -0.118 |
he | -0.117 |
| -0.111 |
very | -0.109 |
other | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
gy | +0.068 |
ind | +0.065 |
enery | +0.063 |
ree | +0.063 |
oses | +0.063 |
Neg logit contributions | |
so | -0.032 |
| -0.031 |
nam | -0.031 |
he | -0.030 |
ready | -0.029 |
Token | They |
Token ID | 1119 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
gy | +0.023 |
ree | +0.022 |
oses | +0.021 |
ind | +0.021 |
enery | +0.021 |
Neg logit contributions | |
so | -0.019 |
ready | -0.018 |
nam | -0.017 |
he | -0.017 |
very | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
gy | +0.053 |
ind | +0.051 |
enery | +0.050 |
ree | +0.049 |
rito | +0.049 |
Neg logit contributions | |
so | -0.025 |
| -0.024 |
he | -0.023 |
ready | -0.022 |
very | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gy | +0.031 |
ind | +0.030 |
rap | +0.029 |
enery | +0.029 |
ree | +0.029 |
Neg logit contributions | |
| -0.010 |
he | -0.010 |
so | -0.010 |
nam | -0.009 |
Once | -0.008 |
Token | plants |
Token ID | 6134 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
gy | +0.031 |
ind | +0.028 |
enery | +0.028 |
rap | +0.028 |
ree | +0.028 |
Neg logit contributions | |
| -0.018 |
he | -0.018 |
so | -0.017 |
Once | -0.017 |
ready | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
| +0.014 |
nam | +0.013 |
Once | +0.012 |
he | +0.012 |
so | +0.011 |
Neg logit contributions | |
gy | -0.024 |
rito | -0.022 |
ind | -0.022 |
rap | -0.021 |
enery | -0.021 |
Token | |
Token ID | 220 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
gy | +0.053 |
ree | +0.051 |
ind | +0.049 |
rap | +0.049 |
enery | +0.049 |
Neg logit contributions | |
so | -0.023 |
he | -0.021 |
ready | -0.020 |
nam | -0.020 |
very | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
gy | +0.053 |
ind | +0.052 |
rap | +0.052 |
ree | +0.052 |
enery | +0.051 |
Neg logit contributions | |
so | -0.011 |
he | -0.010 |
| -0.008 |
ready | -0.008 |
very | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ree | +0.031 |
gy | +0.030 |
ind | +0.030 |
rap | +0.030 |
uth | +0.029 |
Neg logit contributions | |
so | -0.010 |
he | -0.009 |
nam | -0.009 |
ready | -0.009 |
very | -0.008 |
Token | G |
Token ID | 38 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
gy | +0.045 |
ind | +0.045 |
ree | +0.044 |
rap | +0.043 |
enery | +0.042 |
Neg logit contributions | |
so | -0.040 |
he | -0.038 |
| -0.037 |
ready | -0.036 |
very | -0.035 |
Token | inger |
Token ID | 3889 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
enery | +0.089 |
ocol | +0.084 |
gy | +0.084 |
eware | +0.080 |
ree | +0.077 |
Neg logit contributions | |
| -0.129 |
next | -0.129 |
he | -0.128 |
so | -0.127 |
she | -0.125 |
Token | was |
Token ID | 373 |
Feature activation | +5.83e-04 |
Pos logit contributions | |
gy | +0.027 |
ind | +0.027 |
enery | +0.026 |
rap | +0.026 |
ree | +0.026 |
Neg logit contributions | |
so | -0.011 |
he | -0.011 |
| -0.010 |
ready | -0.010 |
very | -0.009 |
Token | relieved |
Token ID | 22598 |
Feature activation | -9.81e-04 |
Pos logit contributions | |
he | +0.000 |
| +0.000 |
nam | +0.000 |
Once | +0.000 |
so | +0.000 |
Neg logit contributions | |
gy | -0.001 |
ind | -0.001 |
rap | -0.001 |
rito | -0.001 |
ook | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
gy | +0.002 |
ree | +0.002 |
ind | +0.002 |
enery | +0.002 |
rap | +0.002 |
Neg logit contributions | |
nam | -0.001 |
| -0.001 |
so | -0.001 |
ready | -0.001 |
refreshed | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
gy | +0.023 |
ree | +0.023 |
enery | +0.022 |
ind | +0.022 |
rap | +0.022 |
Neg logit contributions | |
so | -0.018 |
he | -0.017 |
ready | -0.017 |
very | -0.016 |
nam | -0.016 |
Token | over |
Token ID | 625 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
so | +0.009 |
| +0.008 |
he | +0.008 |
ready | +0.008 |
very | +0.007 |
Neg logit contributions | |
gy | -0.016 |
ind | -0.016 |
ree | -0.016 |
enery | -0.016 |
rap | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
| +0.015 |
so | +0.015 |
he | +0.015 |
ready | +0.014 |
nam | +0.013 |
Neg logit contributions | |
ind | -0.037 |
gy | -0.036 |
ree | -0.035 |
rap | -0.035 |
enery | -0.035 |
Token | ." |
Token ID | 526 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
nam | +0.017 |
| +0.017 |
he | +0.017 |
so | +0.016 |
refreshed | +0.016 |
Neg logit contributions | |
gy | -0.018 |
ind | -0.017 |
rap | -0.017 |
ree | -0.016 |
OO | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
gy | +0.033 |
ree | +0.031 |
enery | +0.031 |
ind | +0.030 |
eth | +0.029 |
Neg logit contributions | |
so | -0.014 |
ready | -0.014 |
nam | -0.013 |
very | -0.013 |
next | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
gy | +0.033 |
ind | +0.032 |
ree | +0.032 |
rap | +0.032 |
enery | +0.031 |
Neg logit contributions | |
so | -0.008 |
he | -0.007 |
ready | -0.006 |
| -0.006 |
very | -0.006 |
Token | G |
Token ID | 38 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.037 |
enery | +0.036 |
ree | +0.036 |
rap | +0.036 |
Neg logit contributions | |
so | -0.033 |
he | -0.031 |
| -0.031 |
ready | -0.030 |
very | -0.029 |
Token | avin |
Token ID | 20637 |
Feature activation | +6.63e-04 |
Pos logit contributions | |
ree | +0.118 |
enery | +0.116 |
gy | +0.116 |
eware | +0.116 |
rito | +0.114 |
Neg logit contributions | |
he | -0.108 |
| -0.101 |
so | -0.101 |
next | -0.097 |
ready | -0.091 |
Token | thanked |
Token ID | 26280 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.002 |
ind | -0.002 |
enery | -0.002 |
rap | -0.002 |
ree | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
gy | +0.023 |
ind | +0.023 |
rap | +0.023 |
enery | +0.022 |
ree | +0.022 |
Neg logit contributions | |
so | -0.008 |
ready | -0.007 |
| -0.007 |
he | -0.007 |
very | -0.006 |
Token | woman |
Token ID | 2415 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
ind | +0.005 |
gy | +0.005 |
enery | +0.005 |
ree | +0.005 |
rap | +0.005 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
| -0.003 |
ready | -0.003 |
nam | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +8.33e-03 |
Pos logit contributions | |
gy | +0.015 |
ind | +0.014 |
enery | +0.014 |
ree | +0.014 |
rap | +0.014 |
Neg logit contributions | |
so | -0.008 |
nam | -0.008 |
he | -0.007 |
| -0.007 |
Once | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
| +0.017 |
he | +0.017 |
refreshed | +0.017 |
nam | +0.016 |
ready | +0.016 |
Neg logit contributions | |
gy | -0.031 |
ind | -0.030 |
rap | -0.030 |
ree | -0.028 |
ook | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +6.25e-03 |
Pos logit contributions | |
so | +0.008 |
he | +0.007 |
ready | +0.006 |
| +0.006 |
very | +0.006 |
Neg logit contributions | |
gy | -0.037 |
ind | -0.036 |
ree | -0.036 |
enery | -0.036 |
rap | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
so | +0.004 |
he | +0.003 |
| +0.003 |
ready | +0.003 |
very | +0.002 |
Neg logit contributions | |
gy | -0.018 |
ind | -0.017 |
ree | -0.017 |
rap | -0.017 |
enery | -0.017 |
Token | When |
Token ID | 2215 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
gy | +0.011 |
enery | +0.011 |
ind | +0.011 |
rap | +0.011 |
ocol | +0.011 |
Neg logit contributions | |
so | -0.009 |
he | -0.008 |
| -0.008 |
Once | -0.008 |
very | -0.008 |
Token | D |
Token ID | 360 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
so | +0.013 |
he | +0.012 |
| +0.012 |
nam | +0.011 |
ready | +0.011 |
Neg logit contributions | |
gy | -0.028 |
ind | -0.027 |
enery | -0.027 |
ree | -0.027 |
rap | -0.026 |
Token | ott |
Token ID | 1252 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
so | +0.018 |
he | +0.017 |
| +0.017 |
ready | +0.016 |
very | +0.016 |
Neg logit contributions | |
gy | -0.018 |
ind | -0.018 |
enery | -0.017 |
rito | -0.017 |
ree | -0.017 |
Token | ie |
Token ID | 494 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ocol | +0.123 |
eware | +0.116 |
enery | +0.115 |
oses | +0.110 |
ues | +0.109 |
Neg logit contributions | |
so | -0.112 |
he | -0.108 |
next | -0.108 |
very | -0.105 |
day | -0.102 |
Token | arrived |
Token ID | 5284 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.037 |
enery | +0.037 |
rap | +0.037 |
ree | +0.036 |
Neg logit contributions | |
so | -0.020 |
he | -0.018 |
| -0.018 |
ready | -0.016 |
very | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
so | +0.002 |
| +0.002 |
he | +0.002 |
ready | +0.002 |
nam | +0.002 |
Neg logit contributions | |
gy | -0.003 |
ind | -0.003 |
rap | -0.003 |
ree | -0.003 |
enery | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.004 |
rap | -0.004 |
ind | -0.004 |
ree | -0.004 |
enery | -0.004 |
Token | lab |
Token ID | 2248 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
so | +0.004 |
he | +0.003 |
| +0.003 |
very | +0.003 |
ready | +0.003 |
Neg logit contributions | |
gy | -0.005 |
ind | -0.005 |
rito | -0.005 |
enery | -0.005 |
ocol | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
| +0.000 |
Once | +0.000 |
so | +0.000 |
he | +0.000 |
nam | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ind | -0.000 |
ocol | -0.000 |
rap | -0.000 |
rito | -0.000 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.036 |
enery | +0.035 |
ree | +0.035 |
rito | +0.035 |
Neg logit contributions | |
so | -0.032 |
| -0.031 |
he | -0.030 |
ready | -0.029 |
Once | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ind | +0.005 |
gy | +0.005 |
ocol | +0.005 |
rap | +0.005 |
rito | +0.005 |
Neg logit contributions | |
| -0.003 |
so | -0.003 |
Once | -0.003 |
he | -0.003 |
ready | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.061 |
enery | +0.059 |
rap | +0.059 |
ree | +0.059 |
Neg logit contributions | |
so | -0.045 |
he | -0.043 |
| -0.042 |
ready | -0.039 |
very | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
enery | +0.089 |
gy | +0.089 |
ind | +0.088 |
ocol | +0.088 |
rap | +0.086 |
Neg logit contributions | |
| -0.009 |
so | -0.009 |
he | -0.008 |
very | -0.004 |
Once | -0.004 |
Token | G |
Token ID | 38 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
ocol | +0.111 |
rap | +0.106 |
ues | +0.105 |
enery | +0.105 |
ittered | +0.104 |
Neg logit contributions | |
so | -0.074 |
he | -0.070 |
Once | -0.069 |
| -0.068 |
very | -0.064 |
Token | igi |
Token ID | 25754 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
gy | +0.084 |
ree | +0.082 |
eware | +0.080 |
ples | +0.078 |
oses | +0.077 |
Neg logit contributions | |
he | -0.131 |
next | -0.129 |
so | -0.128 |
| -0.126 |
she | -0.124 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
gy | +0.048 |
ind | +0.047 |
enery | +0.047 |
rap | +0.046 |
ree | +0.046 |
Neg logit contributions | |
so | -0.021 |
he | -0.019 |
| -0.019 |
ready | -0.017 |
very | -0.017 |
Token | about |
Token ID | 546 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
gy | +0.024 |
rap | +0.024 |
ree | +0.024 |
ind | +0.024 |
ocol | +0.023 |
Neg logit contributions | |
so | -0.013 |
| -0.013 |
nam | -0.012 |
he | -0.012 |
ready | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
so | +0.009 |
ready | +0.009 |
refreshed | +0.009 |
| +0.009 |
he | +0.008 |
Neg logit contributions | |
gy | -0.015 |
rap | -0.014 |
ind | -0.014 |
ree | -0.014 |
ocol | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
nam | +0.002 |
| +0.002 |
refreshed | +0.002 |
Once | +0.002 |
he | +0.001 |
Neg logit contributions | |
gy | -0.002 |
rap | -0.002 |
ree | -0.002 |
ant | -0.002 |
ind | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
gy | +0.011 |
ind | +0.011 |
rap | +0.011 |
rito | +0.010 |
enery | +0.010 |
Neg logit contributions | |
he | -0.012 |
so | -0.012 |
| -0.012 |
ready | -0.011 |
nam | -0.011 |
Token | |
Token ID | 220 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
so | +0.011 |
nam | +0.010 |
ready | +0.010 |
he | +0.009 |
very | +0.009 |
Neg logit contributions | |
gy | -0.034 |
ree | -0.033 |
enery | -0.031 |
rito | -0.031 |
ind | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
so | +0.002 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
rap | -0.007 |
ree | -0.007 |
enery | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
so | +0.011 |
he | +0.009 |
| +0.009 |
ready | +0.008 |
very | +0.007 |
Neg logit contributions | |
gy | -0.052 |
ind | -0.051 |
ree | -0.051 |
rap | -0.050 |
enery | -0.050 |
Token | D |
Token ID | 35 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
so | +0.018 |
he | +0.017 |
| +0.017 |
ready | +0.016 |
very | +0.016 |
Neg logit contributions | |
gy | -0.023 |
ind | -0.022 |
ree | -0.022 |
enery | -0.022 |
rap | -0.022 |
Token | ott |
Token ID | 1252 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
gy | +0.020 |
ind | +0.020 |
enery | +0.020 |
uth | +0.019 |
rito | +0.019 |
Neg logit contributions | |
so | -0.015 |
he | -0.014 |
| -0.014 |
very | -0.013 |
right | -0.013 |
Token | ie |
Token ID | 494 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ocol | +0.109 |
enery | +0.107 |
eware | +0.104 |
oses | +0.098 |
ues | +0.095 |
Neg logit contributions | |
so | -0.124 |
very | -0.116 |
he | -0.114 |
| -0.113 |
next | -0.113 |
Token | per |
Token ID | 583 |
Feature activation | +6.91e-04 |
Pos logit contributions | |
so | +0.012 |
nam | +0.012 |
he | +0.012 |
ready | +0.011 |
| +0.011 |
Neg logit contributions | |
gy | -0.028 |
ind | -0.026 |
ree | -0.025 |
enery | -0.025 |
rap | -0.025 |
Token | ked |
Token ID | 9091 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
| +0.001 |
so | +0.001 |
ready | +0.001 |
he | +0.001 |
very | +0.001 |
Neg logit contributions | |
ind | -0.001 |
arter | -0.001 |
enery | -0.001 |
rap | -0.001 |
ifi | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +6.30e-03 |
Pos logit contributions | |
so | +0.006 |
| +0.006 |
he | +0.006 |
ready | +0.006 |
Once | +0.006 |
Neg logit contributions | |
gy | -0.015 |
ree | -0.014 |
enery | -0.014 |
rap | -0.014 |
ind | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
nam | +0.007 |
| +0.007 |
so | +0.007 |
ready | +0.007 |
Once | +0.007 |
Neg logit contributions | |
gy | -0.013 |
ree | -0.012 |
enery | -0.012 |
ind | -0.012 |
rito | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
gy | +0.000 |
ree | +0.000 |
rap | +0.000 |
ind | +0.000 |
enery | +0.000 |
Neg logit contributions | |
so | -0.000 |
ready | -0.000 |
he | -0.000 |
nam | -0.000 |
refreshed | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
so | +0.003 |
ready | +0.003 |
he | +0.003 |
nam | +0.003 |
| +0.002 |
Neg logit contributions | |
gy | -0.012 |
ree | -0.011 |
ind | -0.011 |
rap | -0.011 |
ook | -0.011 |
Token | One |
Token ID | 3198 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
gy | +0.020 |
ind | +0.020 |
ree | +0.020 |
rap | +0.020 |
enery | +0.019 |
Neg logit contributions | |
so | -0.020 |
he | -0.019 |
| -0.019 |
ready | -0.019 |
very | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
gy | +0.033 |
ind | +0.032 |
ree | +0.032 |
rito | +0.031 |
eware | +0.031 |
Neg logit contributions | |
so | -0.009 |
| -0.008 |
nam | -0.008 |
he | -0.007 |
ready | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
gy | +0.020 |
ind | +0.019 |
enery | +0.019 |
ree | +0.019 |
rap | +0.019 |
Neg logit contributions | |
so | -0.008 |
he | -0.007 |
| -0.007 |
ready | -0.007 |
very | -0.006 |
Token | Rus |
Token ID | 9223 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
gy | +0.013 |
ree | +0.013 |
rap | +0.013 |
enery | +0.013 |
eware | +0.013 |
Neg logit contributions | |
so | -0.008 |
| -0.008 |
ready | -0.007 |
refreshed | -0.007 |
he | -0.007 |
Token | sel |
Token ID | 741 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ind | +0.104 |
gy | +0.103 |
ocol | +0.103 |
rito | +0.100 |
ree | +0.100 |
Neg logit contributions | |
so | -0.116 |
next | -0.115 |
he | -0.113 |
very | -0.108 |
right | -0.104 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
gy | +0.049 |
ind | +0.048 |
enery | +0.047 |
ree | +0.047 |
rap | +0.047 |
Neg logit contributions | |
so | -0.021 |
he | -0.019 |
| -0.019 |
ready | -0.018 |
very | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
gy | +0.003 |
rap | +0.003 |
ind | +0.003 |
ree | +0.003 |
enery | +0.003 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
ready | -0.001 |
refreshed | -0.001 |
Token | mum |
Token ID | 25682 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.014 |
enery | +0.013 |
rap | +0.013 |
ree | +0.013 |
Neg logit contributions | |
so | -0.010 |
he | -0.010 |
| -0.010 |
ready | -0.009 |
very | -0.009 |
Token | if |
Token ID | 611 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
gy | +0.013 |
rap | +0.012 |
ind | +0.012 |
enery | +0.012 |
ree | +0.012 |
Neg logit contributions | |
so | -0.009 |
he | -0.008 |
| -0.008 |
ready | -0.008 |
nam | -0.008 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
so | +0.028 |
he | +0.026 |
| +0.026 |
ready | +0.024 |
very | +0.023 |
Neg logit contributions | |
gy | -0.048 |
ind | -0.047 |
enery | -0.046 |
ree | -0.045 |
rap | -0.045 |
Token | named |
Token ID | 3706 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
so | +0.006 |
he | +0.006 |
| +0.006 |
very | +0.006 |
ready | +0.005 |
Neg logit contributions | |
gy | -0.008 |
enery | -0.008 |
rap | -0.008 |
ind | -0.008 |
rito | -0.007 |
Token | Rus |
Token ID | 9223 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
so | +0.006 |
he | +0.005 |
| +0.005 |
ready | +0.005 |
very | +0.005 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.022 |
enery | -0.021 |
rap | -0.021 |
ree | -0.021 |
Token | sel |
Token ID | 741 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
gy | +0.093 |
ree | +0.093 |
ocol | +0.092 |
ucker | +0.089 |
ucks | +0.089 |
Neg logit contributions | |
he | -0.128 |
so | -0.124 |
next | -0.121 |
very | -0.119 |
| -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
gy | +0.043 |
ind | +0.042 |
enery | +0.041 |
rap | +0.041 |
ree | +0.041 |
Neg logit contributions | |
so | -0.015 |
he | -0.014 |
| -0.013 |
ready | -0.012 |
very | -0.012 |
Token | Rus |
Token ID | 9223 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
gy | +0.013 |
ind | +0.013 |
rap | +0.013 |
enery | +0.013 |
ree | +0.012 |
Neg logit contributions | |
so | -0.008 |
he | -0.008 |
| -0.008 |
ready | -0.007 |
very | -0.007 |
Token | sel |
Token ID | 741 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
ree | +0.101 |
ocol | +0.100 |
gy | +0.098 |
ind | +0.097 |
rito | +0.095 |
Neg logit contributions | |
so | -0.121 |
he | -0.119 |
next | -0.118 |
very | -0.114 |
| -0.108 |
Token | had |
Token ID | 550 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
gy | +0.016 |
ind | +0.015 |
enery | +0.015 |
rap | +0.015 |
ree | +0.014 |
Neg logit contributions | |
so | -0.010 |
he | -0.010 |
| -0.010 |
ready | -0.009 |
nam | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
gy | +0.022 |
ind | +0.021 |
ree | +0.021 |
eware | +0.020 |
OO | +0.020 |
Neg logit contributions | |
he | -0.008 |
| -0.008 |
so | -0.007 |
ready | -0.007 |
shop | -0.006 |
Token | pet |
Token ID | 4273 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.013 |
ree | +0.013 |
enery | +0.013 |
rap | +0.012 |
Neg logit contributions | |
so | -0.007 |
he | -0.007 |
| -0.007 |
ready | -0.006 |
Once | -0.006 |
Token | bunny |
Token ID | 44915 |
Feature activation | -1.22e-04 |
Pos logit contributions | |
gy | +0.006 |
ind | +0.006 |
ree | +0.006 |
enery | +0.006 |
oses | +0.006 |
Neg logit contributions | |
so | -0.006 |
| -0.006 |
ready | -0.005 |
he | -0.005 |
nam | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
gy | +0.007 |
rap | +0.006 |
ook | +0.006 |
ind | +0.006 |
OO | +0.006 |
Neg logit contributions | |
nam | -0.005 |
so | -0.005 |
ready | -0.005 |
refreshed | -0.004 |
he | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
he | +0.004 |
| +0.004 |
so | +0.004 |
nam | +0.004 |
ready | +0.003 |
Neg logit contributions | |
gy | -0.011 |
ind | -0.011 |
rap | -0.011 |
ree | -0.010 |
OO | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.003 |
very | +0.003 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
enery | -0.007 |
ree | -0.006 |
rap | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
so | +0.028 |
he | +0.026 |
| +0.026 |
ready | +0.024 |
very | +0.023 |
Neg logit contributions | |
gy | -0.048 |
ind | -0.047 |
enery | -0.046 |
ree | -0.045 |
rap | -0.045 |
Token | named |
Token ID | 3706 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
so | +0.006 |
he | +0.006 |
| +0.006 |
very | +0.006 |
ready | +0.005 |
Neg logit contributions | |
gy | -0.008 |
enery | -0.008 |
rap | -0.008 |
ind | -0.008 |
rito | -0.007 |
Token | Rus |
Token ID | 9223 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
so | +0.006 |
he | +0.005 |
| +0.005 |
ready | +0.005 |
very | +0.005 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.022 |
enery | -0.021 |
rap | -0.021 |
ree | -0.021 |
Token | sel |
Token ID | 741 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
gy | +0.093 |
ree | +0.093 |
ocol | +0.092 |
ucker | +0.089 |
ucks | +0.089 |
Neg logit contributions | |
he | -0.128 |
so | -0.124 |
next | -0.121 |
very | -0.119 |
| -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
gy | +0.043 |
ind | +0.042 |
enery | +0.041 |
rap | +0.041 |
ree | +0.041 |
Neg logit contributions | |
so | -0.015 |
he | -0.014 |
| -0.013 |
ready | -0.012 |
very | -0.012 |
Token | Rus |
Token ID | 9223 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
gy | +0.013 |
ind | +0.013 |
rap | +0.013 |
enery | +0.013 |
ree | +0.012 |
Neg logit contributions | |
so | -0.008 |
he | -0.008 |
| -0.008 |
ready | -0.007 |
very | -0.007 |
Token | sel |
Token ID | 741 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
ree | +0.101 |
ocol | +0.100 |
gy | +0.098 |
ind | +0.097 |
rito | +0.095 |
Neg logit contributions | |
so | -0.121 |
he | -0.119 |
next | -0.118 |
very | -0.114 |
| -0.108 |
Token | had |
Token ID | 550 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
gy | +0.016 |
ind | +0.015 |
enery | +0.015 |
rap | +0.015 |
ree | +0.014 |
Neg logit contributions | |
so | -0.010 |
he | -0.010 |
| -0.010 |
ready | -0.009 |
nam | -0.009 |
Token | far |
Token ID | 1290 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
| +0.009 |
so | +0.009 |
he | +0.009 |
ready | +0.007 |
refreshed | +0.007 |
Neg logit contributions | |
gy | -0.021 |
ind | -0.021 |
rap | -0.020 |
ree | -0.020 |
ook | -0.020 |
Token | away |
Token ID | 1497 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
gy | +0.006 |
rap | +0.006 |
ree | +0.005 |
ind | +0.005 |
OO | +0.005 |
Neg logit contributions | |
so | -0.004 |
he | -0.003 |
very | -0.003 |
| -0.003 |
ready | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
gy | +0.088 |
ind | +0.086 |
enery | +0.085 |
rap | +0.084 |
ree | +0.084 |
Neg logit contributions | |
so | -0.031 |
he | -0.029 |
| -0.028 |
ready | -0.025 |
very | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
gy | +0.053 |
ind | +0.052 |
enery | +0.051 |
ree | +0.051 |
rap | +0.051 |
Neg logit contributions | |
so | -0.016 |
he | -0.014 |
| -0.014 |
ready | -0.013 |
very | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
gy | +0.033 |
ind | +0.033 |
enery | +0.033 |
rap | +0.032 |
ree | +0.032 |
Neg logit contributions | |
so | -0.005 |
he | -0.005 |
| -0.005 |
very | -0.003 |
ready | -0.003 |
Token | G |
Token ID | 38 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
ocol | +0.076 |
enery | +0.075 |
rap | +0.073 |
ues | +0.071 |
rito | +0.071 |
Neg logit contributions | |
so | -0.050 |
| -0.048 |
Once | -0.048 |
he | -0.047 |
very | -0.044 |
Token | igi |
Token ID | 25754 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
ree | +0.081 |
gy | +0.080 |
ples | +0.078 |
eware | +0.076 |
enery | +0.075 |
Neg logit contributions | |
he | -0.131 |
next | -0.130 |
so | -0.127 |
| -0.125 |
she | -0.125 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
ocol | +0.061 |
enery | +0.060 |
ind | +0.060 |
rap | +0.059 |
ree | +0.059 |
Neg logit contributions | |
so | -0.021 |
he | -0.019 |
| -0.019 |
very | -0.017 |
ready | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
gy | +0.009 |
rap | +0.009 |
ind | +0.008 |
ree | +0.008 |
enery | +0.008 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
| -0.003 |
ready | -0.003 |
nam | -0.003 |
Token | friend |
Token ID | 1545 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
gy | +0.017 |
ind | +0.017 |
enery | +0.016 |
ree | +0.016 |
ocol | +0.016 |
Neg logit contributions | |
so | -0.013 |
he | -0.012 |
| -0.011 |
very | -0.011 |
ready | -0.011 |
Token | Duck |
Token ID | 21867 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
gy | +0.019 |
rap | +0.018 |
ree | +0.017 |
ind | +0.017 |
enery | +0.017 |
Neg logit contributions | |
so | -0.009 |
| -0.008 |
he | -0.008 |
ready | -0.008 |
nam | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
gy | +0.079 |
ind | +0.078 |
enery | +0.076 |
rap | +0.076 |
ree | +0.076 |
Neg logit contributions | |
so | -0.014 |
he | -0.012 |
| -0.012 |
ready | -0.010 |
very | -0.009 |
Token | One |
Token ID | 3198 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
gy | +0.095 |
ocol | +0.095 |
rito | +0.095 |
enery | +0.093 |
rap | +0.090 |
Neg logit contributions | |
so | -0.065 |
he | -0.064 |
| -0.062 |
very | -0.058 |
Once | -0.058 |
Token | day |
Token ID | 1110 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
gy | +0.048 |
ind | +0.047 |
ree | +0.047 |
OO | +0.045 |
eware | +0.045 |
Neg logit contributions | |
so | -0.013 |
| -0.013 |
nam | -0.012 |
he | -0.011 |
ready | -0.010 |
Token | Alan |
Token ID | 12246 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
gy | +0.076 |
ind | +0.074 |
enery | +0.073 |
rap | +0.073 |
ree | +0.073 |
Neg logit contributions | |
so | -0.031 |
he | -0.028 |
| -0.027 |
ready | -0.025 |
very | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
gy | +0.068 |
ind | +0.067 |
enery | +0.065 |
ree | +0.065 |
rap | +0.065 |
Neg logit contributions | |
so | -0.027 |
he | -0.024 |
| -0.024 |
ready | -0.022 |
very | -0.021 |
Token | Aub |
Token ID | 19723 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
gy | +0.034 |
ind | +0.033 |
ree | +0.032 |
enery | +0.032 |
rap | +0.032 |
Neg logit contributions | |
so | -0.029 |
he | -0.027 |
| -0.026 |
ready | -0.026 |
very | -0.025 |
Token | rey |
Token ID | 4364 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
gy | +0.097 |
enery | +0.093 |
ree | +0.092 |
rito | +0.092 |
ocol | +0.092 |
Neg logit contributions | |
so | -0.130 |
he | -0.124 |
| -0.124 |
very | -0.118 |
ready | -0.115 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
gy | +0.052 |
ind | +0.048 |
enery | +0.048 |
ree | +0.047 |
rap | +0.047 |
Neg logit contributions | |
so | -0.029 |
he | -0.028 |
| -0.027 |
ready | -0.026 |
nam | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
gy | +0.027 |
ree | +0.026 |
ind | +0.026 |
enery | +0.026 |
rap | +0.025 |
Neg logit contributions | |
so | -0.019 |
| -0.018 |
he | -0.017 |
ready | -0.017 |
nam | -0.017 |
Token | turn |
Token ID | 1210 |
Feature activation | -4.77e-03 |
Pos logit contributions | |
gy | +0.021 |
ind | +0.021 |
enery | +0.020 |
rap | +0.020 |
ree | +0.020 |
Neg logit contributions | |
so | -0.014 |
he | -0.013 |
| -0.013 |
ready | -0.012 |
very | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
gy | +0.010 |
ind | +0.009 |
ree | +0.009 |
enery | +0.009 |
en | +0.009 |
Neg logit contributions | |
| -0.006 |
Once | -0.005 |
shop | -0.005 |
nam | -0.005 |
so | -0.005 |
Token | monkeys |
Token ID | 26697 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
gy | +0.032 |
ind | +0.030 |
enery | +0.030 |
ree | +0.029 |
ocol | +0.028 |
Neg logit contributions | |
| -0.026 |
so | -0.026 |
ready | -0.025 |
he | -0.025 |
Once | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
gy | +0.023 |
ind | +0.021 |
ree | +0.021 |
rap | +0.021 |
enery | +0.021 |
Neg logit contributions | |
so | -0.010 |
| -0.010 |
he | -0.010 |
nam | -0.009 |
ready | -0.009 |
Token | elephants |
Token ID | 25368 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
gy | +0.054 |
ind | +0.054 |
rap | +0.053 |
enery | +0.052 |
ree | +0.052 |
Neg logit contributions | |
so | -0.055 |
he | -0.053 |
| -0.051 |
ready | -0.049 |
very | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
gy | +0.035 |
ind | +0.034 |
ree | +0.033 |
oses | +0.033 |
enery | +0.032 |
Neg logit contributions | |
so | -0.016 |
| -0.016 |
nam | -0.015 |
he | -0.015 |
ready | -0.015 |
Token | gir |
Token ID | 37370 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
gy | +0.057 |
ind | +0.055 |
enery | +0.054 |
ree | +0.053 |
rap | +0.053 |
Neg logit contributions | |
so | -0.054 |
he | -0.052 |
| -0.051 |
ready | -0.049 |
very | -0.048 |
Token | aff |
Token ID | 2001 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
gy | +0.041 |
enery | +0.038 |
rito | +0.037 |
rap | +0.037 |
ind | +0.035 |
Neg logit contributions | |
so | -0.133 |
he | -0.130 |
| -0.124 |
very | -0.123 |
other | -0.118 |
Token | es |
Token ID | 274 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
enery | +0.115 |
rito | +0.109 |
gy | +0.108 |
ree | +0.108 |
eware | +0.106 |
Neg logit contributions | |
so | -0.113 |
he | -0.112 |
| -0.106 |
very | -0.105 |
other | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.057 |
enery | +0.056 |
oses | +0.056 |
ree | +0.055 |
Neg logit contributions | |
so | -0.030 |
nam | -0.030 |
| -0.030 |
ready | -0.028 |
he | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gy | +0.034 |
ree | +0.033 |
ind | +0.031 |
enery | +0.031 |
oses | +0.031 |
Neg logit contributions | |
so | -0.026 |
ready | -0.024 |
he | -0.024 |
very | -0.023 |
nam | -0.023 |
Token | had |
Token ID | 550 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.036 |
enery | +0.036 |
ree | +0.035 |
rap | +0.035 |
Neg logit contributions | |
so | -0.020 |
| -0.019 |
he | -0.019 |
ready | -0.018 |
very | -0.017 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.058 |
enery | +0.057 |
ree | +0.056 |
rito | +0.055 |
Neg logit contributions | |
he | -0.020 |
| -0.019 |
so | -0.019 |
ready | -0.018 |
nam | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
ocol | +0.005 |
rap | +0.005 |
ind | +0.005 |
ant | +0.005 |
ples | +0.005 |
Neg logit contributions | |
so | -0.003 |
| -0.003 |
he | -0.003 |
Once | -0.003 |
ready | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
gy | +0.018 |
rap | +0.017 |
ind | +0.016 |
en | +0.016 |
eware | +0.016 |
Neg logit contributions | |
nam | -0.014 |
| -0.013 |
Once | -0.012 |
refreshed | -0.012 |
so | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
ree | +0.026 |
gy | +0.025 |
rap | +0.025 |
enery | +0.024 |
ook | +0.024 |
Neg logit contributions | |
so | -0.012 |
he | -0.011 |
nam | -0.011 |
ready | -0.011 |
very | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
gy | +0.013 |
ind | +0.013 |
ree | +0.013 |
rap | +0.013 |
enery | +0.013 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
| -0.002 |
ready | -0.002 |
very | -0.002 |
Token | A |
Token ID | 32 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
gy | +0.045 |
ind | +0.043 |
enery | +0.042 |
rito | +0.042 |
ocol | +0.041 |
Neg logit contributions | |
so | -0.032 |
| -0.030 |
he | -0.030 |
very | -0.028 |
ready | -0.028 |
Token | lic |
Token ID | 677 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
ree | +0.028 |
gy | +0.027 |
ind | +0.027 |
enery | +0.026 |
rap | +0.026 |
Neg logit contributions | |
so | -0.024 |
he | -0.023 |
| -0.022 |
ready | -0.022 |
nam | -0.021 |
Token | ia |
Token ID | 544 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
gy | +0.087 |
ind | +0.085 |
enery | +0.083 |
rap | +0.081 |
rito | +0.080 |
Neg logit contributions | |
so | -0.142 |
he | -0.136 |
| -0.134 |
very | -0.129 |
ready | -0.128 |
Token | smiled |
Token ID | 13541 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
gy | +0.015 |
ind | +0.015 |
ree | +0.014 |
enery | +0.014 |
rap | +0.014 |
Neg logit contributions | |
so | -0.008 |
| -0.008 |
he | -0.008 |
ready | -0.007 |
nam | -0.007 |
Token | while |
Token ID | 981 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
gy | +0.010 |
ind | +0.010 |
enery | +0.010 |
ree | +0.009 |
rap | +0.009 |
Neg logit contributions | |
| -0.005 |
so | -0.005 |
he | -0.004 |
nam | -0.004 |
ready | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
ree | +0.025 |
gy | +0.023 |
rap | +0.023 |
ind | +0.023 |
ook | +0.023 |
Neg logit contributions | |
nam | -0.009 |
so | -0.009 |
| -0.009 |
ready | -0.008 |
refreshed | -0.008 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
gy | +0.017 |
ind | +0.017 |
rap | +0.016 |
enery | +0.016 |
ree | +0.016 |
Neg logit contributions | |
so | -0.009 |
he | -0.008 |
| -0.008 |
ready | -0.008 |
very | -0.007 |
Token | boot |
Token ID | 6297 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
so | +0.018 |
nam | +0.018 |
he | +0.018 |
| +0.017 |
ready | +0.017 |
Neg logit contributions | |
gy | -0.024 |
enery | -0.024 |
ree | -0.023 |
ind | -0.023 |
eware | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
nam | +0.004 |
| +0.004 |
Once | +0.004 |
refreshed | +0.004 |
so | +0.003 |
Neg logit contributions | |
gy | -0.006 |
ree | -0.006 |
rap | -0.006 |
enery | -0.006 |
oses | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
nam | +0.031 |
unatt | +0.029 |
so | +0.026 |
ready | +0.025 |
refreshed | +0.023 |
Neg logit contributions | |
eth | -0.062 |
ree | -0.061 |
gy | -0.060 |
ook | -0.057 |
ucks | -0.057 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
so | +0.010 |
he | +0.009 |
| +0.009 |
nam | +0.009 |
ready | +0.009 |
Neg logit contributions | |
gy | -0.017 |
ind | -0.017 |
rap | -0.016 |
ree | -0.016 |
enery | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
so | +0.015 |
he | +0.015 |
| +0.015 |
nam | +0.014 |
ready | +0.013 |
Neg logit contributions | |
gy | -0.025 |
ind | -0.024 |
ree | -0.024 |
enery | -0.024 |
rap | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ready | +0.023 |
so | +0.021 |
nam | +0.021 |
refreshed | +0.021 |
best | +0.021 |
Neg logit contributions | |
ocol | -0.058 |
rap | -0.057 |
en | -0.056 |
gy | -0.056 |
ind | -0.056 |
Token | house |
Token ID | 2156 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
so | +0.037 |
he | +0.036 |
nam | +0.034 |
ready | +0.034 |
| +0.034 |
Neg logit contributions | |
ind | -0.063 |
gy | -0.061 |
enery | -0.060 |
ree | -0.059 |
rap | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
nam | +0.014 |
| +0.013 |
Once | +0.012 |
other | +0.012 |
refreshed | +0.011 |
Neg logit contributions | |
gy | -0.021 |
oses | -0.019 |
enery | -0.018 |
ook | -0.018 |
rap | -0.018 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
so | +0.028 |
Once | +0.027 |
| +0.026 |
nam | +0.025 |
best | +0.025 |
Neg logit contributions | |
gy | -0.042 |
enery | -0.038 |
ree | -0.037 |
ind | -0.036 |
rap | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
so | +0.016 |
he | +0.015 |
| +0.015 |
ready | +0.014 |
nam | +0.014 |
Neg logit contributions | |
gy | -0.034 |
rap | -0.033 |
ind | -0.033 |
enery | -0.033 |
ree | -0.033 |
Token | M |
Token ID | 44 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
so | +0.008 |
he | +0.008 |
| +0.008 |
very | +0.007 |
ready | +0.007 |
Neg logit contributions | |
ind | -0.012 |
gy | -0.012 |
ree | -0.011 |
rap | -0.011 |
enery | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
| +0.031 |
Once | +0.029 |
so | +0.026 |
nam | +0.026 |
refreshed | +0.026 |
Neg logit contributions | |
ocol | -0.049 |
rap | -0.048 |
ind | -0.048 |
oses | -0.048 |
gy | -0.047 |
Token | other |
Token ID | 584 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
he | +0.029 |
| +0.029 |
so | +0.028 |
nam | +0.027 |
Once | +0.026 |
Neg logit contributions | |
gy | -0.038 |
ind | -0.038 |
rito | -0.037 |
enery | -0.037 |
eware | -0.035 |
Token | clouds |
Token ID | 15114 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
he | +0.056 |
so | +0.056 |
| +0.054 |
ready | +0.052 |
nam | +0.050 |
Neg logit contributions | |
gy | -0.065 |
ind | -0.062 |
enery | -0.060 |
rap | -0.059 |
OO | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
| +0.013 |
Once | +0.013 |
nam | +0.012 |
so | +0.011 |
he | +0.011 |
Neg logit contributions | |
gy | -0.020 |
rito | -0.018 |
ind | -0.018 |
oses | -0.018 |
en | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ready | +0.016 |
nam | +0.016 |
so | +0.016 |
refreshed | +0.015 |
unatt | +0.014 |
Neg logit contributions | |
gy | -0.033 |
ree | -0.032 |
ucks | -0.031 |
oses | -0.030 |
ook | -0.030 |
Token | other |
Token ID | 584 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
he | +0.041 |
| +0.041 |
so | +0.041 |
nam | +0.040 |
ready | +0.037 |
Neg logit contributions | |
ind | -0.042 |
ubby | -0.040 |
gy | -0.039 |
rito | -0.038 |
enery | -0.037 |
Token | clouds |
Token ID | 15114 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
so | +0.037 |
he | +0.035 |
| +0.035 |
ready | +0.033 |
very | +0.032 |
Neg logit contributions | |
gy | -0.048 |
ind | -0.047 |
enery | -0.046 |
rap | -0.046 |
ree | -0.045 |
Token | were |
Token ID | 547 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
| +0.020 |
so | +0.019 |
nam | +0.019 |
Once | +0.018 |
he | +0.018 |
Neg logit contributions | |
gy | -0.034 |
cker | -0.031 |
rito | -0.031 |
ittered | -0.031 |
ind | -0.030 |
Token | en |
Token ID | 551 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
he | +0.014 |
| +0.014 |
so | +0.012 |
nam | +0.012 |
Once | +0.011 |
Neg logit contributions | |
gy | -0.032 |
ind | -0.030 |
rap | -0.029 |
rito | -0.029 |
ubby | -0.028 |
Token | vious |
Token ID | 1442 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
so | +0.029 |
he | +0.029 |
| +0.029 |
ready | +0.027 |
very | +0.026 |
Neg logit contributions | |
ree | -0.014 |
ind | -0.013 |
gy | -0.013 |
rap | -0.012 |
ocol | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
nam | +0.022 |
| +0.021 |
refreshed | +0.019 |
ready | +0.019 |
Once | +0.018 |
Neg logit contributions | |
oses | -0.024 |
gy | -0.023 |
ree | -0.023 |
en | -0.022 |
ubby | -0.022 |
Token | little |
Token ID | 1310 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.002 |
ind | -0.002 |
enery | -0.002 |
rap | -0.002 |
ree | -0.002 |
Token | red |
Token ID | 2266 |
Feature activation | +1.73e-04 |
Pos logit contributions | |
so | +0.021 |
he | +0.020 |
| +0.020 |
ready | +0.018 |
very | +0.018 |
Neg logit contributions | |
gy | -0.036 |
ind | -0.035 |
enery | -0.035 |
rap | -0.034 |
ree | -0.034 |
Token | motor |
Token ID | 5584 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
so | +0.000 |
he | +0.000 |
| +0.000 |
very | +0.000 |
ready | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ind | -0.000 |
rap | -0.000 |
enery | -0.000 |
rito | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
so | +0.014 |
| +0.014 |
ready | +0.013 |
he | +0.013 |
refreshed | +0.012 |
Neg logit contributions | |
gy | -0.028 |
ind | -0.026 |
enery | -0.025 |
oses | -0.024 |
ree | -0.024 |
Token | The |
Token ID | 383 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
so | +0.013 |
ready | +0.012 |
he | +0.012 |
very | +0.012 |
| +0.011 |
Neg logit contributions | |
gy | -0.013 |
rap | -0.012 |
ree | -0.012 |
ocol | -0.012 |
enery | -0.012 |
Token | motor |
Token ID | 5584 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
so | +0.033 |
he | +0.032 |
| +0.031 |
nam | +0.031 |
she | +0.031 |
Neg logit contributions | |
ind | -0.032 |
gy | -0.029 |
ubby | -0.029 |
enery | -0.027 |
rito | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +8.30e-03 |
Pos logit contributions | |
nam | +0.039 |
refreshed | +0.037 |
so | +0.036 |
ready | +0.036 |
Once | +0.035 |
Neg logit contributions | |
gy | -0.058 |
ind | -0.049 |
cker | -0.048 |
oses | -0.046 |
oc | -0.046 |
Token | very |
Token ID | 845 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
| +0.006 |
he | +0.006 |
so | +0.005 |
Once | +0.005 |
nam | +0.005 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.021 |
rap | -0.020 |
rito | -0.020 |
ree | -0.020 |
Token | strong |
Token ID | 1913 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
so | +0.022 |
he | +0.021 |
| +0.020 |
ready | +0.018 |
very | +0.018 |
Neg logit contributions | |
gy | -0.047 |
ind | -0.047 |
enery | -0.046 |
rap | -0.045 |
ree | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
| +0.013 |
nam | +0.012 |
Once | +0.011 |
ready | +0.011 |
he | +0.011 |
Neg logit contributions | |
gy | -0.025 |
ind | -0.023 |
enery | -0.022 |
oses | -0.022 |
rap | -0.022 |
Token | always |
Token ID | 1464 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
Once | +0.029 |
so | +0.028 |
| +0.028 |
refreshed | +0.025 |
ready | +0.025 |
Neg logit contributions | |
gy | -0.052 |
ind | -0.049 |
rito | -0.047 |
enery | -0.046 |
cker | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
so | +0.004 |
| +0.004 |
nam | +0.004 |
he | +0.004 |
ready | +0.004 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.008 |
rito | -0.008 |
ree | -0.008 |
cker | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
gy | +0.015 |
ind | +0.014 |
ree | +0.014 |
enery | +0.014 |
rap | +0.014 |
Neg logit contributions | |
so | -0.008 |
he | -0.007 |
ready | -0.007 |
| -0.007 |
very | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.014 |
ree | +0.014 |
rap | +0.014 |
enery | +0.013 |
Neg logit contributions | |
so | -0.005 |
he | -0.005 |
ready | -0.005 |
nam | -0.004 |
| -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
ind | +0.026 |
gy | +0.025 |
ree | +0.024 |
rap | +0.024 |
enery | +0.024 |
Neg logit contributions | |
so | -0.023 |
he | -0.022 |
| -0.021 |
ready | -0.020 |
very | -0.020 |
Token | You |
Token ID | 1639 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
ind | +0.010 |
ucks | +0.010 |
rito | +0.010 |
ples | +0.009 |
gy | +0.009 |
Neg logit contributions | |
so | -0.008 |
he | -0.008 |
| -0.008 |
ready | -0.007 |
very | -0.007 |
Token | 're |
Token ID | 821 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
he | +0.004 |
so | +0.004 |
| +0.004 |
nam | +0.004 |
ready | +0.004 |
Neg logit contributions | |
gy | -0.007 |
rap | -0.006 |
ind | -0.006 |
rito | -0.006 |
OO | -0.006 |
Token | welcome |
Token ID | 7062 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
he | +0.035 |
| +0.030 |
nam | +0.029 |
however | +0.027 |
she | +0.026 |
Neg logit contributions | |
gy | -0.042 |
rap | -0.042 |
ind | -0.041 |
ubby | -0.039 |
rito | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
so | +0.004 |
he | +0.004 |
| +0.004 |
ready | +0.003 |
very | +0.003 |
Neg logit contributions | |
gy | -0.010 |
ind | -0.010 |
enery | -0.010 |
rap | -0.010 |
ree | -0.010 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
| +0.031 |
he | +0.030 |
so | +0.029 |
ready | +0.028 |
nam | +0.028 |
Neg logit contributions | |
ind | -0.060 |
gy | -0.059 |
rap | -0.059 |
ocol | -0.058 |
ubby | -0.057 |
Token | ," |
Token ID | 553 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
so | +0.015 |
he | +0.014 |
| +0.014 |
ready | +0.013 |
nam | +0.013 |
Neg logit contributions | |
gy | -0.025 |
ind | -0.024 |
enery | -0.023 |
rito | -0.023 |
rap | -0.023 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
so | +0.007 |
unatt | +0.006 |
Once | +0.006 |
ready | +0.006 |
| +0.005 |
Neg logit contributions | |
ucks | -0.012 |
ocol | -0.012 |
gy | -0.012 |
ind | -0.012 |
aa | -0.012 |
Token | Amy |
Token ID | 14235 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
gy | +0.028 |
ree | +0.025 |
enery | +0.025 |
ind | +0.025 |
rap | +0.025 |
Neg logit contributions | |
so | -0.012 |
ready | -0.012 |
| -0.011 |
refreshed | -0.011 |
very | -0.011 |
Token | learned |
Token ID | 4499 |
Feature activation | +3.05e-04 |
Pos logit contributions | |
gy | +0.026 |
ind | +0.025 |
ree | +0.024 |
rap | +0.024 |
enery | +0.024 |
Neg logit contributions | |
so | -0.013 |
he | -0.012 |
| -0.012 |
ready | -0.011 |
nam | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
| +0.000 |
so | +0.000 |
he | +0.000 |
ready | +0.000 |
Once | +0.000 |
Neg logit contributions | |
ind | -0.001 |
gy | -0.001 |
ree | -0.001 |
rap | -0.001 |
enery | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
so | +0.013 |
he | +0.012 |
| +0.012 |
ready | +0.012 |
very | +0.011 |
Neg logit contributions | |
gy | -0.019 |
ind | -0.018 |
rap | -0.018 |
enery | -0.018 |
ree | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
he | +0.022 |
| +0.021 |
so | +0.020 |
Once | +0.020 |
refreshed | +0.019 |
Neg logit contributions | |
gy | -0.047 |
ocol | -0.047 |
ind | -0.047 |
enery | -0.047 |
rito | -0.047 |
Token | things |
Token ID | 1243 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
| +0.005 |
so | +0.005 |
he | +0.005 |
Once | +0.005 |
refreshed | +0.004 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
enery | -0.006 |
rito | -0.006 |
ocol | -0.006 |
Token | away |
Token ID | 1497 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
| +0.050 |
Once | +0.041 |
Luke | +0.039 |
he | +0.038 |
James | +0.037 |
Neg logit contributions | |
gy | -0.054 |
out | -0.051 |
ind | -0.050 |
rito | -0.050 |
ishing | -0.047 |
Token | when |
Token ID | 618 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
gy | +0.013 |
ind | +0.012 |
rito | +0.012 |
enery | +0.012 |
en | +0.012 |
Neg logit contributions | |
| -0.008 |
Once | -0.007 |
he | -0.007 |
nam | -0.007 |
refreshed | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
| +0.008 |
so | +0.008 |
Once | +0.007 |
ready | +0.006 |
very | +0.006 |
Neg logit contributions | |
gy | -0.026 |
ind | -0.026 |
ocol | -0.025 |
enery | -0.025 |
rap | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.004 |
enery | +0.004 |
rap | +0.004 |
ree | +0.004 |
Neg logit contributions | |
so | -0.002 |
| -0.002 |
he | -0.002 |
ready | -0.002 |
very | -0.002 |
Token | done |
Token ID | 1760 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
rito | +0.003 |
enery | +0.003 |
rap | +0.003 |
Neg logit contributions | |
| -0.001 |
he | -0.001 |
so | -0.001 |
nam | -0.001 |
Once | -0.001 |
Token | hadn |
Token ID | 8020 |
Feature activation | +3.87e-04 |
Pos logit contributions | |
gy | +0.016 |
ind | +0.015 |
enery | +0.015 |
rito | +0.015 |
ree | +0.015 |
Neg logit contributions | |
so | -0.008 |
| -0.008 |
he | -0.007 |
nam | -0.007 |
ready | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.000 |
very | +0.000 |
Neg logit contributions | |
gy | -0.001 |
ind | -0.001 |
enery | -0.001 |
rap | -0.001 |
ree | -0.001 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
gy | +0.029 |
enery | +0.027 |
rito | +0.027 |
ree | +0.026 |
ind | +0.026 |
Neg logit contributions | |
| -0.026 |
so | -0.025 |
he | -0.024 |
nam | -0.024 |
ready | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +4.27e-03 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
enery | +0.003 |
ree | +0.003 |
rap | +0.003 |
Neg logit contributions | |
| -0.001 |
so | -0.001 |
he | -0.001 |
ready | -0.001 |
Once | -0.001 |
Token | healthy |
Token ID | 5448 |
Feature activation | +7.23e-04 |
Pos logit contributions | |
| +0.007 |
he | +0.006 |
so | +0.006 |
nam | +0.006 |
Once | +0.006 |
Neg logit contributions | |
gy | -0.008 |
ind | -0.008 |
enery | -0.007 |
ree | -0.007 |
rap | -0.007 |
Token | jumping |
Token ID | 14284 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.002 |
ind | -0.001 |
enery | -0.001 |
rap | -0.001 |
ree | -0.001 |
Token | abilities |
Token ID | 7883 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
| +0.017 |
so | +0.016 |
he | +0.016 |
nam | +0.015 |
ready | +0.015 |
Neg logit contributions | |
gy | -0.030 |
ind | -0.029 |
ree | -0.028 |
rap | -0.028 |
enery | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +6.16e-03 |
Pos logit contributions | |
| +0.006 |
nam | +0.006 |
ready | +0.005 |
refreshed | +0.005 |
Once | +0.005 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.009 |
rap | -0.009 |
rito | -0.009 |
en | -0.009 |
Token | |
Token ID | 220 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
so | +0.005 |
nam | +0.005 |
ready | +0.005 |
very | +0.004 |
he | +0.004 |
Neg logit contributions | |
gy | -0.016 |
ree | -0.015 |
rap | -0.015 |
ind | -0.014 |
ook | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
gy | +0.004 |
ree | +0.004 |
rap | +0.004 |
ind | +0.004 |
rito | +0.004 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
ready | -0.001 |
very | -0.001 |
nam | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
so | +0.005 |
nam | +0.004 |
he | +0.004 |
ready | +0.004 |
very | +0.004 |
Neg logit contributions | |
ree | -0.016 |
gy | -0.016 |
ind | -0.016 |
rap | -0.016 |
ook | -0.015 |
Token | Why |
Token ID | 4162 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
so | +0.014 |
he | +0.014 |
| +0.013 |
ready | +0.013 |
very | +0.013 |
Neg logit contributions | |
gy | -0.021 |
ind | -0.021 |
enery | -0.020 |
ree | -0.020 |
rap | -0.020 |
Token | did |
Token ID | 750 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
so | +0.003 |
| +0.003 |
he | +0.003 |
ready | +0.002 |
very | +0.002 |
Neg logit contributions | |
gy | -0.004 |
rap | -0.004 |
ind | -0.004 |
enery | -0.004 |
ree | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.014 |
ree | +0.014 |
rap | +0.014 |
enery | +0.014 |
Neg logit contributions | |
so | -0.005 |
| -0.005 |
ready | -0.004 |
refreshed | -0.004 |
Once | -0.004 |
Token | pinch |
Token ID | 25394 |
Feature activation | -7.15e-03 |
Pos logit contributions | |
so | +0.012 |
he | +0.011 |
| +0.011 |
ready | +0.011 |
very | +0.010 |
Neg logit contributions | |
gy | -0.015 |
ind | -0.014 |
ree | -0.014 |
rap | -0.014 |
enery | -0.014 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
gy | +0.016 |
ind | +0.016 |
ree | +0.015 |
rap | +0.015 |
enery | +0.015 |
Neg logit contributions | |
so | -0.008 |
he | -0.008 |
| -0.008 |
ready | -0.008 |
very | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
rap | +0.028 |
ree | +0.028 |
OO | +0.027 |
Neg logit contributions | |
he | -0.019 |
so | -0.018 |
| -0.018 |
ready | -0.017 |
nam | -0.017 |
Token | face |
Token ID | 1986 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
gy | +0.009 |
ind | +0.008 |
rap | +0.008 |
ree | +0.008 |
rito | +0.008 |
Neg logit contributions | |
he | -0.006 |
| -0.006 |
so | -0.006 |
Once | -0.006 |
ready | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.037 |
rap | +0.036 |
ree | +0.036 |
enery | +0.036 |
Neg logit contributions | |
so | -0.032 |
he | -0.031 |
| -0.031 |
ready | -0.029 |
very | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
nam | +0.014 |
so | +0.014 |
ready | +0.014 |
unatt | +0.013 |
very | +0.012 |
Neg logit contributions | |
ree | -0.031 |
gy | -0.029 |
oses | -0.029 |
ind | -0.028 |
ook | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
so | +0.002 |
he | +0.002 |
| +0.001 |
ready | +0.001 |
very | +0.001 |
Neg logit contributions | |
gy | -0.009 |
ind | -0.009 |
ree | -0.009 |
rap | -0.009 |
enery | -0.008 |
Token | Ben |
Token ID | 11696 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
gy | +0.012 |
ind | +0.012 |
enery | +0.011 |
ree | +0.011 |
rap | +0.011 |
Neg logit contributions | |
so | -0.009 |
he | -0.008 |
| -0.008 |
ready | -0.008 |
very | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -1.48e-04 |
Pos logit contributions | |
rap | +0.023 |
gy | +0.023 |
ree | +0.023 |
ind | +0.022 |
ocol | +0.022 |
Neg logit contributions | |
so | -0.010 |
he | -0.009 |
| -0.009 |
ready | -0.009 |
nam | -0.009 |
Token | bed |
Token ID | 3996 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
gy | +0.000 |
ind | +0.000 |
enery | +0.000 |
rap | +0.000 |
ree | +0.000 |
Neg logit contributions | |
so | -0.000 |
he | -0.000 |
| -0.000 |
ready | -0.000 |
Once | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
gy | +0.019 |
oses | +0.018 |
eth | +0.018 |
ues | +0.018 |
ind | +0.018 |
Neg logit contributions | |
nam | -0.013 |
| -0.012 |
Once | -0.012 |
he | -0.012 |
so | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
so | +0.008 |
he | +0.007 |
ready | +0.007 |
nam | +0.007 |
very | +0.007 |
Neg logit contributions | |
ree | -0.010 |
gy | -0.010 |
ind | -0.010 |
enery | -0.010 |
rap | -0.010 |
Token | gives |
Token ID | 3607 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
gy | +0.025 |
ree | +0.024 |
rito | +0.024 |
ind | +0.023 |
enery | +0.023 |
Neg logit contributions | |
so | -0.019 |
he | -0.018 |
| -0.017 |
very | -0.017 |
ready | -0.016 |
Token | them |
Token ID | 606 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
so | +0.027 |
he | +0.026 |
| +0.025 |
Once | +0.025 |
ready | +0.025 |
Neg logit contributions | |
ind | -0.018 |
rap | -0.018 |
gy | -0.018 |
ocol | -0.017 |
en | -0.016 |
Token | water |
Token ID | 1660 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
so | +0.023 |
| +0.023 |
he | +0.023 |
Once | +0.019 |
ready | +0.019 |
Neg logit contributions | |
gy | -0.051 |
ind | -0.050 |
enery | -0.048 |
rito | -0.048 |
rap | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -9.23e-03 |
Pos logit contributions | |
so | +0.004 |
| +0.004 |
nam | +0.004 |
he | +0.004 |
Once | +0.004 |
Neg logit contributions | |
gy | -0.008 |
rito | -0.008 |
enery | -0.008 |
ind | -0.008 |
rap | -0.008 |
Token | hugs |
Token ID | 40657 |
Feature activation | +4.03e-04 |
Pos logit contributions | |
gy | +0.018 |
enery | +0.017 |
ocol | +0.017 |
ind | +0.017 |
rito | +0.017 |
Neg logit contributions | |
so | -0.012 |
| -0.012 |
Once | -0.011 |
he | -0.011 |
very | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
so | +0.001 |
ready | +0.001 |
refreshed | +0.001 |
nam | +0.001 |
he | +0.001 |
Neg logit contributions | |
ind | -0.000 |
gy | -0.000 |
en | -0.000 |
enery | -0.000 |
rap | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
so | +0.010 |
he | +0.008 |
ready | +0.008 |
nam | +0.008 |
very | +0.008 |
Neg logit contributions | |
ree | -0.020 |
gy | -0.020 |
ind | -0.019 |
rap | -0.019 |
oses | -0.019 |
Token | We |
Token ID | 775 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
gy | +0.016 |
ind | +0.016 |
enery | +0.016 |
rap | +0.015 |
ree | +0.015 |
Neg logit contributions | |
so | -0.010 |
he | -0.010 |
| -0.010 |
ready | -0.009 |
very | -0.009 |
Token | have |
Token ID | 423 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
so | +0.002 |
| +0.002 |
he | +0.002 |
very | +0.002 |
ready | +0.002 |
Neg logit contributions | |
ind | -0.003 |
gy | -0.003 |
enery | -0.002 |
ree | -0.002 |
rap | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
ree | +0.028 |
rap | +0.027 |
enery | +0.027 |
Neg logit contributions | |
he | -0.020 |
so | -0.020 |
| -0.020 |
ready | -0.018 |
Once | -0.017 |
Token | save |
Token ID | 3613 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
so | +0.002 |
he | +0.002 |
| +0.002 |
ready | +0.002 |
very | +0.002 |
Neg logit contributions | |
gy | -0.003 |
ind | -0.003 |
rap | -0.003 |
enery | -0.003 |
ree | -0.002 |
Token | our |
Token ID | 674 |
Feature activation | -2.48e-04 |
Pos logit contributions | |
ind | +0.036 |
gy | +0.036 |
rap | +0.035 |
enery | +0.035 |
ree | +0.034 |
Neg logit contributions | |
so | -0.014 |
he | -0.014 |
| -0.014 |
Once | -0.013 |
ready | -0.012 |
Token | money |
Token ID | 1637 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
ind | +0.000 |
gy | +0.000 |
enery | +0.000 |
rap | +0.000 |
ocol | +0.000 |
Neg logit contributions | |
he | -0.000 |
| -0.000 |
so | -0.000 |
she | -0.000 |
nam | -0.000 |
Token | ." |
Token ID | 526 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
gy | +0.005 |
ind | +0.005 |
oses | +0.005 |
rap | +0.005 |
rito | +0.005 |
Neg logit contributions | |
| -0.004 |
Once | -0.004 |
refreshed | -0.004 |
nam | -0.004 |
he | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
gy | +0.015 |
ree | +0.015 |
rap | +0.014 |
ind | +0.014 |
enery | +0.014 |
Neg logit contributions | |
he | -0.006 |
so | -0.006 |
ready | -0.006 |
nam | -0.005 |
very | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
nam | +0.004 |
he | +0.004 |
so | +0.004 |
ready | +0.004 |
| +0.004 |
Neg logit contributions | |
gy | -0.006 |
ind | -0.006 |
ree | -0.006 |
OO | -0.006 |
rap | -0.006 |
Token | impatient |
Token ID | 33440 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
gy | +0.024 |
ind | +0.023 |
rito | +0.023 |
ocol | +0.023 |
enery | +0.022 |
Neg logit contributions | |
he | -0.011 |
| -0.011 |
so | -0.011 |
Once | -0.010 |
ready | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
nam | +0.008 |
| +0.007 |
Once | +0.007 |
refreshed | +0.006 |
ready | +0.006 |
Neg logit contributions | |
gy | -0.010 |
en | -0.010 |
ind | -0.009 |
oses | -0.009 |
ree | -0.009 |
Token | rolled |
Token ID | 11686 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
gy | +0.047 |
ind | +0.045 |
enery | +0.044 |
rap | +0.044 |
ree | +0.044 |
Neg logit contributions | |
so | -0.033 |
he | -0.031 |
| -0.031 |
ready | -0.029 |
very | -0.028 |
Token | down |
Token ID | 866 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
| +0.008 |
so | +0.008 |
he | +0.008 |
Once | +0.007 |
refreshed | +0.007 |
Neg logit contributions | |
gy | -0.012 |
ind | -0.012 |
enery | -0.011 |
ree | -0.011 |
rap | -0.011 |
Token | Frankie |
Token ID | 48535 |
Feature activation | -9.18e-03 |
Pos logit contributions | |
gy | +0.034 |
rap | +0.030 |
rito | +0.030 |
enery | +0.030 |
ree | +0.029 |
Neg logit contributions | |
nam | -0.014 |
| -0.013 |
refreshed | -0.012 |
so | -0.012 |
ready | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
gy | +0.022 |
ind | +0.021 |
enery | +0.020 |
ree | +0.020 |
rap | +0.020 |
Neg logit contributions | |
so | -0.009 |
nam | -0.009 |
| -0.009 |
he | -0.008 |
Once | -0.008 |
Token | face |
Token ID | 1986 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
he | +0.003 |
| +0.003 |
so | +0.003 |
ready | +0.003 |
Once | +0.003 |
Neg logit contributions | |
gy | -0.003 |
ind | -0.003 |
enery | -0.003 |
ree | -0.002 |
rito | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -9.26e-03 |
Pos logit contributions | |
gy | +0.006 |
ree | +0.006 |
ind | +0.005 |
en | +0.005 |
oses | +0.005 |
Neg logit contributions | |
nam | -0.004 |
| -0.004 |
Once | -0.003 |
so | -0.003 |
refreshed | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | -3.48e-04 |
Pos logit contributions | |
gy | +0.020 |
ind | +0.019 |
enery | +0.018 |
ree | +0.018 |
rap | +0.018 |
Neg logit contributions | |
so | -0.012 |
he | -0.012 |
| -0.011 |
ready | -0.011 |
very | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
gy | +0.001 |
ind | +0.001 |
enery | +0.001 |
ree | +0.001 |
rap | +0.001 |
Neg logit contributions | |
so | -0.000 |
| -0.000 |
he | -0.000 |
ready | -0.000 |
nam | -0.000 |
Token | become |
Token ID | 1716 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
gy | +0.006 |
ind | +0.005 |
ree | +0.005 |
rito | +0.005 |
rap | +0.005 |
Neg logit contributions | |
| -0.004 |
so | -0.004 |
he | -0.004 |
nam | -0.004 |
ready | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
| +0.010 |
he | +0.010 |
so | +0.009 |
Once | +0.009 |
ready | +0.008 |
Neg logit contributions | |
gy | -0.025 |
ind | -0.024 |
enery | -0.023 |
ocol | -0.023 |
rito | -0.023 |
Token | comfortable |
Token ID | 6792 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
so | +0.004 |
| +0.004 |
he | +0.003 |
ready | +0.003 |
Once | +0.003 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
ree | -0.007 |
enery | -0.007 |
ocol | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
ind | +0.011 |
ocol | +0.011 |
enery | +0.011 |
rito | +0.011 |
gy | +0.011 |
Neg logit contributions | |
| -0.008 |
so | -0.008 |
nam | -0.007 |
ready | -0.007 |
he | -0.007 |
Token | exciting |
Token ID | 7895 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
ind | +0.009 |
ocol | +0.009 |
enery | +0.009 |
gy | +0.009 |
rito | +0.008 |
Neg logit contributions | |
| -0.005 |
so | -0.005 |
he | -0.005 |
ready | -0.005 |
Once | -0.004 |
Token | things |
Token ID | 1243 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
gy | +0.030 |
ree | +0.029 |
rap | +0.029 |
ind | +0.029 |
rito | +0.029 |
Neg logit contributions | |
so | -0.016 |
he | -0.015 |
| -0.014 |
very | -0.013 |
ready | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
nam | +0.007 |
| +0.007 |
Once | +0.006 |
Mom | +0.006 |
Dad | +0.006 |
Neg logit contributions | |
gy | -0.011 |
en | -0.010 |
rito | -0.010 |
enery | -0.010 |
ittered | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
so | +0.010 |
nam | +0.009 |
ready | +0.009 |
very | +0.008 |
he | +0.008 |
Neg logit contributions | |
gy | -0.020 |
ree | -0.019 |
ocol | -0.019 |
enery | -0.019 |
rito | -0.019 |
Token | even |
Token ID | 772 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
so | +0.002 |
| +0.002 |
he | +0.002 |
nam | +0.002 |
ready | +0.002 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
ree | -0.004 |
enery | -0.003 |
rap | -0.003 |
Token | waved |
Token ID | 26834 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
gy | +0.029 |
ree | +0.028 |
enery | +0.027 |
ind | +0.027 |
rito | +0.027 |
Neg logit contributions | |
so | -0.022 |
| -0.021 |
he | -0.021 |
ready | -0.020 |
nam | -0.019 |
Token | hello |
Token ID | 23748 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
| +0.015 |
so | +0.015 |
he | +0.014 |
ready | +0.013 |
nam | +0.013 |
Neg logit contributions | |
gy | -0.027 |
ind | -0.027 |
enery | -0.026 |
ree | -0.026 |
rap | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -8.62e-04 |
Pos logit contributions | |
so | +0.006 |
| +0.006 |
he | +0.006 |
ready | +0.006 |
nam | +0.006 |
Neg logit contributions | |
gy | -0.012 |
ind | -0.012 |
ree | -0.012 |
enery | -0.011 |
rap | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
gy | +0.002 |
ind | +0.002 |
enery | +0.002 |
rap | +0.002 |
ocol | +0.002 |
Neg logit contributions | |
so | -0.001 |
ready | -0.001 |
he | -0.001 |
| -0.001 |
nam | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
ind | +0.016 |
ocol | +0.015 |
enery | +0.015 |
ree | +0.014 |
oses | +0.014 |
Neg logit contributions | |
| -0.010 |
so | -0.009 |
nam | -0.009 |
Once | -0.009 |
he | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -8.18e-03 |
Pos logit contributions | |
| +0.022 |
he | +0.020 |
Once | +0.019 |
so | +0.018 |
nowhere | +0.017 |
Neg logit contributions | |
gy | -0.040 |
rap | -0.036 |
ind | -0.036 |
enery | -0.035 |
ook | -0.034 |
Token | If |
Token ID | 1002 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
ree | +0.015 |
gy | +0.015 |
oses | +0.014 |
rap | +0.014 |
eth | +0.014 |
Neg logit contributions | |
so | -0.012 |
ready | -0.011 |
nam | -0.011 |
he | -0.011 |
very | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
so | +0.007 |
| +0.006 |
refreshed | +0.006 |
ready | +0.006 |
Once | +0.005 |
Neg logit contributions | |
gy | -0.017 |
enery | -0.016 |
oses | -0.016 |
ocol | -0.016 |
rap | -0.016 |
Token | cards |
Token ID | 4116 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
gy | +0.024 |
ind | +0.024 |
enery | +0.024 |
ree | +0.023 |
rap | +0.023 |
Neg logit contributions | |
| -0.022 |
he | -0.022 |
so | -0.021 |
Once | -0.020 |
refreshed | -0.019 |
Token | have |
Token ID | 423 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
nam | +0.010 |
so | +0.010 |
| +0.010 |
refreshed | +0.009 |
Once | +0.009 |
Neg logit contributions | |
gy | -0.011 |
rap | -0.010 |
its | -0.010 |
ues | -0.010 |
ra | -0.010 |
Token | different |
Token ID | 1180 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
gy | +0.090 |
ind | +0.087 |
enery | +0.086 |
rap | +0.085 |
ree | +0.085 |
Neg logit contributions | |
so | -0.053 |
he | -0.050 |
| -0.050 |
ready | -0.046 |
very | -0.045 |
Token | pictures |
Token ID | 5986 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
gy | +0.057 |
ind | +0.055 |
enery | +0.054 |
rap | +0.054 |
ree | +0.054 |
Neg logit contributions | |
so | -0.040 |
he | -0.039 |
| -0.038 |
ready | -0.036 |
very | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
nam | +0.007 |
| +0.007 |
refreshed | +0.006 |
Once | +0.006 |
so | +0.006 |
Neg logit contributions | |
ues | -0.010 |
gy | -0.010 |
rap | -0.010 |
oses | -0.009 |
en | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
oses | +0.015 |
gy | +0.015 |
ocol | +0.014 |
enery | +0.014 |
rap | +0.014 |
Neg logit contributions | |
| -0.006 |
so | -0.005 |
Once | -0.005 |
refreshed | -0.005 |
ready | -0.005 |
Token | say |
Token ID | 910 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
gy | +0.018 |
ind | +0.017 |
enery | +0.017 |
rap | +0.017 |
ree | +0.016 |
Neg logit contributions | |
so | -0.013 |
he | -0.012 |
| -0.012 |
ready | -0.012 |
very | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ues | +0.017 |
oses | +0.017 |
rap | +0.016 |
ree | +0.016 |
gy | +0.016 |
Neg logit contributions | |
so | -0.009 |
he | -0.009 |
| -0.009 |
nam | -0.009 |
ready | -0.009 |
Token | dog |
Token ID | 3290 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
gy | +0.000 |
ind | +0.000 |
enery | +0.000 |
majesty | +0.000 |
eth | +0.000 |
Neg logit contributions | |
so | -0.000 |
| -0.000 |
Once | -0.000 |
refreshed | -0.000 |
he | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
so | +0.007 |
he | +0.007 |
| +0.007 |
ready | +0.006 |
nam | +0.006 |
Neg logit contributions | |
gy | -0.015 |
ind | -0.014 |
enery | -0.014 |
rap | -0.013 |
ree | -0.013 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
gy | +0.006 |
ree | +0.005 |
oses | +0.005 |
ind | +0.005 |
aa | +0.005 |
Neg logit contributions | |
refreshed | -0.004 |
middle | -0.004 |
| -0.004 |
onwards | -0.004 |
unatt | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
so | +0.002 |
he | +0.002 |
| +0.002 |
very | +0.001 |
ready | +0.001 |
Neg logit contributions | |
gy | -0.005 |
ind | -0.005 |
ree | -0.005 |
enery | -0.005 |
rap | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
gy | +0.009 |
ree | +0.008 |
rap | +0.008 |
eth | +0.008 |
ucks | +0.008 |
Neg logit contributions | |
so | -0.007 |
ready | -0.007 |
nam | -0.007 |
he | -0.007 |
very | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.014 |
ree | +0.013 |
OO | +0.013 |
eware | +0.013 |
Neg logit contributions | |
nam | -0.005 |
so | -0.005 |
| -0.005 |
he | -0.004 |
ready | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ind | +0.035 |
gy | +0.035 |
enery | +0.034 |
rito | +0.034 |
rap | +0.034 |
Neg logit contributions | |
so | -0.011 |
he | -0.010 |
| -0.010 |
very | -0.009 |
ready | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
gy | +0.025 |
ree | +0.023 |
rap | +0.023 |
enery | +0.022 |
ind | +0.022 |
Neg logit contributions | |
so | -0.011 |
| -0.010 |
refreshed | -0.009 |
ready | -0.009 |
very | -0.008 |
Token | went |
Token ID | 1816 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
ree | +0.028 |
rap | +0.028 |
enery | +0.028 |
Neg logit contributions | |
so | -0.010 |
he | -0.009 |
| -0.009 |
ready | -0.008 |
very | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
enery | +0.003 |
rap | +0.003 |
ree | +0.003 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
ready | -0.001 |
very | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
gy | +0.026 |
ind | +0.026 |
rap | +0.025 |
ree | +0.025 |
enery | +0.025 |
Neg logit contributions | |
so | -0.007 |
he | -0.007 |
| -0.006 |
ready | -0.006 |
very | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
ocol | +0.004 |
gy | +0.004 |
ind | +0.004 |
ubby | +0.004 |
rap | +0.003 |
Neg logit contributions | |
he | -0.002 |
ready | -0.002 |
refreshed | -0.002 |
so | -0.002 |
| -0.002 |
Token | hearts |
Token ID | 11954 |
Feature activation | +8.10e-03 |
Pos logit contributions | |
gy | +0.005 |
ind | +0.005 |
enery | +0.005 |
ocol | +0.004 |
ree | +0.004 |
Neg logit contributions | |
so | -0.004 |
he | -0.004 |
ready | -0.003 |
| -0.003 |
Once | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
nam | +0.014 |
Once | +0.012 |
| +0.012 |
refreshed | +0.011 |
ready | +0.011 |
Neg logit contributions | |
gy | -0.013 |
oses | -0.012 |
ess | -0.012 |
ues | -0.011 |
rito | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
gy | +0.005 |
ree | +0.005 |
ucks | +0.005 |
oses | +0.005 |
eth | +0.005 |
Neg logit contributions | |
so | -0.006 |
nam | -0.006 |
ready | -0.006 |
refreshed | -0.006 |
very | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
so | +0.005 |
| +0.004 |
he | +0.004 |
ready | +0.004 |
next | +0.004 |
Neg logit contributions | |
gy | -0.007 |
ind | -0.007 |
cker | -0.007 |
igg | -0.007 |
rito | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
gy | +0.031 |
ind | +0.030 |
ree | +0.029 |
rap | +0.029 |
enery | +0.029 |
Neg logit contributions | |
| -0.014 |
so | -0.014 |
he | -0.013 |
ready | -0.012 |
Once | -0.012 |
Token | lesson |
Token ID | 11483 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
gy | +0.050 |
ind | +0.049 |
enery | +0.048 |
ocol | +0.048 |
rap | +0.048 |
Neg logit contributions | |
so | -0.029 |
he | -0.028 |
| -0.027 |
very | -0.026 |
ready | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ind | +0.004 |
gy | +0.004 |
rap | +0.004 |
oses | +0.004 |
enery | +0.004 |
Neg logit contributions | |
| -0.002 |
so | -0.002 |
ready | -0.002 |
nam | -0.002 |
refreshed | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
gy | +0.025 |
ind | +0.024 |
ree | +0.024 |
ucks | +0.024 |
enery | +0.023 |
Neg logit contributions | |
so | -0.023 |
he | -0.022 |
ready | -0.022 |
very | -0.021 |
nam | -0.020 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.004 |
rap | +0.004 |
enery | +0.004 |
rito | +0.004 |
Neg logit contributions | |
so | -0.002 |
| -0.002 |
he | -0.002 |
ready | -0.002 |
nam | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
gy | +0.026 |
ind | +0.025 |
ree | +0.025 |
enery | +0.024 |
rap | +0.024 |
Neg logit contributions | |
| -0.022 |
so | -0.022 |
Once | -0.020 |
he | -0.020 |
ready | -0.020 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
gy | +0.002 |
ree | +0.002 |
ind | +0.001 |
OO | +0.001 |
rap | +0.001 |
Neg logit contributions | |
nam | -0.001 |
so | -0.001 |
ready | -0.001 |
he | -0.001 |
very | -0.001 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
rap | +0.002 |
ree | +0.002 |
enery | +0.002 |
Neg logit contributions | |
so | -0.003 |
he | -0.003 |
| -0.003 |
ready | -0.003 |
very | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
| +0.016 |
nam | +0.015 |
so | +0.015 |
ready | +0.015 |
he | +0.015 |
Neg logit contributions | |
gy | -0.041 |
ind | -0.038 |
ree | -0.038 |
OO | -0.037 |
rap | -0.037 |
Token | time |
Token ID | 640 |
Feature activation | -8.84e-04 |
Pos logit contributions | |
gy | +0.017 |
ind | +0.017 |
ree | +0.017 |
rap | +0.017 |
enery | +0.017 |
Neg logit contributions | |
so | -0.007 |
he | -0.006 |
| -0.006 |
ready | -0.006 |
very | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
gy | +0.002 |
rap | +0.002 |
ree | +0.002 |
OO | +0.002 |
ind | +0.002 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
nam | -0.001 |
ready | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
enery | +0.029 |
ree | +0.029 |
rap | +0.029 |
Neg logit contributions | |
so | -0.007 |
he | -0.005 |
| -0.005 |
ready | -0.005 |
very | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
gy | +0.033 |
rap | +0.030 |
ind | +0.030 |
ook | +0.029 |
OO | +0.029 |
Neg logit contributions | |
nam | -0.019 |
so | -0.018 |
ready | -0.017 |
he | -0.017 |
| -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
gy | +0.013 |
ind | +0.013 |
ree | +0.012 |
OO | +0.012 |
rap | +0.012 |
Neg logit contributions | |
he | -0.005 |
| -0.005 |
so | -0.004 |
nam | -0.004 |
ready | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.004 |
enery | +0.004 |
ree | +0.004 |
rap | +0.004 |
Neg logit contributions | |
so | -0.002 |
he | -0.002 |
| -0.002 |
ready | -0.002 |
very | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
so | +0.022 |
| +0.021 |
he | +0.021 |
ready | +0.020 |
very | +0.018 |
Neg logit contributions | |
gy | -0.035 |
ind | -0.034 |
enery | -0.033 |
ree | -0.032 |
rito | -0.032 |
Token | named |
Token ID | 3706 |
Feature activation | -7.11e-04 |
Pos logit contributions | |
gy | +0.007 |
enery | +0.007 |
ind | +0.007 |
rap | +0.007 |
ree | +0.007 |
Neg logit contributions | |
so | -0.006 |
he | -0.005 |
| -0.005 |
very | -0.005 |
ready | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
so | +0.009 |
nam | +0.008 |
refreshed | +0.008 |
he | +0.008 |
| +0.007 |
Neg logit contributions | |
gy | -0.015 |
ind | -0.014 |
enery | -0.014 |
rap | -0.014 |
ook | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ind | +0.029 |
gy | +0.029 |
rap | +0.028 |
enery | +0.028 |
rito | +0.028 |
Neg logit contributions | |
so | -0.016 |
| -0.015 |
he | -0.015 |
ready | -0.013 |
very | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
gy | +0.024 |
ind | +0.023 |
enery | +0.022 |
rap | +0.022 |
ree | +0.022 |
Neg logit contributions | |
so | -0.016 |
he | -0.014 |
| -0.014 |
ready | -0.014 |
very | -0.013 |
Token | many |
Token ID | 867 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
gy | +0.060 |
ind | +0.058 |
enery | +0.057 |
ree | +0.055 |
rap | +0.055 |
Neg logit contributions | |
so | -0.024 |
| -0.024 |
he | -0.023 |
ready | -0.023 |
Once | -0.021 |
Token | animals |
Token ID | 4695 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
gy | +0.044 |
ree | +0.042 |
ind | +0.042 |
enery | +0.042 |
rap | +0.042 |
Neg logit contributions | |
so | -0.028 |
he | -0.026 |
| -0.025 |
very | -0.024 |
ready | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
gy | +0.005 |
ind | +0.005 |
oses | +0.005 |
enery | +0.005 |
ook | +0.005 |
Neg logit contributions | |
| -0.002 |
so | -0.002 |
nam | -0.002 |
ready | -0.002 |
he | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
gy | +0.100 |
ind | +0.097 |
enery | +0.095 |
ree | +0.095 |
rito | +0.093 |
Neg logit contributions | |
so | -0.065 |
| -0.063 |
he | -0.062 |
ready | -0.059 |
very | -0.056 |
Token | lions |
Token ID | 31420 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
gy | +0.030 |
ind | +0.029 |
enery | +0.027 |
ree | +0.027 |
rap | +0.026 |
Neg logit contributions | |
so | -0.038 |
| -0.038 |
ready | -0.037 |
he | -0.037 |
nam | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
gy | +0.021 |
oses | +0.020 |
ind | +0.020 |
rap | +0.019 |
enery | +0.019 |
Neg logit contributions | |
nam | -0.012 |
so | -0.012 |
ready | -0.011 |
| -0.011 |
he | -0.011 |
Token | monkeys |
Token ID | 26697 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
gy | +0.072 |
ind | +0.072 |
rap | +0.071 |
enery | +0.069 |
ree | +0.069 |
Neg logit contributions | |
so | -0.072 |
he | -0.069 |
| -0.066 |
very | -0.063 |
ready | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
gy | +0.028 |
ind | +0.026 |
ree | +0.026 |
rap | +0.026 |
enery | +0.026 |
Neg logit contributions | |
so | -0.012 |
he | -0.011 |
| -0.011 |
ready | -0.011 |
nam | -0.010 |
Token | like |
Token ID | 588 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
gy | +0.090 |
ind | +0.084 |
enery | +0.084 |
ree | +0.084 |
rito | +0.082 |
Neg logit contributions | |
| -0.050 |
ready | -0.046 |
so | -0.046 |
he | -0.046 |
refreshed | -0.043 |
Token | monkeys |
Token ID | 26697 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
gy | +0.032 |
ind | +0.030 |
enery | +0.030 |
ree | +0.029 |
ocol | +0.028 |
Neg logit contributions | |
| -0.026 |
so | -0.026 |
ready | -0.025 |
he | -0.025 |
Once | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
gy | +0.023 |
ind | +0.021 |
ree | +0.021 |
rap | +0.021 |
enery | +0.021 |
Neg logit contributions | |
so | -0.010 |
| -0.010 |
he | -0.010 |
nam | -0.009 |
ready | -0.009 |
Token | elephants |
Token ID | 25368 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
gy | +0.054 |
ind | +0.054 |
rap | +0.053 |
enery | +0.052 |
ree | +0.052 |
Neg logit contributions | |
so | -0.055 |
he | -0.053 |
| -0.051 |
ready | -0.049 |
very | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
gy | +0.035 |
ind | +0.034 |
ree | +0.033 |
oses | +0.033 |
enery | +0.032 |
Neg logit contributions | |
so | -0.016 |
| -0.016 |
nam | -0.015 |
he | -0.015 |
ready | -0.015 |
Token | gir |
Token ID | 37370 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
gy | +0.057 |
ind | +0.055 |
enery | +0.054 |
ree | +0.053 |
rap | +0.053 |
Neg logit contributions | |
so | -0.054 |
he | -0.052 |
| -0.051 |
ready | -0.049 |
very | -0.048 |
Token | aff |
Token ID | 2001 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
gy | +0.041 |
enery | +0.038 |
rito | +0.037 |
rap | +0.037 |
ind | +0.035 |
Neg logit contributions | |
so | -0.133 |
he | -0.130 |
| -0.124 |
very | -0.123 |
other | -0.118 |
Token | es |
Token ID | 274 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
enery | +0.115 |
rito | +0.109 |
gy | +0.108 |
ree | +0.108 |
eware | +0.106 |
Neg logit contributions | |
so | -0.113 |
he | -0.112 |
| -0.106 |
very | -0.105 |
other | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.057 |
enery | +0.056 |
oses | +0.056 |
ree | +0.055 |
Neg logit contributions | |
so | -0.030 |
nam | -0.030 |
| -0.030 |
ready | -0.028 |
he | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gy | +0.034 |
ree | +0.033 |
ind | +0.031 |
enery | +0.031 |
oses | +0.031 |
Neg logit contributions | |
so | -0.026 |
ready | -0.024 |
he | -0.024 |
very | -0.023 |
nam | -0.023 |
Token | had |
Token ID | 550 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
gy | +0.038 |
ind | +0.036 |
enery | +0.036 |
ree | +0.035 |
rap | +0.035 |
Neg logit contributions | |
so | -0.020 |
| -0.019 |
he | -0.019 |
ready | -0.018 |
very | -0.017 |
Token | play |
Token ID | 711 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
gy | +0.006 |
ind | +0.006 |
enery | +0.006 |
rap | +0.006 |
ree | +0.006 |
Neg logit contributions | |
so | -0.004 |
he | -0.004 |
| -0.004 |
ready | -0.003 |
very | -0.003 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
so | +0.010 |
he | +0.009 |
| +0.008 |
ready | +0.008 |
very | +0.008 |
Neg logit contributions | |
gy | -0.026 |
ind | -0.025 |
enery | -0.025 |
rap | -0.025 |
ree | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-04 |
Pos logit contributions | |
| +0.002 |
refreshed | +0.002 |
ready | +0.002 |
nam | +0.002 |
he | +0.002 |
Neg logit contributions | |
gy | -0.004 |
ind | -0.004 |
en | -0.004 |
rap | -0.004 |
ook | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
so | +0.001 |
he | +0.001 |
| +0.001 |
very | +0.001 |
ready | +0.001 |
Neg logit contributions | |
ind | -0.001 |
gy | -0.001 |
rap | -0.001 |
rito | -0.001 |
enery | -0.001 |
Token | sand |
Token ID | 6450 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
so | +0.005 |
he | +0.004 |
| +0.004 |
very | +0.004 |
ready | +0.004 |
Neg logit contributions | |
gy | -0.010 |
rito | -0.010 |
enery | -0.010 |
ind | -0.010 |
eware | -0.010 |
Token | cast |
Token ID | 2701 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
gy | +0.011 |
ind | +0.011 |
ree | +0.010 |
enery | +0.010 |
rito | +0.010 |
Neg logit contributions | |
so | -0.008 |
he | -0.008 |
| -0.007 |
ready | -0.007 |
very | -0.007 |
Token | les |
Token ID | 829 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
gy | +0.047 |
enery | +0.043 |
ree | +0.040 |
ind | +0.039 |
rito | +0.039 |
Neg logit contributions | |
so | -0.121 |
he | -0.120 |
| -0.115 |
very | -0.112 |
ready | -0.111 |
Token | on |
Token ID | 319 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
gy | +0.007 |
ind | +0.007 |
oses | +0.007 |
rap | +0.007 |
ree | +0.007 |
Neg logit contributions | |
| -0.005 |
nam | -0.004 |
Once | -0.004 |
so | -0.004 |
ready | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
so | +0.005 |
ready | +0.004 |
he | +0.004 |
| +0.004 |
nam | +0.004 |
Neg logit contributions | |
gy | -0.016 |
ind | -0.016 |
rap | -0.016 |
ree | -0.015 |
ocol | -0.015 |
Token | beach |
Token ID | 10481 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
| +0.011 |
he | +0.010 |
so | +0.010 |
Once | +0.010 |
nam | +0.010 |
Neg logit contributions | |
ind | -0.020 |
gy | -0.019 |
enery | -0.019 |
ree | -0.018 |
rito | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
gy | +0.014 |
ind | +0.013 |
enery | +0.013 |
ook | +0.012 |
rap | +0.012 |
Neg logit contributions | |
| -0.008 |
Once | -0.008 |
so | -0.008 |
nam | -0.007 |
ready | -0.007 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
so | +0.000 |
| +0.000 |
he | +0.000 |
ready | +0.000 |
nam | +0.000 |
Neg logit contributions | |
gy | -0.000 |
ind | -0.000 |
ree | -0.000 |
enery | -0.000 |
rap | -0.000 |
Token | hungry |
Token ID | 14720 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
gy | +0.044 |
ind | +0.044 |
enery | +0.042 |
ree | +0.042 |
rap | +0.042 |
Neg logit contributions | |
so | -0.018 |
he | -0.017 |
| -0.017 |
ready | -0.015 |
Once | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
en | +0.005 |
gy | +0.005 |
le | +0.005 |
OO | +0.005 |
rito | +0.005 |
Neg logit contributions | |
nam | -0.008 |
| -0.006 |
Once | -0.006 |
refreshed | -0.006 |
Less | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ind | +0.049 |
gy | +0.048 |
rap | +0.048 |
enery | +0.047 |
ocol | +0.047 |
Neg logit contributions | |
so | -0.024 |
| -0.023 |
he | -0.022 |
very | -0.019 |
ready | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
gy | +0.047 |
enery | +0.047 |
ind | +0.047 |
ocol | +0.046 |
rap | +0.046 |
Neg logit contributions | |
| -0.005 |
so | -0.005 |
he | -0.004 |
Once | -0.002 |
very | -0.002 |
Token | G |
Token ID | 38 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
enery | +0.065 |
ocol | +0.065 |
rap | +0.065 |
ues | +0.064 |
gy | +0.064 |
Neg logit contributions | |
so | -0.043 |
| -0.041 |
he | -0.040 |
Once | -0.039 |
very | -0.036 |
Token | igi |
Token ID | 25754 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
gy | +0.074 |
ues | +0.069 |
ree | +0.069 |
ples | +0.069 |
oses | +0.068 |
Neg logit contributions | |
he | -0.118 |
next | -0.117 |
| -0.116 |
so | -0.114 |
she | -0.112 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
gy | +0.044 |
ind | +0.044 |
enery | +0.044 |
rap | +0.044 |
ocol | +0.043 |
Neg logit contributions | |
so | -0.019 |
he | -0.018 |
| -0.018 |
very | -0.016 |
ready | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
gy | +0.016 |
enery | +0.016 |
ind | +0.016 |
rap | +0.016 |
ree | +0.016 |
Neg logit contributions | |
so | -0.005 |
| -0.005 |
nam | -0.005 |
ready | -0.005 |
Once | -0.005 |
Token | fox |
Token ID | 21831 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
nam | +0.003 |
| +0.003 |
Once | +0.003 |
ready | +0.003 |
so | +0.003 |
Neg logit contributions | |
gy | -0.007 |
enery | -0.007 |
eware | -0.007 |
ind | -0.006 |
oc | -0.006 |
Token | es |
Token ID | 274 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
so | +0.009 |
| +0.009 |
he | +0.009 |
ready | +0.008 |
very | +0.008 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.022 |
enery | -0.021 |
rap | -0.021 |
ree | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -6.02e-03 |
Pos logit contributions | |
so | +0.007 |
ready | +0.007 |
refreshed | +0.007 |
nam | +0.007 |
| +0.007 |
Neg logit contributions | |
gy | -0.011 |
eware | -0.011 |
ind | -0.011 |
rito | -0.011 |
ook | -0.011 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
gy | +0.010 |
ind | +0.010 |
enery | +0.009 |
rap | +0.009 |
rito | +0.009 |
Neg logit contributions | |
| -0.010 |
so | -0.010 |
he | -0.010 |
Once | -0.009 |
ready | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
gy | +0.061 |
ind | +0.060 |
rap | +0.059 |
enery | +0.058 |
ocol | +0.057 |
Neg logit contributions | |
so | -0.029 |
| -0.029 |
Once | -0.028 |
he | -0.028 |
ready | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
gy | +0.016 |
ree | +0.015 |
eth | +0.014 |
oses | +0.014 |
uth | +0.014 |
Neg logit contributions | |
ready | -0.008 |
so | -0.008 |
nam | -0.008 |
he | -0.007 |
very | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
gy | +0.004 |
ind | +0.004 |
ree | +0.004 |
rap | +0.004 |
enery | +0.004 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
ready | -0.001 |
very | -0.001 |
Token | T |
Token ID | 51 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
gy | +0.019 |
ind | +0.019 |
enery | +0.019 |
rap | +0.018 |
ree | +0.018 |
Neg logit contributions | |
so | -0.014 |
he | -0.013 |
| -0.013 |
ready | -0.012 |
very | -0.012 |
Token | iny |
Token ID | 3541 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
ocol | +0.069 |
enery | +0.066 |
rito | +0.058 |
gy | +0.057 |
isel | +0.056 |
Neg logit contributions | |
so | -0.096 |
next | -0.094 |
he | -0.091 |
right | -0.088 |
very | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
gy | +0.003 |
ind | +0.003 |
enery | +0.003 |
ree | +0.003 |
rap | +0.003 |
Neg logit contributions | |
so | -0.001 |
he | -0.001 |
| -0.001 |
ready | -0.001 |
very | -0.001 |
Token | Sam |
Token ID | 3409 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
so | +0.007 |
| +0.006 |
ready | +0.006 |
refreshed | +0.006 |
he | +0.005 |
Neg logit contributions | |
gy | -0.017 |
enery | -0.015 |
ree | -0.015 |
ind | -0.015 |
rito | -0.015 |
Token | walked |
Token ID | 6807 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
so | +0.011 |
he | +0.011 |
| +0.010 |
ready | +0.010 |
very | +0.009 |
Neg logit contributions | |
gy | -0.022 |
ind | -0.020 |
enery | -0.020 |
rap | -0.020 |
ree | -0.020 |
Token | home |
Token ID | 1363 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
gy | +0.008 |
ind | +0.008 |
enery | +0.008 |
ree | +0.008 |
rap | +0.008 |
Neg logit contributions | |
so | -0.005 |
he | -0.005 |
| -0.005 |
ready | -0.004 |
very | -0.004 |