Token | had |
Token ID | 550 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
elt | +0.063 |
ring | +0.062 |
cr | +0.061 |
Sur | +0.057 |
OOOO | +0.056 |
Neg logit contributions | |
gly | -0.062 |
irl | -0.062 |
concert | -0.059 |
professor | -0.059 |
tutor | -0.058 |
Token | saved |
Token ID | 7448 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
elt | +0.068 |
ring | +0.064 |
umbs | +0.062 |
OOOO | +0.060 |
cr | +0.060 |
Neg logit contributions | |
gly | -0.059 |
irl | -0.059 |
concert | -0.057 |
professor | -0.055 |
tutor | -0.054 |
Token | him |
Token ID | 683 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
elt | +0.023 |
cr | +0.022 |
ring | +0.022 |
Sur | +0.021 |
OOOO | +0.021 |
Neg logit contributions | |
irl | -0.018 |
gly | -0.017 |
concert | -0.017 |
professor | -0.017 |
therapist | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
professor | +0.004 |
concert | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.008 |
ring | -0.008 |
Sur | -0.008 |
cr | -0.008 |
OOOO | -0.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.023 |
cr | +0.022 |
Sur | +0.021 |
OOOO | +0.021 |
Neg logit contributions | |
gly | -0.019 |
professor | -0.018 |
irl | -0.018 |
therapist | -0.017 |
tutor | -0.017 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
irl | +0.121 |
gly | +0.121 |
concert | +0.120 |
tutor | +0.119 |
professor | +0.118 |
Neg logit contributions | |
elt | -0.098 |
cr | -0.093 |
Sur | -0.089 |
umbs | -0.086 |
OOOO | -0.084 |
Token | otte |
Token ID | 11404 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
professor | +0.157 |
tutor | +0.152 |
irl | +0.149 |
choice | +0.140 |
therapist | +0.133 |
Neg logit contributions | |
elt | -0.356 |
ring | -0.350 |
cr | -0.341 |
Sur | -0.333 |
OOOO | -0.326 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
gly | +0.109 |
irl | +0.109 |
professor | +0.105 |
concert | +0.104 |
tutor | +0.103 |
Neg logit contributions | |
elt | -0.128 |
ring | -0.121 |
cr | -0.119 |
Sur | -0.116 |
OOOO | -0.114 |
Token | her |
Token ID | 607 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.003 |
professor | +0.003 |
concert | +0.003 |
tutor | +0.003 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.005 |
cr | -0.005 |
OOOO | -0.005 |
Sur | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
irl | +0.004 |
gly | +0.004 |
concert | +0.003 |
therapist | +0.003 |
ines | +0.003 |
Neg logit contributions | |
elt | -0.003 |
Sur | -0.003 |
cr | -0.003 |
ring | -0.003 |
OOOO | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
gly | +0.029 |
irl | +0.028 |
concert | +0.028 |
professor | +0.027 |
Hood | +0.027 |
Neg logit contributions | |
elt | -0.041 |
ring | -0.040 |
cr | -0.039 |
Sur | -0.038 |
OOOO | -0.038 |
Token | â |
Token ID | 22940 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
elt | +0.003 |
cr | +0.003 |
ring | +0.003 |
OOOO | +0.003 |
Sur | +0.003 |
Neg logit contributions | |
gly | -0.004 |
professor | -0.004 |
tutor | -0.004 |
therapist | -0.004 |
concert | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
gly | +0.024 |
irl | +0.024 |
professor | +0.024 |
tutor | +0.024 |
therapist | +0.023 |
Neg logit contributions | |
elt | -0.028 |
ring | -0.027 |
cr | -0.026 |
Sur | -0.025 |
OOOO | -0.025 |
Token | |
Token ID | 220 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
gly | +0.044 |
irl | +0.044 |
professor | +0.043 |
concert | +0.042 |
therapist | +0.042 |
Neg logit contributions | |
elt | -0.047 |
ring | -0.044 |
cr | -0.044 |
Sur | -0.043 |
OOOO | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
gly | +0.063 |
irl | +0.062 |
professor | +0.060 |
tutor | +0.059 |
therapist | +0.058 |
Neg logit contributions | |
elt | -0.080 |
ring | -0.078 |
cr | -0.076 |
Sur | -0.072 |
OOOO | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
elt | +0.002 |
cr | +0.002 |
ring | +0.002 |
Sur | +0.002 |
OOOO | +0.002 |
Neg logit contributions | |
gly | -0.002 |
irl | -0.002 |
professor | -0.002 |
concert | -0.002 |
tutor | -0.002 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.004 |
cr | +0.004 |
OOOO | +0.004 |
Sur | +0.004 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
concert | -0.004 |
therapist | -0.004 |
Token | otte |
Token ID | 11404 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
irl | +0.124 |
professor | +0.119 |
tutor | +0.108 |
mask | +0.106 |
gly | +0.106 |
Neg logit contributions | |
elt | -0.383 |
ring | -0.377 |
Sur | -0.351 |
OOOO | -0.351 |
cr | -0.347 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
irl | +0.107 |
gly | +0.107 |
professor | +0.103 |
concert | +0.101 |
tutor | +0.101 |
Neg logit contributions | |
elt | -0.114 |
cr | -0.105 |
ring | -0.105 |
Sur | -0.103 |
OOOO | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
elt | +0.020 |
cr | +0.019 |
ring | +0.019 |
Sur | +0.019 |
OOOO | +0.019 |
Neg logit contributions | |
professor | -0.012 |
irl | -0.012 |
tutor | -0.012 |
gly | -0.012 |
concert | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
elt | +0.015 |
ring | +0.015 |
cr | +0.015 |
OOOO | +0.014 |
umbs | +0.014 |
Neg logit contributions | |
gly | -0.009 |
irl | -0.009 |
therapist | -0.009 |
concert | -0.008 |
professor | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
gly | +0.011 |
irl | +0.011 |
professor | +0.011 |
concert | +0.010 |
therapist | +0.010 |
Neg logit contributions | |
elt | -0.021 |
ring | -0.020 |
cr | -0.020 |
Sur | -0.019 |
OOOO | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
professor | +0.004 |
concert | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.005 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | green |
Token ID | 4077 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
irl | +0.020 |
gly | +0.019 |
concert | +0.019 |
tutor | +0.018 |
therapist | +0.018 |
Neg logit contributions | |
elt | -0.026 |
ring | -0.024 |
cr | -0.024 |
Sur | -0.024 |
OOOO | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
elt | +0.006 |
ring | +0.006 |
cr | +0.006 |
Sur | +0.005 |
OOOO | +0.005 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
concert | -0.004 |
tutor | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
gly | +0.005 |
irl | +0.005 |
professor | +0.005 |
poster | +0.005 |
ela | +0.005 |
Neg logit contributions | |
elt | -0.005 |
Sur | -0.004 |
umbs | -0.004 |
ring | -0.004 |
cr | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
gly | +0.014 |
professor | +0.014 |
poster | +0.014 |
irl | +0.013 |
concert | +0.013 |
Neg logit contributions | |
Sur | -0.007 |
elt | -0.006 |
umbs | -0.006 |
See | -0.005 |
cr | -0.005 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
gly | +0.009 |
professor | +0.009 |
irl | +0.008 |
poster | +0.008 |
Hood | +0.008 |
Neg logit contributions | |
Sur | -0.007 |
elt | -0.007 |
ring | -0.006 |
cr | -0.006 |
umbs | -0.006 |
Token | otte |
Token ID | 11404 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
irl | +0.156 |
choice | +0.147 |
professor | +0.142 |
gly | +0.140 |
competition | +0.135 |
Neg logit contributions | |
elt | -0.332 |
ring | -0.324 |
Sur | -0.303 |
OOOO | -0.293 |
lette | -0.288 |
Token | 's |
Token ID | 338 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
gly | +0.099 |
irl | +0.097 |
professor | +0.094 |
concert | +0.094 |
tutor | +0.092 |
Neg logit contributions | |
elt | -0.113 |
ring | -0.107 |
cr | -0.105 |
Sur | -0.102 |
OOOO | -0.100 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
elt | +0.040 |
ring | +0.036 |
Sur | +0.035 |
cr | +0.034 |
lette | +0.034 |
Neg logit contributions | |
gly | -0.040 |
irl | -0.039 |
rob | -0.038 |
acio | -0.038 |
therapist | -0.037 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
gly | +0.022 |
irl | +0.022 |
professor | +0.021 |
concert | +0.021 |
tutor | +0.020 |
Neg logit contributions | |
elt | -0.027 |
ring | -0.025 |
cr | -0.025 |
Sur | -0.024 |
OOOO | -0.023 |
Token | at |
Token ID | 379 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
elt | +0.024 |
cr | +0.024 |
OOOO | +0.024 |
ring | +0.023 |
Sur | +0.023 |
Neg logit contributions | |
tutor | -0.014 |
professor | -0.013 |
concert | -0.013 |
therapist | -0.013 |
irl | -0.013 |
Token | do |
Token ID | 466 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
elt | +0.069 |
cr | +0.064 |
ring | +0.064 |
Sur | +0.063 |
OOOO | +0.062 |
Neg logit contributions | |
irl | -0.044 |
gly | -0.043 |
concert | -0.042 |
professor | -0.042 |
tutor | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
gly | +0.028 |
irl | +0.027 |
concert | +0.026 |
professor | +0.026 |
tutor | +0.025 |
Neg logit contributions | |
elt | -0.051 |
ring | -0.048 |
cr | -0.048 |
Sur | -0.046 |
OOOO | -0.046 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
elt | +0.003 |
Sur | +0.002 |
ring | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
Neg logit contributions | |
irl | -0.002 |
gly | -0.002 |
Hood | -0.002 |
concert | -0.002 |
professor | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
elt | +0.068 |
ring | +0.063 |
cr | +0.063 |
Sur | +0.062 |
OOOO | +0.060 |
Neg logit contributions | |
gly | -0.051 |
irl | -0.051 |
professor | -0.049 |
concert | -0.048 |
tutor | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Sur | +0.013 |
elt | +0.013 |
umbs | +0.011 |
cr | +0.011 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
professor | -0.020 |
concert | -0.020 |
Hood | -0.020 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
elt | +0.016 |
Sur | +0.015 |
ring | +0.015 |
cr | +0.015 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
professor | -0.019 |
concert | -0.019 |
Hood | -0.019 |
Token | otte |
Token ID | 11404 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
irl | +0.150 |
professor | +0.143 |
theater | +0.137 |
stage | +0.134 |
concert | +0.130 |
Neg logit contributions | |
elt | -0.345 |
ring | -0.339 |
Sur | -0.318 |
OOOO | -0.309 |
cr | -0.304 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
gly | +0.085 |
irl | +0.083 |
professor | +0.081 |
concert | +0.080 |
tutor | +0.079 |
Neg logit contributions | |
elt | -0.109 |
ring | -0.104 |
cr | -0.103 |
Sur | -0.099 |
OOOO | -0.098 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
elt | +0.021 |
ring | +0.019 |
Sur | +0.019 |
cr | +0.018 |
OOOO | +0.017 |
Neg logit contributions | |
irl | -0.020 |
ines | -0.019 |
gly | -0.019 |
professor | -0.018 |
ls | -0.018 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
gly | +0.009 |
irl | +0.009 |
concert | +0.009 |
Hood | +0.009 |
professor | +0.009 |
Neg logit contributions | |
elt | -0.012 |
OOOO | -0.011 |
cr | -0.011 |
ring | -0.011 |
Sur | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
cr | +0.022 |
OOOO | +0.021 |
Sur | +0.021 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.019 |
professor | -0.019 |
tutor | -0.019 |
concert | -0.019 |
Token | found |
Token ID | 1043 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
gly | +0.015 |
professor | +0.015 |
irl | +0.015 |
concert | +0.014 |
tutor | +0.014 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
Sur | -0.012 |
OOOO | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -9.59e-04 |
Pos logit contributions | |
elt | +0.090 |
ring | +0.086 |
cr | +0.084 |
OOOO | +0.082 |
Sur | +0.082 |
Neg logit contributions | |
gly | -0.056 |
irl | -0.053 |
professor | -0.051 |
concert | -0.051 |
therapist | -0.051 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
elt | +0.002 |
ring | +0.002 |
Sur | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
Neg logit contributions | |
irl | -0.001 |
gly | -0.001 |
tutor | -0.001 |
professor | -0.001 |
concert | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
elt | +0.057 |
ring | +0.053 |
cr | +0.051 |
Sur | +0.051 |
OOOO | +0.049 |
Neg logit contributions | |
gly | -0.058 |
irl | -0.056 |
professor | -0.054 |
concert | -0.054 |
Hood | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
Sur | +0.007 |
elt | +0.007 |
ring | +0.006 |
cr | +0.006 |
umbs | +0.005 |
Neg logit contributions | |
gly | -0.011 |
irl | -0.010 |
Hood | -0.010 |
concert | -0.010 |
professor | -0.010 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Sur | +0.009 |
elt | +0.009 |
ring | +0.008 |
cr | +0.008 |
lette | +0.008 |
Neg logit contributions | |
gly | -0.011 |
irl | -0.011 |
Hood | -0.011 |
professor | -0.011 |
ines | -0.011 |
Token | otte |
Token ID | 11404 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
irl | +0.164 |
choice | +0.159 |
mask | +0.149 |
competition | +0.149 |
professor | +0.148 |
Neg logit contributions | |
ring | -0.312 |
elt | -0.312 |
Sur | -0.283 |
OOOO | -0.272 |
lette | -0.269 |
Token | and |
Token ID | 290 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
gly | +0.089 |
irl | +0.087 |
professor | +0.084 |
concert | +0.084 |
therapist | +0.083 |
Neg logit contributions | |
elt | -0.112 |
ring | -0.107 |
cr | -0.105 |
Sur | -0.101 |
OOOO | -0.101 |
Token | her |
Token ID | 607 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.013 |
Sur | +0.013 |
See | +0.011 |
cr | +0.011 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.017 |
ines | -0.017 |
rob | -0.016 |
ls | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
elt | +0.010 |
Sur | +0.009 |
ring | +0.008 |
cr | +0.008 |
lette | +0.008 |
Neg logit contributions | |
irl | -0.014 |
gly | -0.014 |
acio | -0.014 |
concert | -0.013 |
rob | -0.013 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
gly | +0.018 |
irl | +0.018 |
concert | +0.018 |
professor | +0.017 |
therapist | +0.017 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.019 |
cr | -0.019 |
OOOO | -0.018 |
Sur | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
ring | +0.012 |
elt | +0.011 |
itself | +0.011 |
OOOO | +0.010 |
cr | +0.010 |
Neg logit contributions | |
gly | -0.020 |
mun | -0.020 |
ls | -0.019 |
irl | -0.019 |
therapist | -0.019 |
Token | shed |
Token ID | 14999 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
irl | +0.005 |
gly | +0.005 |
concert | +0.004 |
professor | +0.004 |
Hood | +0.004 |
Neg logit contributions | |
elt | -0.007 |
cr | -0.006 |
ring | -0.006 |
Sur | -0.006 |
lette | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
gly | +0.002 |
irl | +0.002 |
professor | +0.002 |
concert | +0.002 |
tutor | +0.002 |
Neg logit contributions | |
elt | -0.003 |
ring | -0.003 |
cr | -0.003 |
Sur | -0.003 |
OOOO | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
ines | +0.004 |
Hood | +0.004 |
concert | +0.004 |
Neg logit contributions | |
elt | -0.005 |
Sur | -0.004 |
ring | -0.004 |
cr | -0.004 |
umbs | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
poster | +0.007 |
professor | +0.007 |
Hood | +0.007 |
Neg logit contributions | |
Sur | -0.004 |
elt | -0.003 |
See | -0.003 |
umbs | -0.003 |
ring | -0.003 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
Hood | +0.004 |
professor | +0.004 |
ines | +0.004 |
Neg logit contributions | |
Sur | -0.003 |
elt | -0.003 |
ring | -0.003 |
lette | -0.002 |
cr | -0.002 |
Token | otte |
Token ID | 11404 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
choice | +0.177 |
irl | +0.174 |
competition | +0.163 |
mask | +0.162 |
show | +0.160 |
Neg logit contributions | |
elt | -0.300 |
ring | -0.294 |
Sur | -0.270 |
OOOO | -0.256 |
lette | -0.251 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
gly | +0.100 |
irl | +0.100 |
professor | +0.097 |
concert | +0.096 |
Hood | +0.094 |
Neg logit contributions | |
elt | -0.102 |
ring | -0.095 |
cr | -0.095 |
Sur | -0.093 |
OOOO | -0.088 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.024 |
cr | +0.023 |
Sur | +0.021 |
OOOO | +0.019 |
Neg logit contributions | |
gly | -0.044 |
irl | -0.044 |
mun | -0.041 |
concert | -0.041 |
inkle | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
Jen | +0.013 |
cr | +0.012 |
ring | +0.012 |
Sur | +0.012 |
See | +0.012 |
Neg logit contributions | |
gly | -0.037 |
ls | -0.037 |
rob | -0.037 |
ines | -0.036 |
irl | -0.034 |
Token | shed |
Token ID | 14999 |
Feature activation | +9.09e-04 |
Pos logit contributions | |
gly | +0.003 |
irl | +0.003 |
concert | +0.003 |
professor | +0.003 |
therapist | +0.003 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.004 |
cr | -0.004 |
Sur | -0.004 |
OOOO | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
elt | +0.061 |
ring | +0.059 |
OOOO | +0.058 |
cr | +0.058 |
Sur | +0.057 |
Neg logit contributions | |
irl | -0.037 |
gly | -0.036 |
closely | -0.033 |
professor | -0.033 |
ls | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
elt | +0.131 |
ring | +0.126 |
cr | +0.124 |
Sur | +0.121 |
OOOO | +0.120 |
Neg logit contributions | |
gly | -0.084 |
irl | -0.081 |
professor | -0.079 |
concert | -0.079 |
tutor | -0.078 |
Token | strong |
Token ID | 1913 |
Feature activation | +4.59e-04 |
Pos logit contributions | |
elt | +0.022 |
ring | +0.021 |
OOOO | +0.021 |
umbs | +0.021 |
cr | +0.020 |
Neg logit contributions | |
irl | -0.015 |
gly | -0.015 |
therapist | -0.015 |
professor | -0.014 |
Sparkle | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gly | +0.001 |
irl | +0.001 |
professor | +0.001 |
concert | +0.001 |
tutor | +0.001 |
Neg logit contributions | |
elt | -0.001 |
ring | -0.001 |
cr | -0.001 |
Sur | -0.001 |
OOOO | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
elt | +0.024 |
ring | +0.023 |
cr | +0.022 |
OOOO | +0.021 |
Sur | +0.021 |
Neg logit contributions | |
gly | -0.024 |
irl | -0.023 |
professor | -0.022 |
tutor | -0.022 |
therapist | -0.022 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
concert | +0.120 |
irl | +0.118 |
gly | +0.118 |
tutor | +0.118 |
professor | +0.117 |
Neg logit contributions | |
elt | -0.085 |
cr | -0.081 |
Sur | -0.077 |
umbs | -0.074 |
OOOO | -0.073 |
Token | ix |
Token ID | 844 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
therapist | +0.211 |
professor | +0.196 |
mun | +0.195 |
tutor | +0.192 |
avail | +0.180 |
Neg logit contributions | |
OOOO | -0.260 |
cr | -0.253 |
ring | -0.252 |
Sur | -0.241 |
OP | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
gly | +0.073 |
irl | +0.072 |
professor | +0.071 |
concert | +0.071 |
tutor | +0.070 |
Neg logit contributions | |
elt | -0.082 |
ring | -0.079 |
cr | -0.077 |
OOOO | -0.074 |
Sur | -0.073 |
Token | Pac |
Token ID | 6319 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
elt | +0.002 |
ring | +0.002 |
umbs | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
Neg logit contributions | |
gly | -0.001 |
professor | -0.001 |
tutor | -0.001 |
concert | -0.001 |
Hood | -0.001 |
Token | o |
Token ID | 78 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
gly | +0.045 |
professor | +0.042 |
Hood | +0.042 |
irl | +0.042 |
ines | +0.041 |
Neg logit contributions | |
elt | -0.041 |
Sur | -0.039 |
ring | -0.038 |
cr | -0.037 |
eighteen | -0.037 |
Token | were |
Token ID | 547 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
gly | +0.063 |
irl | +0.062 |
concert | +0.060 |
professor | +0.060 |
tutor | +0.059 |
Neg logit contributions | |
elt | -0.056 |
ring | -0.052 |
cr | -0.051 |
Sur | -0.050 |
OOOO | -0.049 |
Token | that |
Token ID | 326 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
elt | +0.025 |
cr | +0.024 |
ring | +0.024 |
Sur | +0.023 |
OOOO | +0.023 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.022 |
professor | -0.022 |
concert | -0.022 |
therapist | -0.022 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
gly | +0.031 |
irl | +0.031 |
concert | +0.029 |
therapist | +0.029 |
tutor | +0.029 |
Neg logit contributions | |
elt | -0.053 |
ring | -0.049 |
Sur | -0.048 |
cr | -0.047 |
OOOO | -0.047 |
Token | |
Token ID | 220 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
elt | +0.062 |
Sur | +0.058 |
ring | +0.052 |
cr | +0.052 |
umbs | +0.050 |
Neg logit contributions | |
gly | -0.079 |
irl | -0.079 |
professor | -0.076 |
Hood | -0.075 |
ines | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
gly | +0.052 |
irl | +0.051 |
concert | +0.050 |
professor | +0.050 |
tutor | +0.049 |
Neg logit contributions | |
elt | -0.054 |
ring | -0.050 |
cr | -0.050 |
Sur | -0.048 |
OOOO | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
Sur | +0.021 |
elt | +0.018 |
umbs | +0.016 |
cr | +0.015 |
See | +0.015 |
Neg logit contributions | |
gly | -0.037 |
irl | -0.037 |
professor | -0.036 |
poster | -0.036 |
Hood | -0.036 |
Token | Charl |
Token ID | 24453 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Sur | +0.044 |
elt | +0.039 |
ring | +0.037 |
lette | +0.036 |
cr | +0.036 |
Neg logit contributions | |
gly | -0.019 |
irl | -0.018 |
ines | -0.018 |
Hood | -0.018 |
professor | -0.017 |
Token | otte |
Token ID | 11404 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
irl | +0.159 |
theater | +0.149 |
professor | +0.144 |
choice | +0.141 |
research | +0.141 |
Neg logit contributions | |
ring | -0.312 |
elt | -0.311 |
Sur | -0.301 |
OOOO | -0.280 |
lette | -0.275 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
gly | +0.076 |
irl | +0.074 |
professor | +0.071 |
concert | +0.071 |
therapist | +0.070 |
Neg logit contributions | |
elt | -0.106 |
ring | -0.101 |
cr | -0.100 |
Sur | -0.097 |
OOOO | -0.096 |
Token | her |
Token ID | 607 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ring | +0.039 |
elt | +0.036 |
itself | +0.036 |
cr | +0.035 |
Sur | +0.034 |
Neg logit contributions | |
ines | -0.070 |
ls | -0.070 |
gly | -0.067 |
rob | -0.067 |
mun | -0.067 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
elt | +0.016 |
cr | +0.015 |
ring | +0.015 |
Sur | +0.014 |
lette | +0.014 |
Neg logit contributions | |
rob | -0.025 |
irl | -0.024 |
gly | -0.024 |
mun | -0.023 |
roads | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
ring | +0.022 |
elt | +0.021 |
cr | +0.020 |
lette | +0.019 |
Sur | +0.018 |
Neg logit contributions | |
irl | -0.025 |
gly | -0.025 |
concert | -0.023 |
professor | -0.023 |
therapist | -0.022 |
Token | were |
Token ID | 547 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
gly | +0.021 |
therapist | +0.020 |
irl | +0.019 |
professor | +0.019 |
concert | +0.019 |
Neg logit contributions | |
elt | -0.030 |
Sur | -0.028 |
cr | -0.028 |
ring | -0.028 |
OOOO | -0.027 |
Token | healed |
Token ID | 28557 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
elt | +0.077 |
Sur | +0.071 |
OOOO | +0.071 |
ring | +0.069 |
cr | +0.069 |
Neg logit contributions | |
irl | -0.054 |
gly | -0.051 |
tutor | -0.049 |
concert | -0.049 |
Sparkle | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
elt | +0.078 |
ring | +0.073 |
cr | +0.072 |
Sur | +0.072 |
OOOO | +0.071 |
Neg logit contributions | |
gly | -0.033 |
irl | -0.032 |
professor | -0.031 |
concert | -0.030 |
therapist | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.026 |
cr | +0.025 |
lette | +0.024 |
OOOO | +0.023 |
Neg logit contributions | |
gly | -0.023 |
professor | -0.022 |
Holly | -0.022 |
tutor | -0.022 |
Sparkle | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
elt | +0.015 |
Sur | +0.014 |
cr | +0.014 |
OOOO | +0.013 |
ring | +0.013 |
Neg logit contributions | |
gly | -0.017 |
concert | -0.017 |
irl | -0.016 |
professor | -0.016 |
therapist | -0.016 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
elt | +0.014 |
ring | +0.013 |
cr | +0.013 |
OOOO | +0.012 |
Sur | +0.012 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.017 |
professor | -0.017 |
concert | -0.017 |
therapist | -0.016 |
Token | icity |
Token ID | 8467 |
Feature activation | +8.10e-03 |
Pos logit contributions | |
therapist | +0.174 |
irl | +0.172 |
tutor | +0.171 |
concert | +0.167 |
professor | +0.167 |
Neg logit contributions | |
OOOO | -0.283 |
ring | -0.279 |
elt | -0.278 |
cr | -0.266 |
Sur | -0.266 |
Token | was |
Token ID | 373 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
gly | +0.012 |
irl | +0.012 |
professor | +0.011 |
concert | +0.011 |
therapist | +0.011 |
Neg logit contributions | |
elt | -0.015 |
ring | -0.014 |
cr | -0.014 |
Sur | -0.013 |
OOOO | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
elt | +0.004 |
cr | +0.003 |
ring | +0.003 |
OOOO | +0.003 |
Sur | +0.003 |
Neg logit contributions | |
irl | -0.003 |
gly | -0.003 |
concert | -0.003 |
professor | -0.002 |
tutor | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
elt | +0.064 |
cr | +0.062 |
ring | +0.062 |
OOOO | +0.061 |
Sur | +0.059 |
Neg logit contributions | |
irl | -0.039 |
gly | -0.037 |
professor | -0.036 |
therapist | -0.035 |
tutor | -0.035 |
Token | that |
Token ID | 326 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
elt | +0.122 |
ring | +0.115 |
cr | +0.114 |
Sur | +0.111 |
OOOO | +0.109 |
Neg logit contributions | |
gly | -0.090 |
irl | -0.089 |
professor | -0.085 |
concert | -0.084 |
therapist | -0.083 |
Token | it |
Token ID | 340 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
elt | +0.039 |
ring | +0.038 |
cr | +0.037 |
OOOO | +0.035 |
Sur | +0.035 |
Neg logit contributions | |
gly | -0.042 |
professor | -0.042 |
mun | -0.042 |
irl | -0.041 |
therapist | -0.041 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
professor | +0.004 |
concert | +0.004 |
therapist | +0.004 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.005 |
cr | -0.005 |
Sur | -0.004 |
OOOO | -0.004 |
Token | |
Token ID | 220 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
elt | +0.046 |
Sur | +0.041 |
cr | +0.040 |
ring | +0.040 |
OOOO | +0.039 |
Neg logit contributions | |
irl | -0.037 |
gly | -0.035 |
professor | -0.035 |
Hood | -0.035 |
concert | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -7.01e-06 |
Pos logit contributions | |
gly | +0.076 |
concert | +0.074 |
irl | +0.074 |
professor | +0.073 |
tutor | +0.071 |
Neg logit contributions | |
elt | -0.072 |
cr | -0.067 |
ring | -0.066 |
Sur | -0.065 |
OOOO | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-03 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Sur | +0.002 |
elt | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
ring | +0.002 |
Neg logit contributions | |
Hood | -0.002 |
irl | -0.002 |
gly | -0.002 |
professor | -0.002 |
tutor | -0.002 |
Token | ix |
Token ID | 844 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Hood | +0.200 |
Sparkle | +0.198 |
therapist | +0.195 |
aisle | +0.195 |
professor | +0.189 |
Neg logit contributions | |
OOOO | -0.242 |
Sur | -0.220 |
elt | -0.219 |
OO | -0.217 |
ring | -0.216 |
Token | was |
Token ID | 373 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
irl | +0.066 |
gly | +0.065 |
concert | +0.065 |
professor | +0.065 |
tutor | +0.063 |
Neg logit contributions | |
elt | -0.075 |
ring | -0.072 |
cr | -0.071 |
Sur | -0.066 |
OOOO | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
gly | +0.015 |
irl | +0.014 |
professor | +0.014 |
concert | +0.014 |
tutor | +0.014 |
Neg logit contributions | |
elt | -0.016 |
ring | -0.016 |
cr | -0.015 |
Sur | -0.015 |
OOOO | -0.015 |
Token | bit |
Token ID | 1643 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
gly | +0.019 |
irl | +0.019 |
Hood | +0.017 |
ines | +0.017 |
therapist | +0.017 |
Neg logit contributions | |
elt | -0.013 |
Sur | -0.012 |
cr | -0.012 |
ring | -0.012 |
OOOO | -0.011 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
elt | +0.032 |
ring | +0.028 |
Sur | +0.027 |
cr | +0.027 |
eared | +0.024 |
Neg logit contributions | |
gly | -0.037 |
irl | -0.036 |
concert | -0.036 |
therapist | -0.035 |
rob | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ring | +0.025 |
elt | +0.025 |
cr | +0.025 |
Sur | +0.024 |
OOOO | +0.023 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.022 |
therapist | -0.022 |
ls | -0.022 |
professor | -0.022 |
Token | friends |
Token ID | 2460 |
Feature activation | -9.37e-04 |
Pos logit contributions | |
elt | +0.041 |
Sur | +0.039 |
ring | +0.038 |
cr | +0.038 |
lette | +0.037 |
Neg logit contributions | |
irl | -0.040 |
gly | -0.038 |
ches | -0.038 |
acio | -0.037 |
rob | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
elt | +0.002 |
ring | +0.002 |
cr | +0.002 |
Sur | +0.002 |
lette | +0.002 |
Neg logit contributions | |
gly | -0.001 |
irl | -0.001 |
professor | -0.001 |
concert | -0.001 |
therapist | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
elt | +0.016 |
Sur | +0.014 |
ring | +0.014 |
cr | +0.014 |
OOOO | +0.013 |
Neg logit contributions | |
irl | -0.025 |
gly | -0.025 |
concert | -0.025 |
tutor | -0.024 |
professor | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
Sur | +0.012 |
cr | +0.011 |
OOOO | +0.011 |
elt | +0.011 |
umbs | +0.010 |
Neg logit contributions | |
tutor | -0.027 |
concert | -0.026 |
professor | -0.026 |
therapist | -0.025 |
gly | -0.025 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Sur | +0.017 |
cr | +0.016 |
elt | +0.015 |
ring | +0.015 |
OOOO | +0.014 |
Neg logit contributions | |
tutor | -0.024 |
gly | -0.023 |
professor | -0.023 |
Hood | -0.022 |
concert | -0.022 |
Token | icity |
Token ID | 8467 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
irl | +0.166 |
mun | +0.161 |
glers | +0.157 |
therapist | +0.157 |
tutor | +0.156 |
Neg logit contributions | |
ring | -0.264 |
OOOO | -0.261 |
Sur | -0.251 |
elt | -0.248 |
OO | -0.238 |
Token | decided |
Token ID | 3066 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
gly | +0.018 |
irl | +0.017 |
concert | +0.017 |
professor | +0.017 |
tutor | +0.016 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.019 |
cr | -0.018 |
Sur | -0.018 |
OOOO | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
elt | +0.081 |
ring | +0.075 |
cr | +0.074 |
Sur | +0.072 |
OOOO | +0.069 |
Neg logit contributions | |
gly | -0.101 |
irl | -0.100 |
professor | -0.096 |
concert | -0.096 |
therapist | -0.094 |
Token | keep |
Token ID | 1394 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.025 |
cr | +0.025 |
Sur | +0.024 |
lette | +0.023 |
Neg logit contributions | |
gly | -0.025 |
professor | -0.024 |
irl | -0.023 |
therapist | -0.023 |
concert | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
therapist | +0.093 |
professor | +0.091 |
gly | +0.090 |
mun | +0.088 |
ines | +0.088 |
Neg logit contributions | |
elt | -0.064 |
lette | -0.057 |
ring | -0.057 |
cr | -0.057 |
Jen | -0.051 |
Token | so |
Token ID | 523 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
irl | +0.011 |
professor | +0.011 |
gly | +0.011 |
tutor | +0.011 |
concert | +0.011 |
Neg logit contributions | |
elt | -0.012 |
cr | -0.011 |
OOOO | -0.011 |
ring | -0.011 |
Sur | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
elt | +0.058 |
ring | +0.057 |
cr | +0.056 |
OOOO | +0.056 |
umbs | +0.055 |
Neg logit contributions | |
irl | -0.030 |
gly | -0.029 |
professor | -0.028 |
tutor | -0.027 |
therapist | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
elt | +0.038 |
ring | +0.036 |
cr | +0.035 |
Sur | +0.034 |
OOOO | +0.034 |
Neg logit contributions | |
gly | -0.030 |
irl | -0.030 |
professor | -0.029 |
concert | -0.029 |
therapist | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
elt | +0.049 |
ring | +0.043 |
cr | +0.042 |
Sur | +0.042 |
OOOO | +0.040 |
Neg logit contributions | |
irl | -0.060 |
gly | -0.060 |
concert | -0.058 |
professor | -0.056 |
tutor | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Sur | +0.010 |
elt | +0.009 |
cr | +0.009 |
OOOO | +0.008 |
umbs | +0.008 |
Neg logit contributions | |
concert | -0.023 |
tutor | -0.023 |
gly | -0.023 |
therapist | -0.023 |
professor | -0.022 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Sur | +0.016 |
elt | +0.016 |
ring | +0.015 |
cr | +0.015 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.019 |
tutor | -0.019 |
irl | -0.019 |
concert | -0.018 |
professor | -0.018 |
Token | icity |
Token ID | 8467 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
mun | +0.162 |
irl | +0.159 |
therapist | +0.156 |
glers | +0.154 |
tutor | +0.151 |
Neg logit contributions | |
ring | -0.261 |
OOOO | -0.257 |
elt | -0.249 |
Sur | -0.248 |
OO | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
gly | +0.016 |
irl | +0.015 |
professor | +0.015 |
concert | +0.015 |
therapist | +0.015 |
Neg logit contributions | |
elt | -0.018 |
ring | -0.017 |
cr | -0.016 |
Sur | -0.016 |
OOOO | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.015 |
Sur | +0.014 |
cr | +0.014 |
OOOO | +0.013 |
Neg logit contributions | |
irl | -0.016 |
gly | -0.016 |
ls | -0.015 |
concert | -0.014 |
therapist | -0.014 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
elt | +0.010 |
ring | +0.009 |
cr | +0.009 |
Sur | +0.008 |
Birthday | +0.008 |
Neg logit contributions | |
irl | -0.017 |
roads | -0.017 |
acio | -0.017 |
gly | -0.017 |
ches | -0.016 |
Token | inspected |
Token ID | 34295 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
gly | +0.002 |
irl | +0.002 |
concert | +0.002 |
professor | +0.002 |
tutor | +0.002 |
Neg logit contributions | |
elt | -0.003 |
cr | -0.002 |
ring | -0.002 |
OOOO | -0.002 |
Sur | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
gly | +0.029 |
irl | +0.028 |
therapist | +0.028 |
concert | +0.027 |
professor | +0.027 |
Neg logit contributions | |
elt | -0.029 |
Sur | -0.026 |
cr | -0.026 |
ring | -0.026 |
OOOO | -0.026 |
Token | healed |
Token ID | 28557 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
elt | +0.081 |
OOOO | +0.075 |
Sur | +0.075 |
ring | +0.073 |
cr | +0.073 |
Neg logit contributions | |
irl | -0.057 |
gly | -0.053 |
concert | -0.051 |
tutor | -0.051 |
ches | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
elt | +0.064 |
ring | +0.061 |
cr | +0.061 |
Sur | +0.059 |
OOOO | +0.059 |
Neg logit contributions | |
gly | -0.035 |
irl | -0.034 |
professor | -0.033 |
concert | -0.032 |
tutor | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
elt | +0.035 |
Sur | +0.032 |
ring | +0.031 |
cr | +0.031 |
OOOO | +0.030 |
Neg logit contributions | |
irl | -0.039 |
concert | -0.038 |
gly | -0.037 |
tutor | -0.036 |
professor | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Sur | +0.022 |
elt | +0.021 |
cr | +0.021 |
OOOO | +0.019 |
ring | +0.018 |
Neg logit contributions | |
concert | -0.040 |
tutor | -0.040 |
professor | -0.039 |
therapist | -0.039 |
gly | -0.038 |
Token | Fel |
Token ID | 42493 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Sur | +0.034 |
elt | +0.033 |
cr | +0.032 |
ring | +0.032 |
OOOO | +0.030 |
Neg logit contributions | |
gly | -0.029 |
tutor | -0.029 |
concert | -0.028 |
professor | -0.028 |
irl | -0.028 |
Token | icity |
Token ID | 8467 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
irl | +0.164 |
mun | +0.148 |
tutor | +0.148 |
gly | +0.146 |
concert | +0.143 |
Neg logit contributions | |
ring | -0.271 |
OOOO | -0.269 |
Sur | -0.261 |
elt | -0.253 |
lette | -0.240 |
Token | was |
Token ID | 373 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
gly | +0.011 |
irl | +0.010 |
professor | +0.010 |
concert | +0.010 |
tutor | +0.010 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
Sur | -0.012 |
OOOO | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
elt | +0.006 |
OOOO | +0.006 |
cr | +0.005 |
ring | +0.005 |
Sur | +0.005 |
Neg logit contributions | |
irl | -0.004 |
concert | -0.004 |
tutor | -0.003 |
professor | -0.003 |
gly | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
elt | +0.073 |
OOOO | +0.072 |
ring | +0.070 |
cr | +0.070 |
umbs | +0.067 |
Neg logit contributions | |
irl | -0.040 |
professor | -0.036 |
gly | -0.036 |
tutor | -0.036 |
therapist | -0.035 |
Token | that |
Token ID | 326 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
elt | +0.116 |
ring | +0.108 |
cr | +0.108 |
Sur | +0.104 |
OOOO | +0.102 |
Neg logit contributions | |
gly | -0.091 |
irl | -0.090 |
professor | -0.085 |
concert | -0.085 |
therapist | -0.083 |
Token | there |
Token ID | 612 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
elt | +0.061 |
ring | +0.058 |
cr | +0.058 |
Sur | +0.056 |
OOOO | +0.055 |
Neg logit contributions | |
gly | -0.030 |
irl | -0.029 |
professor | -0.028 |
concert | -0.028 |
tutor | -0.027 |
Token | were |
Token ID | 547 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
professor | +0.020 |
concert | +0.020 |
tutor | +0.020 |
irl | +0.019 |
gly | +0.019 |
Neg logit contributions | |
elt | -0.026 |
cr | -0.024 |
ring | -0.024 |
Sur | -0.023 |
OOOO | -0.023 |
Token | two |
Token ID | 734 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ring | +0.034 |
elt | +0.031 |
OOOO | +0.030 |
seventeen | +0.030 |
cr | +0.030 |
Neg logit contributions | |
Hood | -0.020 |
irl | -0.020 |
Holly | -0.020 |
gly | -0.019 |
concert | -0.019 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
elt | +0.060 |
cr | +0.056 |
ring | +0.056 |
Sur | +0.055 |
OOOO | +0.054 |
Neg logit contributions | |
gly | -0.046 |
irl | -0.045 |
therapist | -0.044 |
professor | -0.044 |
concert | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
irl | +0.018 |
gly | +0.018 |
therapist | +0.017 |
professor | +0.017 |
concert | +0.017 |
Neg logit contributions | |
elt | -0.022 |
ring | -0.021 |
cr | -0.021 |
OOOO | -0.019 |
Sur | -0.019 |
Token | Bruno |
Token ID | 31045 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
gly | +0.042 |
tutor | +0.040 |
professor | +0.040 |
irl | +0.040 |
concert | +0.040 |
Neg logit contributions | |
elt | -0.040 |
ring | -0.039 |
cr | -0.036 |
OOOO | -0.036 |
Sur | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
irl | +0.229 |
gly | +0.223 |
concert | +0.216 |
professor | +0.212 |
tutor | +0.205 |
Neg logit contributions | |
elt | -0.233 |
ring | -0.220 |
cr | -0.216 |
Sur | -0.207 |
OOOO | -0.204 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
gly | +0.005 |
irl | +0.005 |
professor | +0.004 |
concert | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.005 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
gly | +0.030 |
irl | +0.030 |
professor | +0.028 |
concert | +0.028 |
therapist | +0.027 |
Neg logit contributions | |
elt | -0.053 |
ring | -0.050 |
cr | -0.050 |
Sur | -0.048 |
OOOO | -0.048 |
Token | They |
Token ID | 1119 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
irl | +0.021 |
gly | +0.021 |
professor | +0.020 |
concert | +0.020 |
therapist | +0.020 |
Neg logit contributions | |
elt | -0.007 |
cr | -0.005 |
Sur | -0.005 |
umbs | -0.005 |
ring | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
gly | +0.030 |
irl | +0.029 |
professor | +0.029 |
concert | +0.029 |
therapist | +0.029 |
Neg logit contributions | |
elt | -0.028 |
ring | -0.026 |
cr | -0.026 |
Sur | -0.025 |
OOOO | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.004 |
cr | +0.004 |
Sur | +0.004 |
OOOO | +0.004 |
Neg logit contributions | |
gly | -0.003 |
irl | -0.003 |
professor | -0.003 |
concert | -0.003 |
therapist | -0.003 |
Token | digs |
Token ID | 46561 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
tutor | +0.026 |
gly | +0.026 |
concert | +0.026 |
professor | +0.025 |
therapist | +0.025 |
Neg logit contributions | |
cr | -0.025 |
elt | -0.023 |
ring | -0.022 |
eighteen | -0.022 |
OOOO | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
gly | +0.004 |
concert | +0.004 |
irl | +0.004 |
professor | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.004 |
cr | -0.004 |
ring | -0.004 |
Sur | -0.004 |
OOOO | -0.004 |
Token | bones |
Token ID | 11945 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
gly | +0.052 |
irl | +0.052 |
concert | +0.049 |
professor | +0.049 |
stage | +0.049 |
Neg logit contributions | |
elt | -0.066 |
ring | -0.064 |
cr | -0.060 |
lette | -0.058 |
OOOO | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
gly | +0.042 |
irl | +0.041 |
professor | +0.039 |
concert | +0.039 |
tutor | +0.038 |
Neg logit contributions | |
elt | -0.077 |
ring | -0.074 |
cr | -0.073 |
Sur | -0.071 |
OOOO | -0.071 |
Token | Bones |
Token ID | 31823 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ring | +0.007 |
lette | +0.007 |
elt | +0.006 |
cr | +0.006 |
Sur | +0.006 |
Neg logit contributions | |
gly | -0.005 |
irl | -0.005 |
professor | -0.005 |
aisle | -0.005 |
Holly | -0.004 |
Token | are |
Token ID | 389 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
gly | +0.194 |
concert | +0.194 |
tutor | +0.194 |
therapist | +0.194 |
professor | +0.192 |
Neg logit contributions | |
cr | -0.243 |
elt | -0.243 |
ring | -0.233 |
OOOO | -0.227 |
Sur | -0.223 |
Token | his |
Token ID | 465 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
elt | +0.014 |
ring | +0.013 |
Sur | +0.013 |
cr | +0.013 |
OOOO | +0.012 |
Neg logit contributions | |
irl | -0.007 |
gly | -0.007 |
professor | -0.007 |
tutor | -0.006 |
Hood | -0.006 |
Token | favorite |
Token ID | 4004 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.007 |
professor | +0.007 |
concert | +0.007 |
tutor | +0.007 |
Neg logit contributions | |
elt | -0.012 |
ring | -0.011 |
cr | -0.011 |
Sur | -0.011 |
OOOO | -0.011 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
gly | +0.080 |
irl | +0.078 |
professor | +0.076 |
concert | +0.076 |
therapist | +0.074 |
Neg logit contributions | |
elt | -0.091 |
cr | -0.088 |
ring | -0.087 |
Sur | -0.083 |
OOOO | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
gly | +0.036 |
irl | +0.036 |
concert | +0.034 |
professor | +0.034 |
therapist | +0.033 |
Neg logit contributions | |
elt | -0.049 |
cr | -0.047 |
ring | -0.047 |
Sur | -0.045 |
OOOO | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
elt | +0.062 |
cr | +0.059 |
ring | +0.058 |
Sur | +0.057 |
OOOO | +0.055 |
Neg logit contributions | |
gly | -0.052 |
irl | -0.051 |
professor | -0.049 |
therapist | -0.049 |
concert | -0.048 |
Token | animals |
Token ID | 4695 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
gly | +0.035 |
irl | +0.034 |
therapist | +0.033 |
acio | +0.032 |
concert | +0.032 |
Neg logit contributions | |
cr | -0.030 |
Sur | -0.030 |
elt | -0.029 |
OOOO | -0.028 |
eighteen | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.007 |
professor | +0.007 |
therapist | +0.007 |
issa | +0.007 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.006 |
lette | -0.006 |
umbs | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
gly | +0.044 |
irl | +0.044 |
professor | +0.043 |
concert | +0.043 |
tutor | +0.042 |
Neg logit contributions | |
elt | -0.046 |
ring | -0.043 |
cr | -0.042 |
Sur | -0.041 |
OOOO | -0.041 |
Token | ac |
Token ID | 936 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
gly | +0.035 |
irl | +0.035 |
concert | +0.033 |
therapist | +0.033 |
issa | +0.032 |
Neg logit contributions | |
elt | -0.031 |
cr | -0.030 |
Sur | -0.029 |
ring | -0.028 |
OOOO | -0.028 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
elt | +0.006 |
umbs | +0.006 |
cr | +0.006 |
ring | +0.006 |
OOOO | +0.005 |
Neg logit contributions | |
tutor | -0.003 |
professor | -0.003 |
irl | -0.003 |
concert | -0.003 |
Holly | -0.003 |
Token | ats |
Token ID | 1381 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
professor | +0.150 |
therapist | +0.143 |
tutor | +0.141 |
Sparkle | +0.139 |
Pixie | +0.137 |
Neg logit contributions | |
elt | -0.285 |
ring | -0.278 |
OOOO | -0.277 |
cr | -0.275 |
lette | -0.268 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e-03 |
Pos logit contributions | |
gly | +0.080 |
irl | +0.078 |
professor | +0.076 |
concert | +0.075 |
tutor | +0.074 |
Neg logit contributions | |
elt | -0.131 |
ring | -0.125 |
cr | -0.124 |
Sur | -0.120 |
OOOO | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
professor | +0.003 |
tutor | +0.003 |
concert | +0.003 |
stage | +0.003 |
gly | +0.003 |
Neg logit contributions | |
elt | -0.007 |
ring | -0.007 |
OOOO | -0.007 |
cr | -0.006 |
umbs | -0.006 |
Token | clown |
Token ID | 25573 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gly | +0.029 |
irl | +0.028 |
professor | +0.028 |
concert | +0.028 |
tutor | +0.027 |
Neg logit contributions | |
elt | -0.036 |
ring | -0.035 |
cr | -0.034 |
Sur | -0.033 |
OOOO | -0.033 |
Token | s |
Token ID | 82 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
elt | +0.039 |
ring | +0.037 |
cr | +0.037 |
Sur | +0.036 |
OOOO | +0.036 |
Neg logit contributions | |
gly | -0.018 |
irl | -0.017 |
professor | -0.016 |
concert | -0.016 |
tutor | -0.016 |
Token | elephants |
Token ID | 25368 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
gly | +0.021 |
professor | +0.020 |
irl | +0.020 |
tutor | +0.020 |
concert | +0.020 |
Neg logit contributions | |
elt | -0.027 |
ring | -0.025 |
cr | -0.024 |
OOOO | -0.024 |
Sur | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
elt | +0.061 |
ring | +0.058 |
cr | +0.058 |
Sur | +0.056 |
OOOO | +0.055 |
Neg logit contributions | |
irl | -0.036 |
gly | -0.036 |
professor | -0.034 |
concert | -0.034 |
therapist | -0.033 |
Token | lions |
Token ID | 31420 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
stage | +0.014 |
gly | +0.014 |
poster | +0.014 |
ls | +0.013 |
professor | +0.013 |
Neg logit contributions | |
elt | -0.031 |
ring | -0.031 |
OOOO | -0.030 |
umbs | -0.029 |
lette | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
elt | +0.092 |
ring | +0.088 |
cr | +0.088 |
Sur | +0.085 |
OOOO | +0.084 |
Neg logit contributions | |
gly | -0.050 |
irl | -0.050 |
professor | -0.048 |
concert | -0.047 |
therapist | -0.046 |
Token | ac |
Token ID | 936 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
elt | +0.010 |
ring | +0.010 |
OOOO | +0.010 |
umbs | +0.009 |
lette | +0.009 |
Neg logit contributions | |
professor | -0.007 |
stage | -0.007 |
tutor | -0.007 |
concert | -0.007 |
mun | -0.007 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
elt | +0.015 |
cr | +0.015 |
ring | +0.014 |
umbs | +0.014 |
Sur | +0.014 |
Neg logit contributions | |
tutor | -0.006 |
irl | -0.006 |
concert | -0.005 |
professor | -0.005 |
therapist | -0.005 |
Token | ats |
Token ID | 1381 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
professor | +0.118 |
therapist | +0.118 |
concert | +0.113 |
tutor | +0.112 |
gly | +0.109 |
Neg logit contributions | |
elt | -0.315 |
ring | -0.305 |
cr | -0.301 |
OOOO | -0.298 |
Sur | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
gly | +0.072 |
irl | +0.072 |
professor | +0.069 |
concert | +0.068 |
tutor | +0.067 |
Neg logit contributions | |
elt | -0.115 |
ring | -0.112 |
cr | -0.111 |
Sur | -0.105 |
OOOO | -0.105 |
Token | They |
Token ID | 1119 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
ring | +0.017 |
elt | +0.017 |
cr | +0.016 |
lette | +0.016 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.018 |
professor | -0.018 |
tutor | -0.018 |
Holly | -0.018 |
Sparkle | -0.017 |
Token | are |
Token ID | 389 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
gly | +0.011 |
therapist | +0.011 |
irl | +0.010 |
concert | +0.010 |
tutor | +0.010 |
Neg logit contributions | |
cr | -0.008 |
elt | -0.008 |
ring | -0.008 |
Sur | -0.008 |
eighteen | -0.008 |
Token | amazed |
Token ID | 24562 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
elt | +0.025 |
ring | +0.023 |
cr | +0.023 |
Sur | +0.022 |
OOOO | +0.022 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.017 |
professor | -0.017 |
concert | -0.016 |
tutor | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
gly | +0.005 |
irl | +0.005 |
concert | +0.005 |
professor | +0.005 |
tutor | +0.005 |
Neg logit contributions | |
elt | -0.006 |
cr | -0.006 |
ring | -0.006 |
Sur | -0.006 |
OOOO | -0.006 |
Token | clown |
Token ID | 25573 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
elt | +0.087 |
ring | +0.083 |
cr | +0.081 |
Sur | +0.078 |
OOOO | +0.078 |
Neg logit contributions | |
gly | -0.072 |
irl | -0.070 |
professor | -0.069 |
concert | -0.068 |
tutor | -0.067 |
Token | s |
Token ID | 82 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
elt | +0.043 |
ring | +0.042 |
cr | +0.041 |
Sur | +0.040 |
OOOO | +0.040 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
professor | -0.019 |
concert | -0.019 |
therapist | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -4.40e-04 |
Pos logit contributions | |
gly | +0.034 |
irl | +0.034 |
professor | +0.033 |
concert | +0.032 |
therapist | +0.032 |
Neg logit contributions | |
elt | -0.044 |
ring | -0.041 |
cr | -0.041 |
Sur | -0.039 |
OOOO | -0.039 |
Token | ac |
Token ID | 936 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
elt | +0.001 |
ring | +0.001 |
OOOO | +0.001 |
cr | +0.001 |
umbs | +0.001 |
Neg logit contributions | |
gly | -0.001 |
professor | -0.001 |
tutor | -0.001 |
concert | -0.001 |
stage | -0.001 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
elt | +0.011 |
cr | +0.010 |
umbs | +0.010 |
ring | +0.010 |
Sur | +0.010 |
Neg logit contributions | |
tutor | -0.006 |
professor | -0.006 |
irl | -0.006 |
concert | -0.006 |
therapist | -0.005 |
Token | ats |
Token ID | 1381 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
professor | +0.123 |
therapist | +0.121 |
concert | +0.118 |
tutor | +0.116 |
gly | +0.111 |
Neg logit contributions | |
elt | -0.309 |
ring | -0.297 |
cr | -0.294 |
OOOO | -0.292 |
lette | -0.284 |
Token | and |
Token ID | 290 |
Feature activation | -7.35e-04 |
Pos logit contributions | |
gly | +0.084 |
irl | +0.083 |
professor | +0.080 |
concert | +0.079 |
tutor | +0.078 |
Neg logit contributions | |
elt | -0.113 |
ring | -0.109 |
cr | -0.108 |
Sur | -0.102 |
OOOO | -0.101 |
Token | lions |
Token ID | 31420 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
elt | +0.001 |
ring | +0.001 |
OOOO | +0.001 |
umbs | +0.001 |
cr | +0.001 |
Neg logit contributions | |
professor | -0.001 |
gly | -0.001 |
tutor | -0.001 |
stage | -0.001 |
concert | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -5.98e-04 |
Pos logit contributions | |
elt | +0.089 |
ring | +0.085 |
cr | +0.085 |
Sur | +0.082 |
OOOO | +0.081 |
Neg logit contributions | |
gly | -0.051 |
irl | -0.050 |
professor | -0.048 |
concert | -0.047 |
tutor | -0.046 |
Token | elephants |
Token ID | 25368 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
elt | +0.001 |
ring | +0.001 |
OOOO | +0.001 |
lette | +0.001 |
cr | +0.001 |
Neg logit contributions | |
professor | -0.001 |
stage | -0.001 |
concert | -0.001 |
tutor | -0.001 |
gly | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
gly | +0.011 |
irl | +0.010 |
tutor | +0.009 |
therapist | +0.009 |
ls | +0.009 |
Neg logit contributions | |
elt | -0.031 |
ring | -0.030 |
cr | -0.029 |
OOOO | -0.029 |
Sur | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
gly | +0.019 |
tutor | +0.018 |
therapist | +0.017 |
Sparkle | +0.017 |
irl | +0.017 |
Neg logit contributions | |
elt | -0.026 |
ring | -0.025 |
cr | -0.025 |
umbs | -0.024 |
OOOO | -0.024 |
Token | E |
Token ID | 36 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
therapist | +0.003 |
gly | +0.003 |
mun | +0.003 |
irl | +0.003 |
ricia | +0.003 |
Neg logit contributions | |
ring | -0.004 |
elt | -0.004 |
OOOO | -0.004 |
lette | -0.004 |
asure | -0.004 |
Token | ww |
Token ID | 1383 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
tutor | +0.009 |
professor | +0.009 |
concert | +0.008 |
irl | +0.008 |
Sparkle | +0.008 |
Neg logit contributions | |
elt | -0.009 |
cr | -0.008 |
OOOO | -0.008 |
ring | -0.008 |
Sur | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
elt | +0.189 |
ring | +0.178 |
cr | +0.178 |
Sur | +0.173 |
OOOO | +0.172 |
Neg logit contributions | |
gly | -0.114 |
professor | -0.113 |
irl | -0.112 |
concert | -0.109 |
tutor | -0.108 |
Token | Bruno |
Token ID | 31045 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
gly | +0.019 |
irl | +0.019 |
concert | +0.018 |
professor | +0.018 |
tutor | +0.018 |
Neg logit contributions | |
elt | -0.024 |
ring | -0.023 |
cr | -0.022 |
Sur | -0.022 |
OOOO | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
irl | +0.192 |
concert | +0.183 |
professor | +0.182 |
gly | +0.179 |
tutor | +0.174 |
Neg logit contributions | |
elt | -0.243 |
cr | -0.232 |
ring | -0.230 |
OOOO | -0.223 |
Sur | -0.217 |
Token | You |
Token ID | 921 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.008 |
OOOO | +0.008 |
Neg logit contributions | |
gly | -0.009 |
Holly | -0.008 |
therapist | -0.008 |
Sparkle | -0.008 |
Bruno | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.004 |
cr | +0.003 |
Sur | +0.003 |
OOOO | +0.003 |
Neg logit contributions | |
gly | -0.003 |
irl | -0.003 |
concert | -0.003 |
professor | -0.003 |
Hood | -0.003 |
Token | st |
Token ID | 336 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
elt | +0.024 |
ring | +0.023 |
cr | +0.022 |
Sur | +0.022 |
OOOO | +0.021 |
Neg logit contributions | |
gly | -0.019 |
irl | -0.019 |
professor | -0.018 |
concert | -0.018 |
tutor | -0.018 |
Token | inky |
Token ID | 29246 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
gly | +0.009 |
irl | +0.009 |
professor | +0.008 |
concert | +0.008 |
therapist | +0.008 |
Neg logit contributions | |
elt | -0.010 |
ring | -0.009 |
cr | -0.009 |
Sur | -0.009 |
OOOO | -0.009 |
Token | Hi |
Token ID | 17250 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
elt | +0.012 |
ring | +0.012 |
cr | +0.012 |
OOOO | +0.011 |
Sur | +0.011 |
Neg logit contributions | |
gly | -0.013 |
irl | -0.012 |
professor | -0.012 |
concert | -0.012 |
therapist | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
irl | +0.010 |
professor | +0.010 |
gly | +0.009 |
concert | +0.009 |
therapist | +0.009 |
Neg logit contributions | |
elt | -0.010 |
Sur | -0.010 |
cr | -0.009 |
OOOO | -0.009 |
ring | -0.009 |
Token | m |
Token ID | 285 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
irl | +0.013 |
gly | +0.013 |
ines | +0.012 |
professor | +0.012 |
Hood | +0.012 |
Neg logit contributions | |
elt | -0.014 |
Sur | -0.013 |
cr | -0.013 |
ring | -0.012 |
OOOO | -0.012 |
Token | ister |
Token ID | 1694 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
irl | +0.044 |
concert | +0.041 |
tutor | +0.040 |
Sparkle | +0.040 |
Hood | +0.039 |
Neg logit contributions | |
elt | -0.085 |
ring | -0.080 |
cr | -0.078 |
OOOO | -0.077 |
Sur | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
irl | +0.055 |
gly | +0.051 |
concert | +0.049 |
professor | +0.048 |
tutor | +0.048 |
Neg logit contributions | |
elt | -0.065 |
ring | -0.063 |
cr | -0.062 |
OOOO | -0.059 |
Sur | -0.057 |
Token | Bruno |
Token ID | 31045 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.012 |
cr | +0.012 |
umbs | +0.012 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.016 |
professor | -0.016 |
therapist | -0.015 |
tutor | -0.015 |
Sparkle | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
irl | +0.185 |
professor | +0.176 |
tutor | +0.175 |
concert | +0.174 |
gly | +0.173 |
Neg logit contributions | |
elt | -0.240 |
ring | -0.225 |
cr | -0.225 |
OOOO | -0.211 |
Sur | -0.211 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
gly | +0.054 |
irl | +0.052 |
concert | +0.052 |
professor | +0.051 |
therapist | +0.050 |
Neg logit contributions | |
elt | -0.043 |
cr | -0.041 |
ring | -0.040 |
Sur | -0.039 |
OOOO | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
elt | +0.029 |
ring | +0.028 |
cr | +0.027 |
Sur | +0.026 |
OOOO | +0.026 |
Neg logit contributions | |
gly | -0.019 |
irl | -0.019 |
concert | -0.018 |
professor | -0.018 |
therapist | -0.017 |
Token | Can |
Token ID | 1680 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
elt | +0.014 |
ring | +0.014 |
cr | +0.013 |
OOOO | +0.013 |
Sur | +0.013 |
Neg logit contributions | |
gly | -0.017 |
professor | -0.017 |
therapist | -0.016 |
tutor | -0.016 |
irl | -0.016 |
Token | we |
Token ID | 356 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
elt | +0.020 |
cr | +0.019 |
ring | +0.019 |
Sur | +0.018 |
OOOO | +0.017 |
Neg logit contributions | |
irl | -0.032 |
gly | -0.032 |
professor | -0.032 |
concert | -0.031 |
tutor | -0.031 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
irl | +0.005 |
gly | +0.005 |
ls | +0.005 |
issa | +0.005 |
ricia | +0.005 |
Neg logit contributions | |
ring | -0.009 |
elt | -0.009 |
cr | -0.009 |
lette | -0.009 |
umbs | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
elt | +0.102 |
ring | +0.101 |
cr | +0.098 |
OOOO | +0.096 |
lette | +0.095 |
Neg logit contributions | |
gly | -0.064 |
tutor | -0.061 |
irl | -0.060 |
concert | -0.060 |
professor | -0.059 |
Token | seeds |
Token ID | 11904 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
tutor | +0.008 |
poster | +0.007 |
gly | +0.007 |
concert | +0.007 |
Hood | +0.007 |
Neg logit contributions | |
elt | -0.010 |
ring | -0.009 |
cr | -0.009 |
Sur | -0.009 |
OOOO | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -4.61e-03 |
Pos logit contributions | |
elt | +0.127 |
ring | +0.119 |
cr | +0.117 |
Sur | +0.117 |
OOOO | +0.116 |
Neg logit contributions | |
irl | -0.069 |
gly | -0.066 |
concert | -0.064 |
ls | -0.062 |
therapist | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
ring | +0.011 |
elt | +0.011 |
umbs | +0.010 |
OOOO | +0.010 |
lette | +0.010 |
Neg logit contributions | |
ls | -0.004 |
show | -0.004 |
stage | -0.004 |
tutor | -0.004 |
Hood | -0.004 |
Token | pulp |
Token ID | 38341 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
tutor | +0.009 |
poster | +0.008 |
stage | +0.008 |
gly | +0.008 |
professor | +0.008 |
Neg logit contributions | |
elt | -0.009 |
ring | -0.009 |
cr | -0.008 |
umbs | -0.008 |
OOOO | -0.008 |
Token | spill |
Token ID | 19431 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
elt | +0.408 |
Sur | +0.389 |
OOOO | +0.388 |
ring | +0.385 |
eighteen | +0.373 |
Neg logit contributions | |
ls | -0.127 |
irl | -0.118 |
ines | -0.109 |
closely | -0.105 |
up | -0.104 |
Token | out |
Token ID | 503 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
elt | +0.164 |
ring | +0.155 |
lette | +0.154 |
OOOO | +0.150 |
Sur | +0.150 |
Neg logit contributions | |
up | -0.050 |
ls | -0.050 |
closely | -0.038 |
ches | -0.037 |
irl | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
elt | +0.042 |
lette | +0.040 |
Sur | +0.039 |
OOOO | +0.039 |
ring | +0.039 |
Neg logit contributions | |
ls | -0.009 |
up | -0.007 |
ines | -0.007 |
closely | -0.007 |
aisle | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +5.74e-03 |
Pos logit contributions | |
ring | +0.018 |
cr | +0.018 |
lette | +0.017 |
eighteen | +0.017 |
OOOO | +0.017 |
Neg logit contributions | |
tutor | -0.011 |
gly | -0.010 |
Sparkle | -0.010 |
professor | -0.010 |
Pixie | -0.010 |
Token | cried |
Token ID | 16896 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
irl | +0.006 |
ls | +0.006 |
gly | +0.006 |
issa | +0.006 |
ricia | +0.006 |
Neg logit contributions | |
ring | -0.012 |
elt | -0.012 |
lette | -0.011 |
cr | -0.011 |
OOOO | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
gly | +0.081 |
irl | +0.078 |
professor | +0.075 |
concert | +0.074 |
therapist | +0.072 |
Neg logit contributions | |
elt | -0.101 |
ring | -0.097 |
cr | -0.096 |
Sur | -0.091 |
OOOO | -0.089 |
Token | it |
Token ID | 340 |
Feature activation | -5.14e-03 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.024 |
cr | +0.024 |
Sur | +0.023 |
OOOO | +0.023 |
Neg logit contributions | |
gly | -0.018 |
irl | -0.018 |
concert | -0.017 |
professor | -0.017 |
therapist | -0.017 |
Token | shattered |
Token ID | 23273 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.009 |
irl | -0.008 |
professor | -0.008 |
concert | -0.008 |
tutor | -0.008 |
Token | into |
Token ID | 656 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
elt | +0.161 |
cr | +0.152 |
ring | +0.152 |
Sur | +0.149 |
OOOO | +0.148 |
Neg logit contributions | |
irl | -0.105 |
gly | -0.105 |
therapist | -0.101 |
concert | -0.100 |
professor | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
elt | +0.037 |
ring | +0.035 |
cr | +0.034 |
lette | +0.033 |
OOOO | +0.033 |
Neg logit contributions | |
stage | -0.028 |
irl | -0.027 |
gly | -0.027 |
tutor | -0.027 |
professor | -0.027 |
Token | million |
Token ID | 1510 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
elt | +0.007 |
ring | +0.006 |
cr | +0.006 |
Sur | +0.006 |
OOOO | +0.006 |
Neg logit contributions | |
gly | -0.010 |
irl | -0.010 |
professor | -0.009 |
concert | -0.009 |
therapist | -0.009 |
Token | pieces |
Token ID | 5207 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
elt | +0.221 |
ring | +0.209 |
cr | +0.207 |
Sur | +0.201 |
OOOO | +0.193 |
Neg logit contributions | |
gly | -0.261 |
irl | -0.252 |
professor | -0.249 |
concert | -0.246 |
tutor | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
elt | +0.088 |
ring | +0.083 |
cr | +0.082 |
Sur | +0.081 |
OOOO | +0.080 |
Neg logit contributions | |
gly | -0.049 |
irl | -0.049 |
concert | -0.047 |
professor | -0.047 |
therapist | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
elt | +0.040 |
ring | +0.039 |
cr | +0.039 |
OOOO | +0.037 |
Sur | +0.036 |
Neg logit contributions | |
gly | -0.034 |
irl | -0.033 |
professor | -0.032 |
tutor | -0.032 |
concert | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
elt | +0.005 |
ring | +0.005 |
cr | +0.005 |
Sur | +0.005 |
OOOO | +0.004 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
concert | -0.004 |
tutor | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.008 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.007 |
irl | -0.007 |
professor | -0.007 |
concert | -0.007 |
therapist | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
elt | +0.058 |
cr | +0.055 |
Sur | +0.054 |
lette | +0.053 |
ring | +0.053 |
Neg logit contributions | |
gly | -0.048 |
professor | -0.046 |
issa | -0.046 |
therapist | -0.046 |
Hood | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
elt | +0.104 |
ring | +0.098 |
cr | +0.097 |
Sur | +0.094 |
OOOO | +0.092 |
Neg logit contributions | |
gly | -0.075 |
irl | -0.073 |
professor | -0.071 |
concert | -0.071 |
therapist | -0.070 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
elt | +0.034 |
ring | +0.033 |
cr | +0.032 |
Sur | +0.031 |
OOOO | +0.031 |
Neg logit contributions | |
gly | -0.021 |
irl | -0.021 |
professor | -0.020 |
concert | -0.020 |
therapist | -0.020 |
Token | Mary |
Token ID | 5335 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ring | +0.062 |
elt | +0.062 |
cr | +0.061 |
Sur | +0.059 |
lette | +0.058 |
Neg logit contributions | |
irl | -0.052 |
gly | -0.052 |
therapist | -0.050 |
professor | -0.049 |
concert | -0.048 |
Token | two |
Token ID | 734 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
ring | +0.042 |
elt | +0.042 |
cr | +0.041 |
lette | +0.038 |
Sur | +0.037 |
Neg logit contributions | |
gly | -0.044 |
irl | -0.044 |
concert | -0.041 |
professor | -0.040 |
therapist | -0.040 |
Token | million |
Token ID | 1510 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
elt | +0.101 |
ring | +0.098 |
Sur | +0.096 |
cr | +0.096 |
umbs | +0.091 |
Neg logit contributions | |
irl | -0.113 |
gly | -0.111 |
professor | -0.104 |
concert | -0.104 |
issa | -0.103 |
Token | times |
Token ID | 1661 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
elt | +0.196 |
ring | +0.195 |
cr | +0.193 |
Sur | +0.184 |
umbs | +0.183 |
Neg logit contributions | |
irl | -0.245 |
therapist | -0.237 |
concert | -0.234 |
gly | -0.228 |
professor | -0.224 |
Token | for |
Token ID | 329 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
elt | +0.125 |
ring | +0.122 |
cr | +0.119 |
Sur | +0.113 |
OOOO | +0.112 |
Neg logit contributions | |
gly | -0.093 |
irl | -0.093 |
concert | -0.087 |
professor | -0.087 |
therapist | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
gly | +0.033 |
irl | +0.032 |
professor | +0.031 |
therapist | +0.031 |
concert | +0.031 |
Neg logit contributions | |
elt | -0.040 |
cr | -0.039 |
ring | -0.039 |
Sur | -0.037 |
OOOO | -0.036 |
Token | surprise |
Token ID | 5975 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
elt | +0.014 |
cr | +0.014 |
ring | +0.014 |
Sur | +0.013 |
lette | +0.013 |
Neg logit contributions | |
irl | -0.012 |
therapist | -0.011 |
gly | -0.011 |
issa | -0.011 |
professor | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
irl | +0.009 |
gly | +0.009 |
professor | +0.008 |
concert | +0.008 |
Hood | +0.008 |
Neg logit contributions | |
elt | -0.011 |
ring | -0.011 |
cr | -0.011 |
Sur | -0.010 |
lette | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
elt | +0.005 |
ring | +0.005 |
umbs | +0.005 |
OOOO | +0.005 |
cr | +0.005 |
Neg logit contributions | |
gly | -0.003 |
therapist | -0.003 |
tutor | -0.003 |
professor | -0.003 |
irl | -0.003 |
Token | I |
Token ID | 40 |
Feature activation | +7.81e-04 |
Pos logit contributions | |
elt | +0.024 |
OOOO | +0.023 |
ring | +0.023 |
cr | +0.022 |
umbs | +0.021 |
Neg logit contributions | |
therapist | -0.022 |
gly | -0.022 |
irl | -0.021 |
concert | -0.021 |
professor | -0.021 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
gly | +0.001 |
irl | +0.001 |
professor | +0.001 |
concert | +0.001 |
tutor | +0.001 |
Neg logit contributions | |
elt | -0.001 |
ring | -0.001 |
cr | -0.001 |
Sur | -0.001 |
OOOO | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.012 |
cr | +0.012 |
Sur | +0.011 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.019 |
professor | -0.019 |
concert | -0.019 |
tutor | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
elt | +0.034 |
ring | +0.033 |
cr | +0.032 |
Sur | +0.031 |
OOOO | +0.031 |
Neg logit contributions | |
gly | -0.030 |
irl | -0.029 |
professor | -0.029 |
concert | -0.028 |
therapist | -0.028 |
Token | million |
Token ID | 1510 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Sur | +0.005 |
elt | +0.005 |
cr | +0.005 |
ring | +0.005 |
eighteen | +0.005 |
Neg logit contributions | |
gly | -0.005 |
irl | -0.005 |
acio | -0.004 |
therapist | -0.004 |
Hood | -0.004 |
Token | bucks |
Token ID | 24780 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
elt | +0.254 |
ring | +0.246 |
cr | +0.242 |
Sur | +0.234 |
OOOO | +0.229 |
Neg logit contributions | |
gly | -0.204 |
irl | -0.198 |
professor | -0.193 |
therapist | -0.192 |
tutor | -0.189 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
elt | +0.012 |
Sur | +0.011 |
ring | +0.011 |
cr | +0.011 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.008 |
irl | -0.008 |
professor | -0.007 |
therapist | -0.007 |
tutor | -0.007 |
Token | And |
Token ID | 843 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
elt | +0.070 |
ring | +0.067 |
cr | +0.066 |
OOOO | +0.064 |
Sur | +0.063 |
Neg logit contributions | |
gly | -0.061 |
professor | -0.058 |
irl | -0.058 |
tutor | -0.058 |
concert | -0.058 |
Token | just |
Token ID | 655 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
cr | +0.022 |
OOOO | +0.021 |
Sur | +0.021 |
Neg logit contributions | |
gly | -0.018 |
professor | -0.017 |
concert | -0.017 |
therapist | -0.017 |
irl | -0.017 |
Token | like |
Token ID | 588 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
umbs | +0.035 |
elt | +0.035 |
Sur | +0.034 |
OOOO | +0.033 |
cr | +0.032 |
Neg logit contributions | |
gly | -0.027 |
irl | -0.026 |
closely | -0.025 |
professor | -0.025 |
concert | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Sur | +0.017 |
elt | +0.017 |
cr | +0.016 |
OOOO | +0.015 |
ring | +0.015 |
Neg logit contributions | |
irl | -0.023 |
therapist | -0.023 |
gly | -0.023 |
concert | -0.023 |
professor | -0.022 |
Token | Sarah |
Token ID | 29284 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
elt | +0.021 |
ring | +0.020 |
cr | +0.020 |
Sur | +0.019 |
OOOO | +0.019 |
Neg logit contributions | |
gly | -0.024 |
irl | -0.024 |
professor | -0.023 |
concert | -0.023 |
therapist | -0.023 |
Token | wished |
Token ID | 16555 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
elt | +0.032 |
ring | +0.030 |
cr | +0.030 |
Sur | +0.029 |
OOOO | +0.028 |
Neg logit contributions | |
gly | -0.024 |
irl | -0.024 |
professor | -0.023 |
concert | -0.023 |
tutor | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.015 |
cr | +0.015 |
Sur | +0.015 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.012 |
irl | -0.012 |
professor | -0.012 |
concert | -0.012 |
therapist | -0.011 |
Token | one |
Token ID | 530 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
gly | +0.049 |
irl | +0.049 |
therapist | +0.047 |
concert | +0.047 |
professor | +0.046 |
Neg logit contributions | |
elt | -0.035 |
ring | -0.034 |
cr | -0.034 |
Sur | -0.033 |
OOOO | -0.031 |
Token | million |
Token ID | 1510 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
gly | +0.009 |
irl | +0.009 |
acio | +0.009 |
concert | +0.008 |
Hood | +0.008 |
Neg logit contributions | |
ring | -0.010 |
elt | -0.010 |
cr | -0.009 |
Sur | -0.009 |
lette | -0.009 |
Token | toy |
Token ID | 13373 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ring | +0.227 |
elt | +0.225 |
cr | +0.214 |
Sur | +0.207 |
lette | +0.200 |
Neg logit contributions | |
gly | -0.222 |
irl | -0.219 |
concert | -0.213 |
therapist | -0.211 |
professor | -0.209 |
Token | animals |
Token ID | 4695 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
irl | +0.006 |
gly | +0.006 |
concert | +0.005 |
professor | +0.005 |
therapist | +0.005 |
Neg logit contributions | |
elt | -0.007 |
ring | -0.007 |
cr | -0.007 |
Sur | -0.006 |
OOOO | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
cr | +0.022 |
Sur | +0.020 |
lette | +0.020 |
Neg logit contributions | |
irl | -0.019 |
gly | -0.019 |
concert | -0.018 |
professor | -0.018 |
therapist | -0.018 |
Token | but |
Token ID | 475 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
professor | +0.002 |
gly | +0.002 |
concert | +0.002 |
tutor | +0.002 |
irl | +0.002 |
Neg logit contributions | |
elt | -0.002 |
ring | -0.002 |
OOOO | -0.002 |
cr | -0.002 |
Sur | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
elt | +0.028 |
ring | +0.026 |
cr | +0.026 |
Sur | +0.025 |
OOOO | +0.025 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
professor | -0.019 |
concert | -0.019 |
therapist | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
elt | +0.188 |
ring | +0.178 |
cr | +0.172 |
OOOO | +0.167 |
lette | +0.166 |
Neg logit contributions | |
irl | -0.068 |
ls | -0.067 |
gly | -0.064 |
poster | -0.059 |
stage | -0.059 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
poster | +0.022 |
ls | +0.021 |
closely | +0.021 |
first | +0.021 |
top | +0.020 |
Neg logit contributions | |
elt | -0.022 |
ring | -0.019 |
and | -0.018 |
OOOO | -0.018 |
lette | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
elt | +0.240 |
ring | +0.231 |
OOOO | +0.223 |
cr | +0.222 |
lette | +0.218 |
Neg logit contributions | |
irl | -0.068 |
gly | -0.064 |
ls | -0.064 |
stage | -0.059 |
ines | -0.058 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
poster | +0.024 |
closely | +0.022 |
show | +0.022 |
ls | +0.022 |
bar | +0.022 |
Neg logit contributions | |
elt | -0.021 |
ring | -0.016 |
OOOO | -0.016 |
and | -0.016 |
lette | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
elt | +0.324 |
ring | +0.322 |
cr | +0.307 |
OOOO | +0.299 |
Sur | +0.296 |
Neg logit contributions | |
irl | -0.089 |
gly | -0.087 |
ls | -0.077 |
poster | -0.069 |
ines | -0.067 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
poster | +0.022 |
closely | +0.022 |
first | +0.021 |
ls | +0.021 |
show | +0.021 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.016 |
OOOO | -0.015 |
and | -0.015 |
keeping | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
elt | +0.382 |
ring | +0.379 |
cr | +0.352 |
OOOO | +0.350 |
lette | +0.345 |
Neg logit contributions | |
irl | -0.087 |
ls | -0.085 |
gly | -0.076 |
ines | -0.068 |
stage | -0.067 |
Token | nineteen |
Token ID | 43063 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
poster | +0.021 |
closely | +0.021 |
first | +0.020 |
show | +0.020 |
ls | +0.020 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.016 |
OOOO | -0.016 |
umbs | -0.015 |
and | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
elt | +0.269 |
ring | +0.263 |
cr | +0.249 |
umbs | +0.244 |
Sur | +0.244 |
Neg logit contributions | |
irl | -0.076 |
gly | -0.067 |
closely | -0.064 |
ls | -0.064 |
ines | -0.061 |
Token | twenty |
Token ID | 8208 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
closely | +0.020 |
poster | +0.019 |
up | +0.018 |
irl | +0.018 |
first | +0.018 |
Neg logit contributions | |
elt | -0.021 |
ring | -0.020 |
umbs | -0.020 |
OOOO | -0.019 |
cr | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
elt | +0.067 |
ring | +0.062 |
cr | +0.060 |
Sur | +0.058 |
OOOO | +0.057 |
Neg logit contributions | |
irl | -0.040 |
gly | -0.038 |
ls | -0.037 |
ela | -0.036 |
ines | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
elt | +0.189 |
ring | +0.180 |
cr | +0.176 |
OOOO | +0.166 |
lette | +0.165 |
Neg logit contributions | |
irl | -0.065 |
ls | -0.063 |
ines | -0.059 |
poster | -0.058 |
stage | -0.057 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
poster | +0.021 |
first | +0.020 |
hard | +0.019 |
closely | +0.019 |
top | +0.019 |
Neg logit contributions | |
elt | -0.021 |
ring | -0.017 |
OOOO | -0.017 |
cr | -0.017 |
keeping | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
elt | +0.248 |
ring | +0.241 |
cr | +0.234 |
OOOO | +0.228 |
lette | +0.223 |
Neg logit contributions | |
irl | -0.060 |
ls | -0.055 |
ines | -0.054 |
stage | -0.053 |
poster | -0.051 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
poster | +0.022 |
show | +0.021 |
closely | +0.021 |
stage | +0.020 |
hard | +0.020 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.015 |
OOOO | -0.015 |
cr | -0.015 |
lette | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ring | +0.326 |
elt | +0.325 |
cr | +0.314 |
OOOO | +0.300 |
Sur | +0.296 |
Neg logit contributions | |
irl | -0.086 |
gly | -0.080 |
ls | -0.075 |
ines | -0.070 |
poster | -0.068 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
poster | +0.021 |
closely | +0.020 |
first | +0.020 |
up | +0.019 |
show | +0.019 |
Neg logit contributions | |
elt | -0.019 |
ring | -0.015 |
keeping | -0.015 |
OOOO | -0.015 |
cr | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ring | +0.385 |
elt | +0.384 |
cr | +0.362 |
OOOO | +0.351 |
lette | +0.346 |
Neg logit contributions | |
irl | -0.080 |
ls | -0.079 |
ines | -0.069 |
stage | -0.062 |
poster | -0.062 |
Token | nineteen |
Token ID | 43063 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
poster | +0.020 |
closely | +0.019 |
first | +0.019 |
show | +0.019 |
up | +0.018 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.016 |
keeping | -0.016 |
OOOO | -0.015 |
cr | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
elt | +0.274 |
ring | +0.271 |
cr | +0.258 |
umbs | +0.249 |
OOOO | +0.249 |
Neg logit contributions | |
irl | -0.069 |
closely | -0.059 |
ines | -0.058 |
gly | -0.057 |
ls | -0.057 |
Token | twenty |
Token ID | 8208 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
closely | +0.018 |
poster | +0.018 |
up | +0.017 |
irl | +0.017 |
stage | +0.017 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.020 |
OOOO | -0.019 |
cr | -0.019 |
umbs | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
elt | +0.074 |
ring | +0.069 |
cr | +0.068 |
Sur | +0.063 |
OOOO | +0.062 |
Neg logit contributions | |
irl | -0.035 |
ls | -0.033 |
ines | -0.032 |
gly | -0.032 |
poster | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
gly | +0.046 |
irl | +0.045 |
professor | +0.044 |
concert | +0.043 |
therapist | +0.042 |
Neg logit contributions | |
elt | -0.064 |
ring | -0.060 |
cr | -0.060 |
Sur | -0.058 |
OOOO | -0.057 |
Token | it |
Token ID | 340 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
elt | +0.020 |
ring | +0.019 |
cr | +0.019 |
OOOO | +0.018 |
umbs | +0.018 |
Neg logit contributions | |
irl | -0.012 |
gly | -0.012 |
concert | -0.012 |
therapist | -0.012 |
professor | -0.011 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
elt | +0.003 |
lette | +0.003 |
ring | +0.003 |
cr | +0.002 |
Sur | +0.002 |
Neg logit contributions | |
irl | -0.002 |
ches | -0.002 |
gly | -0.002 |
ls | -0.002 |
therapist | -0.002 |
Token | into |
Token ID | 656 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
elt | +0.124 |
ring | +0.117 |
Sur | +0.117 |
lette | +0.116 |
cr | +0.115 |
Neg logit contributions | |
up | -0.051 |
irl | -0.051 |
ls | -0.049 |
issa | -0.048 |
stage | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
elt | +0.031 |
ring | +0.029 |
cr | +0.028 |
lette | +0.028 |
seventeen | +0.026 |
Neg logit contributions | |
stage | -0.019 |
issa | -0.019 |
aisle | -0.018 |
tutor | -0.018 |
irl | -0.018 |
Token | million |
Token ID | 1510 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.003 |
concert | +0.003 |
professor | +0.003 |
tutor | +0.003 |
Neg logit contributions | |
elt | -0.003 |
ring | -0.003 |
cr | -0.003 |
OOOO | -0.002 |
Sur | -0.002 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
elt | +0.253 |
cr | +0.238 |
ring | +0.236 |
OOOO | +0.226 |
lette | +0.225 |
Neg logit contributions | |
irl | -0.200 |
gly | -0.194 |
concert | -0.190 |
issa | -0.188 |
stage | -0.187 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
elt | +0.084 |
ring | +0.080 |
cr | +0.079 |
Sur | +0.078 |
OOOO | +0.077 |
Neg logit contributions | |
gly | -0.042 |
irl | -0.041 |
concert | -0.039 |
professor | -0.039 |
tutor | -0.038 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
ring | +0.034 |
cr | +0.033 |
elt | +0.033 |
lette | +0.031 |
OOOO | +0.031 |
Neg logit contributions | |
gly | -0.026 |
tutor | -0.025 |
professor | -0.025 |
Holly | -0.025 |
therapist | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +6.42e-04 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
professor | +0.004 |
concert | +0.004 |
therapist | +0.004 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
irl | +0.001 |
gly | +0.001 |
concert | +0.001 |
professor | +0.001 |
tutor | +0.001 |
Neg logit contributions | |
elt | -0.001 |
cr | -0.001 |
ring | -0.001 |
OOOO | -0.001 |
Sur | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
elt | +0.048 |
ring | +0.046 |
cr | +0.045 |
Sur | +0.044 |
OOOO | +0.044 |
Neg logit contributions | |
gly | -0.026 |
irl | -0.025 |
professor | -0.024 |
concert | -0.024 |
tutor | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
elt | +0.033 |
ring | +0.031 |
cr | +0.031 |
OOOO | +0.030 |
umbs | +0.030 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
professor | -0.019 |
concert | -0.019 |
therapist | -0.019 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.007 |
cr | +0.007 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.007 |
irl | -0.007 |
professor | -0.007 |
concert | -0.007 |
tutor | -0.007 |
Token | into |
Token ID | 656 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
elt | +0.124 |
ring | +0.116 |
Sur | +0.116 |
cr | +0.114 |
lette | +0.113 |
Neg logit contributions | |
gly | -0.056 |
irl | -0.055 |
ls | -0.053 |
up | -0.053 |
Hood | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
elt | +0.035 |
ring | +0.033 |
cr | +0.031 |
lette | +0.031 |
OOOO | +0.030 |
Neg logit contributions | |
stage | -0.018 |
issa | -0.018 |
aisle | -0.018 |
gly | -0.018 |
professor | -0.017 |
Token | million |
Token ID | 1510 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
elt | +0.002 |
ring | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
Sur | +0.002 |
Neg logit contributions | |
gly | -0.002 |
irl | -0.001 |
professor | -0.001 |
concert | -0.001 |
tutor | -0.001 |
Token | pieces |
Token ID | 5207 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
elt | +0.218 |
ring | +0.206 |
cr | +0.203 |
Sur | +0.195 |
OOOO | +0.192 |
Neg logit contributions | |
gly | -0.237 |
irl | -0.233 |
professor | -0.227 |
concert | -0.226 |
therapist | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
elt | +0.089 |
ring | +0.085 |
cr | +0.084 |
Sur | +0.083 |
OOOO | +0.081 |
Neg logit contributions | |
gly | -0.046 |
irl | -0.045 |
professor | -0.043 |
concert | -0.043 |
tutor | -0.042 |
Token | His |
Token ID | 2399 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ring | +0.039 |
cr | +0.037 |
lette | +0.035 |
OOOO | +0.035 |
elt | +0.035 |
Neg logit contributions | |
gly | -0.031 |
Holly | -0.028 |
tutor | -0.028 |
shop | -0.027 |
aisle | -0.027 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
elt | +0.022 |
ring | +0.020 |
cr | +0.020 |
Sur | +0.020 |
OOOO | +0.019 |
Neg logit contributions | |
gly | -0.021 |
professor | -0.020 |
therapist | -0.020 |
irl | -0.020 |
ela | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.008 |
concert | +0.008 |
tutor | +0.008 |
Neg logit contributions | |
elt | -0.011 |
ring | -0.010 |
cr | -0.010 |
Sur | -0.010 |
OOOO | -0.010 |
Token | v |
Token ID | 410 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
cr | +0.022 |
Sur | +0.021 |
OOOO | +0.021 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.016 |
professor | -0.016 |
concert | -0.016 |
tutor | -0.015 |
Token | ase |
Token ID | 589 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.007 |
irl | -0.007 |
concert | -0.007 |
professor | -0.007 |
therapist | -0.007 |
Token | shattered |
Token ID | 23273 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
elt | +0.033 |
ring | +0.031 |
cr | +0.030 |
Sur | +0.029 |
OOOO | +0.029 |
Neg logit contributions | |
gly | -0.028 |
irl | -0.027 |
professor | -0.027 |
concert | -0.026 |
therapist | -0.026 |
Token | into |
Token ID | 656 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
elt | +0.148 |
lette | +0.145 |
cr | +0.143 |
Sur | +0.142 |
ring | +0.141 |
Neg logit contributions | |
ls | -0.089 |
irl | -0.083 |
stage | -0.083 |
up | -0.083 |
gly | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | -5.81e-04 |
Pos logit contributions | |
elt | +0.027 |
ring | +0.026 |
lette | +0.024 |
cr | +0.024 |
OOOO | +0.024 |
Neg logit contributions | |
stage | -0.016 |
aisle | -0.015 |
issa | -0.015 |
Holly | -0.015 |
tutor | -0.015 |
Token | million |
Token ID | 1510 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
elt | +0.001 |
ring | +0.001 |
cr | +0.001 |
OOOO | +0.001 |
lette | +0.001 |
Neg logit contributions | |
gly | -0.001 |
concert | -0.001 |
irl | -0.001 |
professor | -0.001 |
tutor | -0.001 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
elt | +0.228 |
ring | +0.214 |
cr | +0.212 |
Sur | +0.204 |
OOOO | +0.202 |
Neg logit contributions | |
gly | -0.224 |
irl | -0.221 |
professor | -0.214 |
concert | -0.214 |
therapist | -0.210 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
elt | +0.077 |
ring | +0.073 |
cr | +0.072 |
Sur | +0.072 |
OOOO | +0.071 |
Neg logit contributions | |
gly | -0.047 |
irl | -0.047 |
concert | -0.045 |
professor | -0.044 |
therapist | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
elt | +0.027 |
ring | +0.026 |
OOOO | +0.025 |
lette | +0.024 |
cr | +0.024 |
Neg logit contributions | |
therapist | -0.014 |
irl | -0.014 |
gly | -0.014 |
stage | -0.014 |
concert | -0.013 |
Token | elderly |
Token ID | 13830 |
Feature activation | +3.52e-04 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.012 |
cr | +0.012 |
Sur | +0.011 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.010 |
irl | -0.009 |
concert | -0.009 |
professor | -0.009 |
tutor | -0.009 |
Token | lady |
Token ID | 10846 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
gly | +0.000 |
irl | +0.000 |
professor | +0.000 |
concert | +0.000 |
Hood | +0.000 |
Neg logit contributions | |
elt | -0.001 |
ring | -0.001 |
Sur | -0.001 |
cr | -0.001 |
OOOO | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
ring | +0.029 |
cr | +0.029 |
elt | +0.027 |
lette | +0.027 |
Sur | +0.026 |
Neg logit contributions | |
professor | -0.024 |
gly | -0.023 |
tutor | -0.023 |
Sparkle | -0.023 |
stage | -0.022 |
Token | burst |
Token ID | 11173 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
elt | +0.005 |
ring | +0.005 |
Sur | +0.005 |
OOOO | +0.005 |
cr | +0.005 |
Neg logit contributions | |
irl | -0.004 |
gly | -0.004 |
concert | -0.004 |
professor | -0.004 |
Hood | -0.004 |
Token | open |
Token ID | 1280 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
elt | +0.219 |
OOOO | +0.214 |
cr | +0.213 |
ring | +0.211 |
Sur | +0.210 |
Neg logit contributions | |
up | -0.130 |
closely | -0.122 |
stage | -0.113 |
curiously | -0.112 |
Sparkle | -0.108 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
elt | +0.056 |
ring | +0.053 |
cr | +0.053 |
Sur | +0.052 |
OOOO | +0.051 |
Neg logit contributions | |
gly | -0.038 |
irl | -0.037 |
professor | -0.036 |
concert | -0.035 |
tutor | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
gly | +0.016 |
stage | +0.016 |
irl | +0.016 |
professor | +0.015 |
concert | +0.015 |
Neg logit contributions | |
elt | -0.025 |
ring | -0.024 |
cr | -0.023 |
OOOO | -0.023 |
lette | -0.022 |
Token | million |
Token ID | 1510 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
professor | +0.004 |
concert | +0.004 |
therapist | +0.004 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.005 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.004 |
Token | different |
Token ID | 1180 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
elt | +0.244 |
ring | +0.229 |
cr | +0.225 |
OOOO | +0.218 |
Sur | +0.215 |
Neg logit contributions | |
irl | -0.204 |
gly | -0.203 |
concert | -0.195 |
professor | -0.194 |
stage | -0.192 |
Token | colours |
Token ID | 18915 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
elt | +0.028 |
ring | +0.025 |
cr | +0.025 |
Sur | +0.024 |
OOOO | +0.024 |
Neg logit contributions | |
stage | -0.019 |
gly | -0.019 |
irl | -0.019 |
concert | -0.018 |
professor | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
elt | +0.094 |
OOOO | +0.089 |
Sur | +0.089 |
ring | +0.088 |
cr | +0.088 |
Neg logit contributions | |
gly | -0.041 |
irl | -0.041 |
concert | -0.040 |
stage | -0.039 |
professor | -0.038 |
Token | he |
Token ID | 339 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
elt | +0.026 |
umbs | +0.024 |
OOOO | +0.024 |
ring | +0.024 |
Sur | +0.023 |
Neg logit contributions | |
stage | -0.016 |
professor | -0.016 |
gly | -0.015 |
concert | -0.015 |
irl | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
irl | -0.006 |
gly | -0.006 |
professor | -0.005 |
concert | -0.005 |
therapist | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
therapist | +0.004 |
tutor | +0.004 |
gly | +0.004 |
concert | +0.004 |
professor | +0.004 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.006 |
OOOO | -0.006 |
Sur | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -2.84e-05 |
Pos logit contributions | |
elt | +0.021 |
ring | +0.020 |
cr | +0.019 |
lette | +0.019 |
OOOO | +0.019 |
Neg logit contributions | |
irl | -0.012 |
gly | -0.012 |
therapist | -0.012 |
Hood | -0.011 |
tutor | -0.011 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
elt | +0.000 |
ring | +0.000 |
cr | +0.000 |
Sur | +0.000 |
lette | +0.000 |
Neg logit contributions | |
irl | -0.000 |
gly | -0.000 |
therapist | -0.000 |
concert | -0.000 |
Hood | -0.000 |
Token | into |
Token ID | 656 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
elt | +0.110 |
ring | +0.104 |
Sur | +0.102 |
lette | +0.101 |
cr | +0.100 |
Neg logit contributions | |
ls | -0.058 |
irl | -0.058 |
issa | -0.058 |
up | -0.057 |
gly | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
elt | +0.027 |
ring | +0.026 |
cr | +0.024 |
lette | +0.024 |
OOOO | +0.023 |
Neg logit contributions | |
stage | -0.016 |
issa | -0.016 |
aisle | -0.016 |
tutor | -0.016 |
irl | -0.015 |
Token | million |
Token ID | 1510 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.007 |
professor | +0.007 |
concert | +0.007 |
therapist | +0.007 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
elt | +0.216 |
ring | +0.203 |
cr | +0.201 |
Sur | +0.193 |
OOOO | +0.190 |
Neg logit contributions | |
gly | -0.233 |
irl | -0.228 |
professor | -0.223 |
concert | -0.222 |
tutor | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
elt | +0.084 |
ring | +0.079 |
cr | +0.078 |
Sur | +0.078 |
OOOO | +0.077 |
Neg logit contributions | |
gly | -0.038 |
irl | -0.038 |
concert | -0.036 |
professor | -0.036 |
tutor | -0.035 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
cr | +0.028 |
ring | +0.028 |
elt | +0.028 |
OOOO | +0.026 |
lette | +0.026 |
Neg logit contributions | |
gly | -0.027 |
tutor | -0.027 |
professor | -0.026 |
irl | -0.026 |
therapist | -0.026 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
elt | +0.029 |
ring | +0.027 |
cr | +0.026 |
Sur | +0.026 |
OOOO | +0.026 |
Neg logit contributions | |
gly | -0.026 |
professor | -0.025 |
irl | -0.025 |
concert | -0.025 |
acio | -0.024 |
Token | my |
Token ID | 1820 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.007 |
concert | +0.007 |
tutor | +0.007 |
Neg logit contributions | |
elt | -0.012 |
cr | -0.012 |
ring | -0.012 |
Sur | -0.011 |
OOOO | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
elt | +0.111 |
ring | +0.107 |
cr | +0.105 |
Sur | +0.102 |
OOOO | +0.101 |
Neg logit contributions | |
gly | -0.081 |
irl | -0.078 |
professor | -0.077 |
concert | -0.076 |
tutor | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
gly | +0.003 |
professor | +0.003 |
irl | +0.003 |
concert | +0.003 |
therapist | +0.003 |
Neg logit contributions | |
elt | -0.007 |
ring | -0.007 |
cr | -0.006 |
OOOO | -0.006 |
umbs | -0.006 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
elt | +0.022 |
ring | +0.021 |
umbs | +0.021 |
OOOO | +0.021 |
cr | +0.020 |
Neg logit contributions | |
gly | -0.009 |
therapist | -0.009 |
professor | -0.009 |
irl | -0.009 |
up | -0.008 |
Token | Bill |
Token ID | 3941 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
elt | +0.043 |
ring | +0.040 |
cr | +0.039 |
Sur | +0.037 |
OOOO | +0.037 |
Neg logit contributions | |
gly | -0.057 |
irl | -0.056 |
professor | -0.055 |
concert | -0.054 |
tutor | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
ring | +0.039 |
elt | +0.039 |
cr | +0.038 |
lette | +0.035 |
OOOO | +0.035 |
Neg logit contributions | |
irl | -0.041 |
gly | -0.040 |
concert | -0.038 |
professor | -0.038 |
therapist | -0.037 |
Token | million |
Token ID | 1510 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
gly | +0.003 |
professor | +0.003 |
tutor | +0.003 |
concert | +0.003 |
irl | +0.003 |
Neg logit contributions | |
elt | -0.004 |
ring | -0.004 |
cr | -0.004 |
OOOO | -0.004 |
lette | -0.004 |
Token | times |
Token ID | 1661 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
ring | +0.159 |
elt | +0.154 |
cr | +0.149 |
Sur | +0.148 |
umbs | +0.136 |
Neg logit contributions | |
irl | -0.269 |
gly | -0.268 |
acio | -0.253 |
professor | -0.252 |
concert | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
elt | +0.124 |
ring | +0.120 |
cr | +0.118 |
Sur | +0.113 |
OOOO | +0.112 |
Neg logit contributions | |
gly | -0.083 |
irl | -0.082 |
concert | -0.078 |
professor | -0.077 |
therapist | -0.075 |
Token | He |
Token ID | 679 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
ring | +0.028 |
cr | +0.027 |
elt | +0.027 |
OOOO | +0.025 |
lette | +0.025 |
Neg logit contributions | |
gly | -0.022 |
professor | -0.022 |
tutor | -0.020 |
irl | -0.020 |
acio | -0.020 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
elt | +0.007 |
ring | +0.006 |
cr | +0.006 |
Sur | +0.006 |
OOOO | +0.006 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
professor | -0.006 |
concert | -0.005 |
tutor | -0.005 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
gly | +0.016 |
professor | +0.016 |
therapist | +0.015 |
tutor | +0.015 |
concert | +0.015 |
Neg logit contributions | |
elt | -0.019 |
ring | -0.018 |
cr | -0.018 |
Sur | -0.017 |
lette | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -8.23e-03 |
Pos logit contributions | |
cr | +0.021 |
elt | +0.020 |
ring | +0.020 |
lette | +0.019 |
OOOO | +0.019 |
Neg logit contributions | |
gly | -0.020 |
irl | -0.020 |
tutor | -0.020 |
concert | -0.019 |
professor | -0.019 |
Token | ornament |
Token ID | 45618 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.015 |
cr | +0.015 |
Sur | +0.015 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.011 |
irl | -0.011 |
professor | -0.010 |
concert | -0.010 |
tutor | -0.010 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
elt | +0.030 |
ring | +0.028 |
cr | +0.028 |
Sur | +0.028 |
OOOO | +0.027 |
Neg logit contributions | |
gly | -0.025 |
irl | -0.025 |
concert | -0.024 |
therapist | -0.024 |
professor | -0.024 |
Token | into |
Token ID | 656 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
elt | +0.113 |
Sur | +0.106 |
lette | +0.106 |
ring | +0.105 |
cr | +0.105 |
Neg logit contributions | |
irl | -0.058 |
gly | -0.058 |
ls | -0.057 |
up | -0.057 |
issa | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.025 |
lette | +0.024 |
cr | +0.023 |
OOOO | +0.023 |
Neg logit contributions | |
stage | -0.015 |
issa | -0.014 |
aisle | -0.014 |
tutor | -0.014 |
case | -0.014 |
Token | million |
Token ID | 1510 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
irl | +0.008 |
gly | +0.008 |
concert | +0.008 |
tutor | +0.008 |
professor | +0.008 |
Neg logit contributions | |
elt | -0.010 |
ring | -0.009 |
cr | -0.009 |
OOOO | -0.009 |
lette | -0.009 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
elt | +0.240 |
cr | +0.224 |
ring | +0.223 |
OOOO | +0.215 |
Sur | +0.213 |
Neg logit contributions | |
irl | -0.204 |
gly | -0.204 |
concert | -0.193 |
professor | -0.192 |
ls | -0.192 |
Token | and |
Token ID | 290 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
elt | +0.078 |
ring | +0.073 |
cr | +0.073 |
Sur | +0.072 |
OOOO | +0.072 |
Neg logit contributions | |
gly | -0.043 |
irl | -0.043 |
concert | -0.041 |
professor | -0.040 |
tutor | -0.040 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
elt | +0.021 |
ring | +0.020 |
OOOO | +0.019 |
cr | +0.019 |
lette | +0.019 |
Neg logit contributions | |
irl | -0.010 |
gly | -0.010 |
therapist | -0.010 |
concert | -0.010 |
tutor | -0.010 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
irl | +0.009 |
gly | +0.009 |
therapist | +0.009 |
concert | +0.008 |
issa | +0.008 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
OOOO | -0.013 |
Sur | -0.013 |
Token | really |
Token ID | 1107 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
elt | +0.046 |
ring | +0.044 |
cr | +0.043 |
OOOO | +0.043 |
Sur | +0.042 |
Neg logit contributions | |
irl | -0.023 |
gly | -0.022 |
professor | -0.021 |
tutor | -0.021 |
concert | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
elt | +0.039 |
cr | +0.036 |
ring | +0.036 |
Sur | +0.036 |
OOOO | +0.036 |
Neg logit contributions | |
concert | -0.020 |
gly | -0.020 |
tutor | -0.020 |
professor | -0.020 |
irl | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
umbs | +0.021 |
cr | +0.021 |
lette | +0.021 |
Neg logit contributions | |
irl | -0.010 |
therapist | -0.010 |
gly | -0.010 |
issa | -0.009 |
stage | -0.009 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.004 |
cr | +0.004 |
lette | +0.004 |
OOOO | +0.004 |
Neg logit contributions | |
irl | -0.004 |
gly | -0.004 |
therapist | -0.004 |
concert | -0.004 |
ls | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
elt | +0.113 |
ring | +0.106 |
Sur | +0.105 |
cr | +0.105 |
lette | +0.104 |
Neg logit contributions | |
irl | -0.058 |
gly | -0.057 |
issa | -0.057 |
ls | -0.057 |
up | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
elt | +0.026 |
ring | +0.025 |
cr | +0.024 |
lette | +0.024 |
OOOO | +0.023 |
Neg logit contributions | |
issa | -0.016 |
aisle | -0.016 |
stage | -0.016 |
tutor | -0.015 |
professor | -0.015 |
Token | million |
Token ID | 1510 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gly | +0.005 |
irl | +0.005 |
concert | +0.004 |
professor | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.004 |
ring | -0.004 |
cr | -0.004 |
OOOO | -0.004 |
Sur | -0.004 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
elt | +0.228 |
ring | +0.215 |
cr | +0.213 |
Sur | +0.203 |
OOOO | +0.202 |
Neg logit contributions | |
gly | -0.217 |
irl | -0.215 |
concert | -0.208 |
professor | -0.207 |
tutor | -0.205 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
elt | +0.085 |
ring | +0.080 |
cr | +0.080 |
Sur | +0.078 |
OOOO | +0.077 |
Neg logit contributions | |
gly | -0.042 |
irl | -0.041 |
professor | -0.039 |
concert | -0.039 |
tutor | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ring | +0.038 |
cr | +0.037 |
elt | +0.037 |
lette | +0.035 |
OOOO | +0.035 |
Neg logit contributions | |
gly | -0.028 |
tutor | -0.028 |
Holly | -0.027 |
professor | -0.027 |
therapist | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
elt | +0.036 |
ring | +0.034 |
cr | +0.034 |
Sur | +0.033 |
OOOO | +0.032 |
Neg logit contributions | |
gly | -0.032 |
irl | -0.031 |
professor | -0.030 |
concert | -0.030 |
tutor | -0.030 |
Token | L |
Token ID | 43 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
elt | +0.036 |
cr | +0.035 |
ring | +0.034 |
lette | +0.032 |
OOOO | +0.032 |
Neg logit contributions | |
irl | -0.033 |
gly | -0.032 |
tutor | -0.031 |
concert | -0.031 |
therapist | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
elt | +0.020 |
Sur | +0.019 |
OOOO | +0.019 |
ring | +0.019 |
cr | +0.019 |
Neg logit contributions | |
irl | -0.008 |
therapist | -0.008 |
aisle | -0.008 |
gly | -0.008 |
concert | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +7.48e-03 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.003 |
cr | +0.003 |
OOOO | +0.003 |
Sur | +0.003 |
Neg logit contributions | |
irl | -0.003 |
gly | -0.002 |
concert | -0.002 |
professor | -0.002 |
therapist | -0.002 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
irl | +0.010 |
gly | +0.010 |
concert | +0.009 |
professor | +0.009 |
therapist | +0.009 |
Neg logit contributions | |
elt | -0.015 |
ring | -0.014 |
cr | -0.014 |
Sur | -0.013 |
OOOO | -0.013 |
Token | into |
Token ID | 656 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
elt | +0.117 |
ring | +0.110 |
cr | +0.109 |
Sur | +0.108 |
OOOO | +0.106 |
Neg logit contributions | |
gly | -0.052 |
irl | -0.051 |
issa | -0.050 |
ls | -0.047 |
stage | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
elt | +0.029 |
ring | +0.028 |
cr | +0.027 |
lette | +0.026 |
OOOO | +0.026 |
Neg logit contributions | |
stage | -0.019 |
issa | -0.018 |
aisle | -0.018 |
gly | -0.018 |
tutor | -0.018 |
Token | million |
Token ID | 1510 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gly | +0.013 |
irl | +0.013 |
concert | +0.013 |
professor | +0.012 |
tutor | +0.012 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
OOOO | -0.012 |
Sur | -0.012 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
elt | +0.240 |
ring | +0.226 |
cr | +0.226 |
OOOO | +0.215 |
Sur | +0.213 |
Neg logit contributions | |
irl | -0.203 |
gly | -0.202 |
concert | -0.195 |
tutor | -0.190 |
professor | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | -9.82e-03 |
Pos logit contributions | |
elt | +0.074 |
ring | +0.069 |
Sur | +0.068 |
cr | +0.068 |
OOOO | +0.068 |
Neg logit contributions | |
gly | -0.033 |
irl | -0.033 |
concert | -0.032 |
tutor | -0.031 |
professor | -0.031 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
ring | +0.018 |
elt | +0.017 |
cr | +0.017 |
OOOO | +0.016 |
lette | +0.016 |
Neg logit contributions | |
gly | -0.014 |
tutor | -0.013 |
professor | -0.013 |
Holly | -0.013 |
therapist | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
gly | +0.015 |
irl | +0.015 |
professor | +0.014 |
concert | +0.014 |
tutor | +0.014 |
Neg logit contributions | |
elt | -0.017 |
ring | -0.016 |
cr | -0.015 |
Sur | -0.015 |
OOOO | -0.015 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
elt | +0.057 |
ring | +0.054 |
cr | +0.053 |
Sur | +0.051 |
OOOO | +0.051 |
Neg logit contributions | |
gly | -0.043 |
irl | -0.042 |
professor | -0.041 |
concert | -0.040 |
therapist | -0.040 |
Token | pocket |
Token ID | 10000 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
elt | +0.065 |
cr | +0.062 |
ring | +0.062 |
Sur | +0.060 |
OOOO | +0.059 |
Neg logit contributions | |
gly | -0.049 |
irl | -0.048 |
tutor | -0.048 |
professor | -0.048 |
concert | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
gly | +0.019 |
irl | +0.018 |
concert | +0.018 |
professor | +0.018 |
therapist | +0.017 |
Neg logit contributions | |
elt | -0.037 |
ring | -0.035 |
cr | -0.035 |
Sur | -0.034 |
OOOO | -0.034 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
elt | +0.028 |
ring | +0.027 |
umbs | +0.027 |
cr | +0.026 |
OOOO | +0.026 |
Neg logit contributions | |
gly | -0.016 |
concert | -0.016 |
tutor | -0.015 |
therapist | -0.015 |
Hood | -0.015 |
Token | into |
Token ID | 656 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
elt | +0.117 |
ring | +0.112 |
Sur | +0.109 |
cr | +0.109 |
OOOO | +0.106 |
Neg logit contributions | |
gly | -0.054 |
irl | -0.052 |
ls | -0.048 |
professor | -0.048 |
therapist | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
elt | +0.020 |
ring | +0.019 |
cr | +0.018 |
lette | +0.017 |
OOOO | +0.017 |
Neg logit contributions | |
gly | -0.015 |
irl | -0.014 |
professor | -0.014 |
stage | -0.014 |
issa | -0.014 |
Token | million |
Token ID | 1510 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gly | +0.006 |
irl | +0.006 |
professor | +0.005 |
concert | +0.005 |
therapist | +0.005 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.006 |
Sur | -0.006 |
OOOO | -0.006 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
elt | +0.200 |
ring | +0.187 |
cr | +0.185 |
Sur | +0.180 |
OOOO | +0.173 |
Neg logit contributions | |
gly | -0.246 |
irl | -0.240 |
professor | -0.238 |
concert | -0.235 |
tutor | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
elt | +0.082 |
ring | +0.078 |
cr | +0.077 |
Sur | +0.075 |
OOOO | +0.074 |
Neg logit contributions | |
gly | -0.045 |
irl | -0.044 |
professor | -0.042 |
concert | -0.042 |
therapist | -0.041 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
ring | +0.036 |
cr | +0.033 |
lette | +0.032 |
elt | +0.031 |
eighteen | +0.030 |
Neg logit contributions | |
gly | -0.031 |
tutor | -0.028 |
aisle | -0.027 |
Holly | -0.027 |
professor | -0.027 |
Token | my |
Token ID | 1820 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
professor | -0.006 |
concert | -0.006 |
tutor | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
gly | +0.028 |
irl | +0.028 |
professor | +0.027 |
concert | +0.027 |
tutor | +0.026 |
Neg logit contributions | |
elt | -0.040 |
ring | -0.038 |
cr | -0.038 |
Sur | -0.036 |
OOOO | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
elt | +0.005 |
ring | +0.005 |
cr | +0.005 |
Sur | +0.005 |
OOOO | +0.005 |
Neg logit contributions | |
gly | -0.003 |
irl | -0.003 |
professor | -0.003 |
concert | -0.003 |
tutor | -0.003 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
cr | +0.028 |
ring | +0.027 |
lette | +0.025 |
elt | +0.024 |
pulp | +0.024 |
Neg logit contributions | |
professor | -0.022 |
tutor | -0.021 |
aisle | -0.021 |
gly | -0.021 |
Ross | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
elt | +0.035 |
ring | +0.034 |
cr | +0.034 |
umbs | +0.033 |
OOOO | +0.032 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.016 |
concert | -0.015 |
professor | -0.015 |
therapist | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
elt | +0.006 |
ring | +0.005 |
cr | +0.005 |
umbs | +0.005 |
OOOO | +0.005 |
Neg logit contributions | |
irl | -0.004 |
concert | -0.004 |
professor | -0.004 |
gly | -0.004 |
therapist | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
elt | +0.095 |
ring | +0.091 |
cr | +0.087 |
OOOO | +0.085 |
Sur | +0.085 |
Neg logit contributions | |
gly | -0.093 |
professor | -0.091 |
irl | -0.090 |
concert | -0.089 |
tutor | -0.088 |
Token | million |
Token ID | 1510 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.007 |
Hood | +0.007 |
therapist | +0.007 |
acio | +0.007 |
Neg logit contributions | |
elt | -0.008 |
Sur | -0.008 |
cr | -0.007 |
ring | -0.007 |
OOOO | -0.007 |
Token | stars |
Token ID | 5788 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
elt | +0.204 |
ring | +0.193 |
Sur | +0.188 |
cr | +0.187 |
OOOO | +0.176 |
Neg logit contributions | |
gly | -0.241 |
irl | -0.230 |
therapist | -0.226 |
professor | -0.223 |
concert | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
elt | +0.088 |
ring | +0.084 |
cr | +0.083 |
Sur | +0.081 |
OOOO | +0.080 |
Neg logit contributions | |
gly | -0.058 |
irl | -0.056 |
professor | -0.054 |
concert | -0.054 |
therapist | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
elt | +0.022 |
ring | +0.021 |
umbs | +0.021 |
OOOO | +0.021 |
cr | +0.021 |
Neg logit contributions | |
professor | -0.014 |
stage | -0.014 |
Sparkle | -0.014 |
concert | -0.014 |
irl | -0.013 |
Token | planets |
Token ID | 14705 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.003 |
cr | +0.003 |
Sur | +0.003 |
OOOO | +0.003 |
Neg logit contributions | |
gly | -0.003 |
irl | -0.003 |
professor | -0.003 |
therapist | -0.003 |
concert | -0.003 |
Token | tw |
Token ID | 665 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
elt | +0.085 |
ring | +0.081 |
cr | +0.080 |
Sur | +0.078 |
OOOO | +0.077 |
Neg logit contributions | |
gly | -0.058 |
irl | -0.057 |
professor | -0.055 |
concert | -0.055 |
tutor | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.007 |
concert | +0.006 |
professor | +0.006 |
tutor | +0.006 |
Neg logit contributions | |
elt | -0.010 |
ring | -0.009 |
cr | -0.009 |
Sur | -0.009 |
OOOO | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.015 |
cr | +0.015 |
lette | +0.015 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.011 |
irl | -0.011 |
concert | -0.010 |
therapist | -0.010 |
professor | -0.010 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
elt | +0.003 |
ring | +0.003 |
cr | +0.003 |
lette | +0.003 |
Sur | +0.003 |
Neg logit contributions | |
irl | -0.003 |
gly | -0.003 |
concert | -0.003 |
therapist | -0.003 |
professor | -0.003 |
Token | into |
Token ID | 656 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
elt | +0.111 |
ring | +0.104 |
cr | +0.103 |
Sur | +0.102 |
lette | +0.101 |
Neg logit contributions | |
gly | -0.059 |
irl | -0.059 |
issa | -0.056 |
professor | -0.056 |
Hood | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.022 |
cr | +0.022 |
lette | +0.021 |
seventeen | +0.020 |
Neg logit contributions | |
issa | -0.014 |
stage | -0.014 |
aisle | -0.014 |
tutor | -0.014 |
gly | -0.014 |
Token | million |
Token ID | 1510 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.006 |
professor | +0.006 |
concert | +0.006 |
tutor | +0.006 |
Neg logit contributions | |
elt | -0.007 |
ring | -0.007 |
cr | -0.007 |
Sur | -0.006 |
OOOO | -0.006 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
elt | +0.209 |
ring | +0.197 |
cr | +0.193 |
Sur | +0.187 |
OOOO | +0.183 |
Neg logit contributions | |
gly | -0.237 |
irl | -0.231 |
professor | -0.227 |
concert | -0.225 |
therapist | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
elt | +0.086 |
ring | +0.081 |
cr | +0.080 |
Sur | +0.080 |
OOOO | +0.078 |
Neg logit contributions | |
gly | -0.039 |
irl | -0.039 |
concert | -0.037 |
professor | -0.037 |
tutor | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
cr | +0.025 |
ring | +0.025 |
lette | +0.024 |
elt | +0.024 |
OOOO | +0.023 |
Neg logit contributions | |
tutor | -0.017 |
gly | -0.017 |
Holly | -0.017 |
professor | -0.016 |
Sparkle | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
elt | +0.018 |
Sur | +0.017 |
cr | +0.016 |
ring | +0.016 |
OOOO | +0.016 |
Neg logit contributions | |
gly | -0.022 |
irl | -0.022 |
concert | -0.022 |
professor | -0.022 |
therapist | -0.021 |
Token | L |
Token ID | 43 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
elt | +0.019 |
ring | +0.017 |
cr | +0.017 |
OOOO | +0.016 |
Sur | +0.016 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.022 |
professor | -0.022 |
concert | -0.022 |
tutor | -0.021 |
Token | v |
Token ID | 410 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
elt | +0.027 |
ring | +0.026 |
cr | +0.025 |
Sur | +0.024 |
OOOO | +0.024 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.023 |
professor | -0.022 |
concert | -0.022 |
tutor | -0.021 |
Token | ase |
Token ID | 589 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
elt | +0.009 |
cr | +0.009 |
ring | +0.009 |
Sur | +0.008 |
lette | +0.008 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
concert | -0.006 |
professor | -0.006 |
therapist | -0.006 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
elt | +0.034 |
cr | +0.032 |
ring | +0.032 |
lette | +0.031 |
OOOO | +0.031 |
Neg logit contributions | |
irl | -0.020 |
gly | -0.019 |
ls | -0.019 |
concert | -0.019 |
therapist | -0.019 |
Token | into |
Token ID | 656 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
elt | +0.110 |
Sur | +0.104 |
lette | +0.103 |
cr | +0.103 |
ring | +0.101 |
Neg logit contributions | |
up | -0.055 |
ls | -0.054 |
irl | -0.051 |
stage | -0.050 |
ela | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
elt | +0.025 |
ring | +0.023 |
cr | +0.022 |
lette | +0.022 |
OOOO | +0.021 |
Neg logit contributions | |
stage | -0.014 |
aisle | -0.014 |
issa | -0.014 |
case | -0.013 |
irl | -0.013 |
Token | million |
Token ID | 1510 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
gly | +0.006 |
irl | +0.006 |
concert | +0.006 |
professor | +0.006 |
tutor | +0.006 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.005 |
cr | -0.005 |
OOOO | -0.005 |
Sur | -0.005 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
elt | +0.240 |
cr | +0.225 |
ring | +0.224 |
OOOO | +0.214 |
Sur | +0.212 |
Neg logit contributions | |
gly | -0.201 |
irl | -0.201 |
concert | -0.193 |
professor | -0.190 |
ls | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
elt | +0.082 |
ring | +0.076 |
Sur | +0.076 |
cr | +0.076 |
OOOO | +0.075 |
Neg logit contributions | |
gly | -0.039 |
irl | -0.039 |
concert | -0.037 |
professor | -0.036 |
aisle | -0.035 |
Token | they |
Token ID | 484 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
elt | +0.019 |
ring | +0.018 |
OOOO | +0.018 |
lette | +0.018 |
cr | +0.018 |
Neg logit contributions | |
stage | -0.009 |
irl | -0.009 |
gly | -0.009 |
concert | -0.009 |
therapist | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
elt | +0.010 |
Sur | +0.009 |
ring | +0.009 |
cr | +0.009 |
OOOO | +0.009 |
Neg logit contributions | |
irl | -0.008 |
gly | -0.008 |
concert | -0.007 |
Hood | -0.007 |
issa | -0.007 |
Token | very |
Token ID | 845 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
elt | +0.084 |
cr | +0.081 |
ring | +0.078 |
Sur | +0.078 |
OOOO | +0.078 |
Neg logit contributions | |
irl | -0.040 |
gly | -0.039 |
concert | -0.039 |
tutor | -0.038 |
professor | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
concert | +0.075 |
tutor | +0.075 |
gly | +0.075 |
irl | +0.074 |
professor | +0.073 |
Neg logit contributions | |
elt | -0.086 |
ring | -0.084 |
cr | -0.082 |
Sur | -0.080 |
OOOO | -0.079 |
Token | spin |
Token ID | 7906 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
elt | +0.025 |
ring | +0.023 |
cr | +0.023 |
Sur | +0.023 |
OOOO | +0.022 |
Neg logit contributions | |
irl | -0.014 |
gly | -0.014 |
concert | -0.014 |
tutor | -0.013 |
professor | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
gly | +0.036 |
professor | +0.033 |
therapist | +0.033 |
tutor | +0.033 |
Hood | +0.032 |
Neg logit contributions | |
ring | -0.039 |
elt | -0.038 |
cr | -0.038 |
Sur | -0.036 |
OOOO | -0.033 |
Token | circles |
Token ID | 13332 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
gly | +0.039 |
therapist | +0.038 |
professor | +0.038 |
Hood | +0.037 |
irl | +0.037 |
Neg logit contributions | |
elt | -0.029 |
cr | -0.029 |
ring | -0.029 |
Sur | -0.028 |
OOOO | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-04 |
Pos logit contributions | |
ring | +0.016 |
elt | +0.015 |
cr | +0.015 |
Sur | +0.014 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.014 |
professor | -0.013 |
tutor | -0.012 |
irl | -0.012 |
concert | -0.012 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
cr | +0.001 |
elt | +0.001 |
ring | +0.001 |
Sur | +0.001 |
OOOO | +0.001 |
Neg logit contributions | |
gly | -0.001 |
tutor | -0.001 |
professor | -0.001 |
irl | -0.001 |
concert | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
gly | +0.118 |
irl | +0.116 |
professor | +0.113 |
concert | +0.111 |
tutor | +0.109 |
Neg logit contributions | |
elt | -0.161 |
ring | -0.149 |
cr | -0.149 |
Sur | -0.147 |
OOOO | -0.143 |
Token | went |
Token ID | 1816 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
gly | +0.018 |
tutor | +0.017 |
professor | +0.017 |
therapist | +0.017 |
irl | +0.017 |
Neg logit contributions | |
elt | -0.011 |
ring | -0.010 |
Sur | -0.009 |
cr | -0.009 |
OOOO | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
elt | +0.060 |
ring | +0.057 |
cr | +0.056 |
Sur | +0.055 |
OOOO | +0.054 |
Neg logit contributions | |
gly | -0.032 |
irl | -0.031 |
professor | -0.030 |
concert | -0.029 |
therapist | -0.029 |
Token | would |
Token ID | 561 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
gly | +0.016 |
tutor | +0.015 |
professor | +0.015 |
therapist | +0.015 |
Percy | +0.014 |
Neg logit contributions | |
elt | -0.011 |
ring | -0.011 |
cr | -0.010 |
Sur | -0.010 |
OOOO | -0.009 |
Token | spin |
Token ID | 7906 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
gly | +0.101 |
irl | +0.092 |
professor | +0.092 |
therapist | +0.091 |
tutor | +0.090 |
Neg logit contributions | |
elt | -0.119 |
ring | -0.117 |
cr | -0.114 |
Sur | -0.109 |
OOOO | -0.107 |
Token | seal |
Token ID | 13810 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
elt | +0.016 |
cr | +0.015 |
Sur | +0.015 |
ring | +0.015 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.017 |
irl | -0.016 |
professor | -0.016 |
issa | -0.015 |
therapist | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
gly | +0.011 |
irl | +0.011 |
concert | +0.011 |
professor | +0.011 |
therapist | +0.010 |
Neg logit contributions | |
elt | -0.013 |
ring | -0.013 |
cr | -0.012 |
Sur | -0.012 |
OOOO | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
gly | +0.012 |
tutor | +0.011 |
irl | +0.011 |
professor | +0.011 |
concert | +0.010 |
Neg logit contributions | |
elt | -0.028 |
ring | -0.028 |
cr | -0.027 |
umbs | -0.027 |
Sur | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
gly | +0.018 |
tutor | +0.018 |
professor | +0.018 |
Sparkle | +0.017 |
concert | +0.017 |
Neg logit contributions | |
elt | -0.023 |
ring | -0.022 |
cr | -0.022 |
umbs | -0.022 |
lette | -0.021 |
Token | Please |
Token ID | 5492 |
Feature activation | +9.40e-03 |
Pos logit contributions | |
gly | +0.002 |
therapist | +0.002 |
irl | +0.001 |
concert | +0.001 |
mun | +0.001 |
Neg logit contributions | |
elt | -0.002 |
ring | -0.002 |
cr | -0.002 |
umbs | -0.002 |
eighteen | -0.002 |
Token | forgive |
Token ID | 20927 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
gly | +0.015 |
therapist | +0.015 |
professor | +0.015 |
irl | +0.014 |
tutor | +0.014 |
Neg logit contributions | |
elt | -0.015 |
cr | -0.015 |
ring | -0.015 |
OOOO | -0.014 |
Sur | -0.014 |
Token | me |
Token ID | 502 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
gly | +0.090 |
irl | +0.087 |
concert | +0.083 |
professor | +0.079 |
tutor | +0.078 |
Neg logit contributions | |
elt | -0.206 |
ring | -0.196 |
cr | -0.191 |
Sur | -0.188 |
umbs | -0.186 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
gly | +0.017 |
irl | +0.016 |
concert | +0.016 |
tutor | +0.016 |
professor | +0.016 |
Neg logit contributions | |
elt | -0.033 |
ring | -0.031 |
cr | -0.031 |
Sur | -0.031 |
OOOO | -0.029 |
Token | I |
Token ID | 314 |
Feature activation | -8.24e-04 |
Pos logit contributions | |
gly | +0.015 |
concert | +0.015 |
irl | +0.014 |
tutor | +0.014 |
professor | +0.014 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.019 |
cr | -0.018 |
Sur | -0.018 |
lette | -0.018 |
Token | just |
Token ID | 655 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
elt | +0.001 |
cr | +0.001 |
ring | +0.001 |
OOOO | +0.001 |
Sur | +0.001 |
Neg logit contributions | |
gly | -0.001 |
professor | -0.001 |
therapist | -0.001 |
aisle | -0.001 |
issa | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
elt | +0.023 |
umbs | +0.022 |
Sur | +0.022 |
ring | +0.021 |
cr | +0.021 |
Neg logit contributions | |
irl | -0.018 |
gly | -0.016 |
concert | -0.016 |
tutor | -0.015 |
professor | -0.015 |
Token | liked |
Token ID | 8288 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
gly | +0.018 |
concert | +0.018 |
professor | +0.018 |
tutor | +0.018 |
irl | +0.018 |
Neg logit contributions | |
elt | -0.015 |
cr | -0.013 |
ring | -0.013 |
Sur | -0.013 |
OOOO | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -4.77e-03 |
Pos logit contributions | |
tutor | +0.059 |
concert | +0.059 |
gly | +0.059 |
irl | +0.057 |
professor | +0.057 |
Neg logit contributions | |
elt | -0.073 |
ring | -0.072 |
cr | -0.071 |
Sur | -0.068 |
OOOO | -0.068 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
elt | +0.009 |
ring | +0.009 |
cr | +0.009 |
Sur | +0.008 |
OOOO | +0.008 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
professor | -0.006 |
concert | -0.006 |
therapist | -0.006 |
Token | math |
Token ID | 10688 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
elt | +0.016 |
cr | +0.016 |
ring | +0.015 |
Sur | +0.015 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.018 |
irl | -0.017 |
professor | -0.017 |
concert | -0.017 |
therapist | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
gly | +0.070 |
irl | +0.067 |
therapist | +0.065 |
concert | +0.064 |
acio | +0.064 |
Neg logit contributions | |
cr | -0.078 |
elt | -0.077 |
Sur | -0.075 |
ring | -0.075 |
eighteen | -0.071 |
Token | Every |
Token ID | 3887 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.008 |
tutor | +0.008 |
concert | +0.007 |
Neg logit contributions | |
elt | -0.016 |
ring | -0.016 |
cr | -0.016 |
Sur | -0.016 |
OOOO | -0.015 |
Token | night |
Token ID | 1755 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
gly | +0.141 |
ls | +0.133 |
acio | +0.133 |
mun | +0.130 |
irl | +0.129 |
Neg logit contributions | |
elt | -0.150 |
ring | -0.141 |
OOOO | -0.139 |
cr | -0.137 |
Sur | -0.135 |
Token | he |
Token ID | 339 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
elt | +0.019 |
ring | +0.019 |
cr | +0.019 |
umbs | +0.019 |
ige | +0.018 |
Neg logit contributions | |
gly | -0.006 |
professor | -0.006 |
therapist | -0.006 |
concert | -0.006 |
tutor | -0.006 |
Token | went |
Token ID | 1816 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
gly | +0.018 |
irl | +0.017 |
concert | +0.017 |
professor | +0.017 |
therapist | +0.017 |
Neg logit contributions | |
elt | -0.024 |
ring | -0.023 |
cr | -0.022 |
Sur | -0.021 |
OOOO | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -8.88e-03 |
Pos logit contributions | |
elt | +0.031 |
ring | +0.027 |
cr | +0.022 |
Sur | +0.022 |
OOOO | +0.021 |
Neg logit contributions | |
gly | -0.063 |
irl | -0.059 |
mun | -0.056 |
ricia | -0.055 |
therapist | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.016 |
cr | +0.016 |
OOOO | +0.015 |
Sur | +0.015 |
Neg logit contributions | |
gly | -0.012 |
irl | -0.011 |
therapist | -0.011 |
professor | -0.011 |
ls | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
gly | +0.004 |
irl | +0.004 |
concert | +0.004 |
professor | +0.004 |
tutor | +0.004 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.005 |
cr | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
elt | +0.020 |
ring | +0.019 |
cr | +0.019 |
Sur | +0.018 |
OOOO | +0.018 |
Neg logit contributions | |
gly | -0.018 |
irl | -0.017 |
concert | -0.017 |
professor | -0.017 |
tutor | -0.017 |
Token | always |
Token ID | 1464 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.008 |
tutor | +0.008 |
concert | +0.008 |
Neg logit contributions | |
elt | -0.008 |
ring | -0.008 |
cr | -0.008 |
Sur | -0.008 |
OOOO | -0.007 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
elt | +0.037 |
umbs | +0.036 |
ring | +0.035 |
Sur | +0.035 |
cr | +0.034 |
Neg logit contributions | |
gly | -0.028 |
irl | -0.028 |
concert | -0.027 |
professor | -0.027 |
therapist | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
elt | +0.028 |
ring | +0.027 |
cr | +0.026 |
Sur | +0.026 |
OOOO | +0.025 |
Neg logit contributions | |
gly | -0.021 |
irl | -0.021 |
professor | -0.020 |
concert | -0.020 |
tutor | -0.020 |
Token | trust |
Token ID | 3774 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
elt | +0.015 |
ring | +0.015 |
cr | +0.014 |
Sur | +0.014 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.013 |
irl | -0.012 |
professor | -0.012 |
concert | -0.012 |
therapist | -0.012 |
Token | y |
Token ID | 88 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
irl | +0.126 |
gly | +0.125 |
concert | +0.120 |
professor | +0.118 |
tutor | +0.113 |
Neg logit contributions | |
elt | -0.156 |
ring | -0.151 |
cr | -0.148 |
lette | -0.137 |
OOOO | -0.137 |
Token | brush |
Token ID | 14093 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
elt | +0.085 |
ring | +0.080 |
cr | +0.080 |
Sur | +0.077 |
OOOO | +0.077 |
Neg logit contributions | |
gly | -0.060 |
irl | -0.059 |
professor | -0.057 |
tutor | -0.057 |
concert | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
gly | +0.045 |
irl | +0.044 |
professor | +0.043 |
concert | +0.043 |
tutor | +0.042 |
Neg logit contributions | |
elt | -0.065 |
ring | -0.062 |
cr | -0.061 |
Sur | -0.059 |
OOOO | -0.058 |
Token | her |
Token ID | 607 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
professor | +0.047 |
gly | +0.046 |
irl | +0.046 |
concert | +0.045 |
therapist | +0.045 |
Neg logit contributions | |
elt | -0.052 |
cr | -0.052 |
ring | -0.051 |
Sur | -0.049 |
lette | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
elt | +0.017 |
ring | +0.016 |
cr | +0.016 |
Sur | +0.015 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.012 |
irl | -0.011 |
concert | -0.011 |
professor | -0.011 |
therapist | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
gly | +0.010 |
irl | +0.010 |
tutor | +0.010 |
concert | +0.010 |
professor | +0.010 |
Neg logit contributions | |
elt | -0.018 |
Sur | -0.017 |
ring | -0.017 |
cr | -0.017 |
OOOO | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
irl | +0.026 |
gly | +0.025 |
concert | +0.025 |
professor | +0.025 |
stage | +0.024 |
Neg logit contributions | |
elt | -0.042 |
ring | -0.040 |
cr | -0.039 |
Sur | -0.038 |
OOOO | -0.038 |
Token | yellow |
Token ID | 7872 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
stage | +0.038 |
professor | +0.034 |
shop | +0.034 |
Hood | +0.034 |
show | +0.032 |
Neg logit contributions | |
elt | -0.089 |
cr | -0.087 |
OOOO | -0.084 |
ring | -0.082 |
umbs | -0.081 |
Token | wheels |
Token ID | 13666 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
stage | +0.017 |
aisle | +0.016 |
concert | +0.015 |
irl | +0.015 |
poster | +0.015 |
Neg logit contributions | |
cr | -0.027 |
elt | -0.025 |
OOOO | -0.025 |
lette | -0.025 |
ring | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
elt | +0.046 |
Sur | +0.044 |
cr | +0.044 |
OOOO | +0.043 |
ring | +0.043 |
Neg logit contributions | |
gly | -0.018 |
irl | -0.018 |
concert | -0.017 |
professor | -0.017 |
aisle | -0.016 |
Token | Every |
Token ID | 3887 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
gly | +0.005 |
tutor | +0.005 |
professor | +0.005 |
stage | +0.005 |
Sparkle | +0.005 |
Neg logit contributions | |
elt | -0.006 |
ring | -0.006 |
cr | -0.006 |
OOOO | -0.006 |
lette | -0.006 |
Token | morning |
Token ID | 3329 |
Feature activation | +3.36e-04 |
Pos logit contributions | |
gly | +0.103 |
irl | +0.098 |
professor | +0.095 |
therapist | +0.091 |
concert | +0.091 |
Neg logit contributions | |
elt | -0.189 |
ring | -0.181 |
cr | -0.179 |
OOOO | -0.175 |
Sur | -0.175 |
Token | it |
Token ID | 340 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
stage | +0.000 |
concert | +0.000 |
festival | +0.000 |
therapist | +0.000 |
aisle | +0.000 |
Neg logit contributions | |
elt | -0.001 |
cr | -0.001 |
ring | -0.001 |
umbs | -0.001 |
lette | -0.001 |
Token | would |
Token ID | 561 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
concert | +0.008 |
professor | +0.008 |
therapist | +0.008 |
Neg logit contributions | |
elt | -0.015 |
ring | -0.014 |
cr | -0.014 |
Sur | -0.014 |
OOOO | -0.013 |
Token | go |
Token ID | 467 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
irl | +0.103 |
concert | +0.100 |
gly | +0.097 |
professor | +0.097 |
tutor | +0.095 |
Neg logit contributions | |
elt | -0.142 |
cr | -0.130 |
Sur | -0.128 |
ring | -0.127 |
OOOO | -0.126 |
Token | split |
Token ID | 6626 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.013 |
cr | +0.011 |
OOOO | +0.011 |
Sur | +0.011 |
Neg logit contributions | |
gly | -0.016 |
therapist | -0.015 |
irl | -0.015 |
ricia | -0.014 |
tutor | -0.014 |
Token | them |
Token ID | 606 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
elt | +0.046 |
cr | +0.045 |
ring | +0.043 |
Sur | +0.043 |
OOOO | +0.042 |
Neg logit contributions | |
therapist | -0.045 |
professor | -0.043 |
gly | -0.042 |
tutor | -0.042 |
irl | -0.042 |
Token | came |
Token ID | 1625 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
elt | +0.015 |
ring | +0.015 |
cr | +0.014 |
Sur | +0.014 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.016 |
irl | -0.016 |
professor | -0.016 |
concert | -0.016 |
tutor | -0.016 |
Token | close |
Token ID | 1969 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
elt | +0.113 |
cr | +0.107 |
ring | +0.106 |
OOOO | +0.098 |
Sur | +0.096 |
Neg logit contributions | |
gly | -0.120 |
concert | -0.114 |
therapist | -0.114 |
irl | -0.114 |
issa | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
gly | +0.021 |
irl | +0.020 |
concert | +0.020 |
therapist | +0.019 |
professor | +0.019 |
Neg logit contributions | |
elt | -0.020 |
ring | -0.019 |
cr | -0.018 |
OOOO | -0.017 |
Sur | -0.017 |
Token | Finally |
Token ID | 9461 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ring | +0.003 |
elt | +0.003 |
cr | +0.003 |
lette | +0.002 |
OOOO | +0.002 |
Neg logit contributions | |
gly | -0.003 |
tutor | -0.002 |
professor | -0.002 |
irl | -0.002 |
Holly | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
gly | +0.015 |
professor | +0.015 |
irl | +0.015 |
concert | +0.015 |
therapist | +0.015 |
Neg logit contributions | |
elt | -0.026 |
cr | -0.024 |
ring | -0.024 |
Sur | -0.024 |
OOOO | -0.023 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
gly | +0.025 |
irl | +0.024 |
professor | +0.024 |
concert | +0.024 |
therapist | +0.023 |
Neg logit contributions | |
elt | -0.031 |
cr | -0.029 |
ring | -0.029 |
Sur | -0.028 |
OOOO | -0.028 |
Token | got |
Token ID | 1392 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
gly | +0.027 |
irl | +0.027 |
professor | +0.026 |
concert | +0.026 |
tutor | +0.026 |
Neg logit contributions | |
elt | -0.032 |
ring | -0.030 |
cr | -0.030 |
Sur | -0.029 |
OOOO | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -8.26e-03 |
Pos logit contributions | |
elt | +0.058 |
cr | +0.055 |
ring | +0.050 |
Sur | +0.049 |
lette | +0.047 |
Neg logit contributions | |
gly | -0.066 |
concert | -0.064 |
professor | -0.062 |
irl | -0.062 |
therapist | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.016 |
cr | +0.015 |
Sur | +0.015 |
OOOO | +0.015 |
Neg logit contributions | |
gly | -0.011 |
irl | -0.011 |
concert | -0.010 |
professor | -0.010 |
tutor | -0.010 |
Token | flag |
Token ID | 6056 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
concert | +0.015 |
poster | +0.015 |
irl | +0.015 |
stage | +0.015 |
professor | +0.015 |
Neg logit contributions | |
elt | -0.021 |
ring | -0.020 |
cr | -0.020 |
umbs | -0.019 |
OOOO | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
irl | +0.061 |
gly | +0.061 |
professor | +0.057 |
tutor | +0.057 |
therapist | +0.056 |
Neg logit contributions | |
elt | -0.087 |
ring | -0.085 |
cr | -0.082 |
Sur | -0.079 |
OOOO | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
elt | +0.006 |
cr | +0.005 |
Sur | +0.005 |
ring | +0.005 |
OOOO | +0.005 |
Neg logit contributions | |
gly | -0.007 |
irl | -0.007 |
concert | -0.006 |
professor | -0.006 |
therapist | -0.006 |
Token | L |
Token ID | 43 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
elt | +0.008 |
ring | +0.008 |
cr | +0.007 |
OOOO | +0.007 |
umbs | +0.007 |
Neg logit contributions | |
irl | -0.008 |
gly | -0.008 |
concert | -0.008 |
professor | -0.008 |
tutor | -0.008 |
Token | ily |
Token ID | 813 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
elt | +0.013 |
ring | +0.012 |
cr | +0.012 |
Sur | +0.011 |
OOOO | +0.011 |
Neg logit contributions | |
gly | -0.019 |
irl | -0.019 |
professor | -0.018 |
concert | -0.018 |
therapist | -0.018 |
Token | worked |
Token ID | 3111 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
elt | +0.056 |
ring | +0.053 |
cr | +0.052 |
Sur | +0.050 |
OOOO | +0.049 |
Neg logit contributions | |
gly | -0.055 |
irl | -0.053 |
professor | -0.053 |
concert | -0.052 |
tutor | -0.051 |
Token | hard |
Token ID | 1327 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
gly | +0.048 |
concert | +0.048 |
therapist | +0.046 |
professor | +0.045 |
irl | +0.045 |
Neg logit contributions | |
elt | -0.062 |
cr | -0.059 |
ring | -0.058 |
Sur | -0.057 |
eighteen | -0.055 |
Token | in |
Token ID | 287 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
gly | +0.095 |
irl | +0.092 |
concert | +0.089 |
professor | +0.089 |
therapist | +0.088 |
Neg logit contributions | |
elt | -0.107 |
ring | -0.102 |
cr | -0.099 |
Sur | -0.095 |
OOOO | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-04 |
Pos logit contributions | |
gly | +0.022 |
irl | +0.021 |
professor | +0.021 |
concert | +0.021 |
tutor | +0.020 |
Neg logit contributions | |
elt | -0.030 |
ring | -0.028 |
cr | -0.028 |
Sur | -0.027 |
OOOO | -0.027 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
elt | +0.002 |
Sur | +0.002 |
ring | +0.002 |
cr | +0.002 |
lette | +0.002 |
Neg logit contributions | |
gly | -0.001 |
irl | -0.001 |
professor | -0.001 |
ela | -0.001 |
concert | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
elt | +0.030 |
ring | +0.029 |
Sur | +0.028 |
cr | +0.028 |
OOOO | +0.027 |
Neg logit contributions | |
tutor | -0.014 |
aisle | -0.014 |
gly | -0.014 |
professor | -0.014 |
stage | -0.014 |
Token | made |
Token ID | 925 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
elt | +0.020 |
ring | +0.019 |
cr | +0.018 |
Sur | +0.018 |
OOOO | +0.018 |
Neg logit contributions | |
gly | -0.016 |
irl | -0.016 |
concert | -0.015 |
professor | -0.015 |
therapist | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
elt | +0.044 |
ring | +0.042 |
Sur | +0.041 |
cr | +0.041 |
OOOO | +0.040 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.023 |
therapist | -0.022 |
concert | -0.022 |
professor | -0.022 |
Token | Just |
Token ID | 2329 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
elt | +0.010 |
ring | +0.010 |
cr | +0.009 |
Sur | +0.009 |
OOOO | +0.009 |
Neg logit contributions | |
gly | -0.009 |
professor | -0.009 |
irl | -0.009 |
therapist | -0.009 |
tutor | -0.009 |
Token | when |
Token ID | 618 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
elt | +0.015 |
Sur | +0.014 |
umbs | +0.014 |
OOOO | +0.013 |
ring | +0.013 |
Neg logit contributions | |
irl | -0.011 |
gly | -0.011 |
concert | -0.010 |
Sparkle | -0.010 |
therapist | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
elt | +0.007 |
ring | +0.007 |
cr | +0.006 |
Sur | +0.006 |
OOOO | +0.006 |
Neg logit contributions | |
gly | -0.005 |
irl | -0.005 |
professor | -0.005 |
concert | -0.005 |
tutor | -0.005 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
gly | +0.005 |
tutor | +0.005 |
professor | +0.005 |
concert | +0.005 |
irl | +0.005 |
Neg logit contributions | |
elt | -0.005 |
ring | -0.005 |
cr | -0.004 |
Sur | -0.004 |
OOOO | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +6.25e-03 |
Pos logit contributions | |
gly | +0.046 |
irl | +0.046 |
concert | +0.045 |
professor | +0.045 |
tutor | +0.043 |
Neg logit contributions | |
elt | -0.061 |
ring | -0.059 |
cr | -0.058 |
OOOO | -0.056 |
Sur | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
concert | +0.012 |
tutor | +0.012 |
irl | +0.011 |
gly | +0.011 |
professor | +0.011 |
Neg logit contributions | |
elt | -0.009 |
ring | -0.008 |
cr | -0.008 |
Sur | -0.008 |
lette | -0.007 |
Token | going |
Token ID | 1016 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
gly | +0.011 |
irl | +0.011 |
professor | +0.011 |
concert | +0.010 |
tutor | +0.010 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
Sur | -0.012 |
OOOO | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
elt | +0.051 |
cr | +0.047 |
ring | +0.046 |
lette | +0.040 |
OOOO | +0.040 |
Neg logit contributions | |
gly | -0.069 |
irl | -0.067 |
concert | -0.065 |
mun | -0.064 |
issa | -0.064 |
Token | be |
Token ID | 307 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
elt | +0.018 |
ring | +0.017 |
cr | +0.016 |
Sur | +0.016 |
OOOO | +0.016 |
Neg logit contributions | |
irl | -0.012 |
gly | -0.012 |
concert | -0.012 |
professor | -0.012 |
tutor | -0.012 |
Token | swept |
Token ID | 17676 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
elt | +0.041 |
ring | +0.039 |
cr | +0.038 |
Sur | +0.037 |
OOOO | +0.037 |
Neg logit contributions | |
irl | -0.036 |
gly | -0.036 |
professor | -0.035 |
concert | -0.035 |
therapist | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
elt | +0.025 |
ring | +0.025 |
cr | +0.024 |
Sur | +0.023 |
OOOO | +0.023 |
Neg logit contributions | |
irl | -0.019 |
gly | -0.019 |
concert | -0.018 |
professor | -0.017 |
therapist | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
elt | +0.010 |
ring | +0.009 |
cr | +0.009 |
OOOO | +0.009 |
Sur | +0.009 |
Neg logit contributions | |
gly | -0.007 |
professor | -0.007 |
irl | -0.007 |
tutor | -0.007 |
therapist | -0.007 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
elt | +0.015 |
ring | +0.015 |
cr | +0.014 |
Sur | +0.014 |
OOOO | +0.014 |
Neg logit contributions | |
gly | -0.013 |
irl | -0.013 |
professor | -0.013 |
concert | -0.013 |
tutor | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
elt | +0.056 |
ring | +0.054 |
cr | +0.053 |
Sur | +0.051 |
OOOO | +0.050 |
Neg logit contributions | |
gly | -0.041 |
irl | -0.040 |
professor | -0.039 |
concert | -0.039 |
tutor | -0.038 |
Token | too |
Token ID | 1165 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.008 |
concert | +0.008 |
therapist | +0.007 |
Neg logit contributions | |
elt | -0.009 |
ring | -0.008 |
cr | -0.008 |
Sur | -0.008 |
OOOO | -0.008 |
Token | afraid |
Token ID | 7787 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
irl | +0.056 |
gly | +0.056 |
professor | +0.053 |
tutor | +0.052 |
concert | +0.052 |
Neg logit contributions | |
elt | -0.093 |
ring | -0.089 |
cr | -0.088 |
Sur | -0.085 |
OOOO | -0.084 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
gly | +0.002 |
professor | +0.002 |
irl | +0.002 |
concert | +0.002 |
tutor | +0.002 |
Neg logit contributions | |
elt | -0.003 |
cr | -0.003 |
ring | -0.003 |
Sur | -0.003 |
OOOO | -0.003 |
Token | answer |
Token ID | 3280 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ring | +0.023 |
cr | +0.023 |
elt | +0.021 |
lette | +0.020 |
OOOO | +0.020 |
Neg logit contributions | |
gly | -0.026 |
therapist | -0.025 |
irl | -0.025 |
issa | -0.025 |
professor | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
irl | +0.044 |
concert | +0.042 |
gly | +0.041 |
Hood | +0.041 |
professor | +0.041 |
Neg logit contributions | |
ring | -0.047 |
elt | -0.046 |
cr | -0.046 |
lette | -0.042 |
Sur | -0.041 |
Token | Peter |
Token ID | 5613 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
elt | +0.012 |
ring | +0.011 |
cr | +0.011 |
Sur | +0.011 |
OOOO | +0.010 |
Neg logit contributions | |
irl | -0.011 |
gly | -0.011 |
concert | -0.010 |
professor | -0.010 |
therapist | -0.010 |
Token | slowly |
Token ID | 6364 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
gly | +0.033 |
irl | +0.033 |
professor | +0.032 |
concert | +0.032 |
tutor | +0.031 |
Neg logit contributions | |
elt | -0.038 |
ring | -0.036 |
cr | -0.036 |
Sur | -0.034 |
lette | -0.033 |
Token | is |
Token ID | 318 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
gly | +0.079 |
ela | +0.079 |
irl | +0.078 |
professor | +0.077 |
acio | +0.076 |
Neg logit contributions | |
elt | -0.104 |
Sur | -0.100 |
ring | -0.097 |
cr | -0.096 |
OOOO | -0.095 |
Token | Leo |
Token ID | 19632 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
irl | +0.057 |
gly | +0.055 |
concert | +0.054 |
therapist | +0.054 |
professor | +0.054 |
Neg logit contributions | |
elt | -0.046 |
cr | -0.043 |
ring | -0.042 |
Sur | -0.041 |
OOOO | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-04 |
Pos logit contributions | |
irl | +0.070 |
gly | +0.069 |
professor | +0.068 |
concert | +0.068 |
acio | +0.066 |
Neg logit contributions | |
cr | -0.067 |
elt | -0.066 |
ring | -0.066 |
lette | -0.061 |
OOOO | -0.060 |
Token | Leo |
Token ID | 19632 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
elt | +0.000 |
ring | +0.000 |
cr | +0.000 |
Sur | +0.000 |
OOOO | +0.000 |
Neg logit contributions | |
gly | -0.000 |
professor | -0.000 |
irl | -0.000 |
tutor | -0.000 |
concert | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
concert | +0.072 |
therapist | +0.072 |
avail | +0.072 |
professor | +0.071 |
tutor | +0.071 |
Neg logit contributions | |
elt | -0.059 |
cr | -0.055 |
OOOO | -0.054 |
ring | -0.053 |
eighteen | -0.052 |
Token | shy |
Token ID | 15800 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
gly | +0.053 |
irl | +0.051 |
concert | +0.050 |
therapist | +0.050 |
professor | +0.049 |
Neg logit contributions | |
elt | -0.052 |
ring | -0.048 |
cr | -0.048 |
Sur | -0.046 |
OOOO | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-04 |
Pos logit contributions | |
gly | +0.016 |
irl | +0.016 |
professor | +0.015 |
concert | +0.015 |
therapist | +0.015 |
Neg logit contributions | |
elt | -0.027 |
ring | -0.026 |
cr | -0.026 |
Sur | -0.025 |
OOOO | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
elt | +0.001 |
ring | +0.001 |
cr | +0.001 |
Sur | +0.001 |
lette | +0.001 |
Neg logit contributions | |
gly | -0.001 |
professor | -0.001 |
tutor | -0.001 |
irl | -0.001 |
therapist | -0.001 |
Token | does |
Token ID | 857 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
therapist | +0.015 |
ela | +0.015 |
aisle | +0.015 |
otte | +0.014 |
gly | +0.014 |
Neg logit contributions | |
elt | -0.009 |
OOOO | -0.008 |
eighteen | -0.008 |
ring | -0.008 |
See | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
gly | +0.097 |
therapist | +0.093 |
Hood | +0.093 |
aisle | +0.093 |
issa | +0.093 |
Neg logit contributions | |
cr | -0.038 |
ring | -0.037 |
eighteen | -0.037 |
Sur | -0.034 |
elt | -0.033 |
Token | talk |
Token ID | 1561 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
gly | +0.031 |
irl | +0.031 |
professor | +0.030 |
concert | +0.030 |
tutor | +0.030 |
Neg logit contributions | |
elt | -0.025 |
ring | -0.023 |
cr | -0.022 |
Sur | -0.022 |
OOOO | -0.021 |
Token | park |
Token ID | 3952 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
concert | +0.007 |
professor | +0.007 |
therapist | +0.007 |
Neg logit contributions | |
elt | -0.012 |
cr | -0.011 |
Sur | -0.011 |
ring | -0.011 |
OOOO | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
gly | +0.019 |
irl | +0.018 |
professor | +0.017 |
concert | +0.017 |
therapist | +0.017 |
Neg logit contributions | |
elt | -0.034 |
ring | -0.032 |
cr | -0.032 |
Sur | -0.031 |
OOOO | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
ring | +0.015 |
cr | +0.014 |
elt | +0.014 |
lette | +0.014 |
Sur | +0.013 |
Neg logit contributions | |
Holly | -0.014 |
gly | -0.013 |
Sparkle | -0.013 |
Pixie | -0.013 |
irl | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.007 |
tutor | +0.007 |
professor | +0.007 |
concert | +0.007 |
Neg logit contributions | |
elt | -0.005 |
cr | -0.005 |
ring | -0.005 |
Sur | -0.005 |
OOOO | -0.005 |
Token | hurt |
Token ID | 5938 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
elt | +0.061 |
ring | +0.058 |
cr | +0.057 |
Sur | +0.056 |
OOOO | +0.055 |
Neg logit contributions | |
irl | -0.045 |
gly | -0.045 |
professor | -0.043 |
concert | -0.042 |
tutor | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
gly | +0.021 |
professor | +0.021 |
irl | +0.020 |
tutor | +0.020 |
concert | +0.020 |
Neg logit contributions | |
elt | -0.044 |
ring | -0.042 |
cr | -0.042 |
lette | -0.041 |
Sur | -0.041 |
Token | dirty |
Token ID | 11841 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
elt | +0.007 |
ring | +0.007 |
cr | +0.007 |
Sur | +0.007 |
OOOO | +0.007 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
concert | -0.004 |
tutor | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
elt | +0.020 |
ring | +0.019 |
cr | +0.019 |
Sur | +0.019 |
OOOO | +0.019 |
Neg logit contributions | |
gly | -0.008 |
professor | -0.007 |
concert | -0.007 |
irl | -0.007 |
therapist | -0.007 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
elt | +0.006 |
ring | +0.006 |
Sur | +0.006 |
cr | +0.006 |
OOOO | +0.006 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
concert | -0.004 |
therapist | -0.004 |
professor | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -7.09e-03 |
Pos logit contributions | |
gly | +0.010 |
professor | +0.008 |
tutor | +0.008 |
concert | +0.008 |
irl | +0.008 |
Neg logit contributions | |
elt | -0.028 |
ring | -0.026 |
cr | -0.026 |
lette | -0.025 |
OOOO | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
ring | +0.012 |
elt | +0.011 |
cr | +0.011 |
lette | +0.010 |
Sur | +0.010 |
Neg logit contributions | |
gly | -0.011 |
Holly | -0.011 |
Pixie | -0.011 |
Sparkle | -0.011 |
irl | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
elt | +0.013 |
cr | +0.013 |
ring | +0.013 |
Sur | +0.012 |
OOOO | +0.012 |
Neg logit contributions | |
gly | -0.013 |
irl | -0.013 |
concert | -0.013 |
professor | -0.013 |
therapist | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
elt | +0.016 |
ring | +0.015 |
cr | +0.014 |
pulp | +0.013 |
lette | +0.013 |
Neg logit contributions | |
irl | -0.012 |
gly | -0.011 |
professor | -0.011 |
aisle | -0.011 |
concert | -0.011 |
Token | rocket |
Token ID | 10701 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
Sur | +0.021 |
elt | +0.021 |
ring | +0.021 |
OOOO | +0.020 |
cr | +0.020 |
Neg logit contributions | |
gly | -0.021 |
irl | -0.019 |
Holly | -0.019 |
ela | -0.019 |
therapist | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
elt | +0.060 |
ring | +0.057 |
cr | +0.056 |
Sur | +0.055 |
OOOO | +0.054 |
Neg logit contributions | |
gly | -0.040 |
irl | -0.039 |
professor | -0.038 |
concert | -0.038 |
therapist | -0.037 |
Token | amazing |
Token ID | 4998 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
irl | +0.009 |
up | +0.008 |
stage | +0.008 |
professor | +0.008 |
concert | +0.008 |
Neg logit contributions | |
elt | -0.016 |
ring | -0.014 |
Sur | -0.014 |
cr | -0.014 |
OOOO | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
elt | +0.040 |
ring | +0.037 |
cr | +0.037 |
Sur | +0.035 |
OOOO | +0.035 |
Neg logit contributions | |
irl | -0.033 |
gly | -0.033 |
concert | -0.032 |
therapist | -0.031 |
professor | -0.031 |
Token | It |
Token ID | 632 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
cr | +0.021 |
ring | +0.020 |
elt | +0.019 |
lette | +0.019 |
pulp | +0.018 |
Neg logit contributions | |
professor | -0.017 |
gly | -0.016 |
tutor | -0.016 |
Ross | -0.016 |
tests | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
elt | +0.035 |
ring | +0.033 |
cr | +0.033 |
Sur | +0.032 |
OOOO | +0.032 |
Neg logit contributions | |
gly | -0.023 |
irl | -0.023 |
professor | -0.022 |
concert | -0.022 |
therapist | -0.022 |
Token | many |
Token ID | 867 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
elt | +0.083 |
ring | +0.078 |
cr | +0.074 |
lette | +0.073 |
umbs | +0.072 |
Neg logit contributions | |
stage | -0.045 |
professor | -0.041 |
show | -0.040 |
Hood | -0.040 |
Sparkle | -0.040 |
Token | buttons |
Token ID | 12163 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
elt | +0.053 |
ring | +0.051 |
Sur | +0.050 |
cr | +0.050 |
OOOO | +0.047 |
Neg logit contributions | |
gly | -0.056 |
irl | -0.054 |
therapist | -0.053 |
professor | -0.053 |
concert | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
elt | +0.032 |
cr | +0.031 |
Sur | +0.031 |
OOOO | +0.030 |
ring | +0.030 |
Neg logit contributions | |
gly | -0.014 |
professor | -0.014 |
irl | -0.014 |
concert | -0.014 |
stage | -0.013 |
Token | worry |
Token ID | 5490 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
concert | +0.058 |
irl | +0.058 |
gly | +0.057 |
tutor | +0.056 |
professor | +0.055 |
Neg logit contributions | |
elt | -0.060 |
cr | -0.054 |
umbs | -0.054 |
Sur | -0.054 |
OOOO | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
elt | +0.117 |
ring | +0.111 |
cr | +0.110 |
Sur | +0.109 |
OOOO | +0.105 |
Neg logit contributions | |
gly | -0.054 |
irl | -0.052 |
concert | -0.050 |
tutor | -0.050 |
professor | -0.049 |
Token | I |
Token ID | 314 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
tutor | +0.025 |
Sparkle | +0.024 |
concert | +0.024 |
irl | +0.024 |
Felix | +0.023 |
Neg logit contributions | |
elt | -0.039 |
ring | -0.037 |
umbs | -0.035 |
OOOO | -0.035 |
Sur | -0.034 |
Token | will |
Token ID | 481 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
gly | +0.013 |
professor | +0.013 |
concert | +0.013 |
tutor | +0.013 |
irl | +0.012 |
Neg logit contributions | |
elt | -0.013 |
cr | -0.013 |
ring | -0.013 |
Sur | -0.012 |
OOOO | -0.012 |
Token | help |
Token ID | 1037 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
gly | +0.106 |
professor | +0.103 |
therapist | +0.100 |
concert | +0.098 |
tutor | +0.098 |
Neg logit contributions | |
ring | -0.114 |
cr | -0.112 |
elt | -0.111 |
lette | -0.105 |
OOOO | -0.102 |
Token | you |
Token ID | 345 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
gly | +0.123 |
irl | +0.120 |
professor | +0.119 |
concert | +0.117 |
therapist | +0.116 |
Neg logit contributions | |
elt | -0.124 |
ring | -0.118 |
cr | -0.117 |
Sur | -0.111 |
OOOO | -0.110 |
Token | ." |
Token ID | 526 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
elt | +0.029 |
ring | +0.027 |
cr | +0.027 |
Sur | +0.027 |
OOOO | +0.026 |
Neg logit contributions | |
irl | -0.020 |
gly | -0.019 |
concert | -0.018 |
professor | -0.018 |
tutor | -0.018 |
Token | |
Token ID | 220 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
ring | +0.046 |
elt | +0.046 |
cr | +0.044 |
OOOO | +0.043 |
Sur | +0.042 |
Neg logit contributions | |
gly | -0.041 |
tutor | -0.038 |
therapist | -0.038 |
professor | -0.038 |
irl | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
gly | +0.076 |
irl | +0.074 |
concert | +0.073 |
professor | +0.073 |
therapist | +0.071 |
Neg logit contributions | |
elt | -0.080 |
cr | -0.074 |
ring | -0.074 |
Sur | -0.072 |
OOOO | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
elt | +0.002 |
ring | +0.002 |
cr | +0.002 |
OOOO | +0.002 |
Sur | +0.002 |
Neg logit contributions | |
gly | -0.002 |
irl | -0.002 |
professor | -0.002 |
concert | -0.002 |
therapist | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
elt | +0.004 |
ring | +0.004 |
cr | +0.003 |
OOOO | +0.003 |
lette | +0.003 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
therapist | -0.004 |
concert | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
ring | +0.040 |
elt | +0.040 |
umbs | +0.038 |
lette | +0.038 |
OOOO | +0.037 |
Neg logit contributions | |
irl | -0.031 |
stage | -0.030 |
concert | -0.030 |
gly | -0.030 |
professor | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
irl | +0.039 |
gly | +0.039 |
therapist | +0.038 |
professor | +0.037 |
ricia | +0.037 |
Neg logit contributions | |
elt | -0.050 |
ring | -0.048 |
cr | -0.047 |
Sur | -0.045 |
OOOO | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
irl | +0.012 |
gly | +0.011 |
concert | +0.011 |
professor | +0.011 |
stage | +0.011 |
Neg logit contributions | |
elt | -0.024 |
ring | -0.023 |
cr | -0.023 |
OOOO | -0.022 |
umbs | -0.022 |
Token | boot |
Token ID | 6297 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
gly | +0.007 |
irl | +0.007 |
professor | +0.007 |
concert | +0.007 |
tutor | +0.007 |
Neg logit contributions | |
elt | -0.009 |
ring | -0.009 |
cr | -0.009 |
Sur | -0.008 |
OOOO | -0.008 |
Token | ventured |
Token ID | 44716 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
irl | +0.039 |
gly | +0.038 |
professor | +0.037 |
concert | +0.037 |
therapist | +0.037 |
Neg logit contributions | |
elt | -0.055 |
ring | -0.052 |
cr | -0.052 |
OOOO | -0.050 |
Sur | -0.050 |
Token | through |
Token ID | 832 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
elt | +0.049 |
cr | +0.045 |
ring | +0.045 |
Sur | +0.044 |
OOOO | +0.043 |
Neg logit contributions | |
gly | -0.044 |
irl | -0.042 |
concert | -0.041 |
professor | -0.041 |
tutor | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
elt | +0.006 |
ring | +0.005 |
cr | +0.005 |
OOOO | +0.005 |
Sur | +0.005 |
Neg logit contributions | |
irl | -0.003 |
gly | -0.003 |
stage | -0.003 |
professor | -0.003 |
concert | -0.003 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
gly | +0.017 |
irl | +0.016 |
Hood | +0.016 |
therapist | +0.015 |
professor | +0.015 |
Neg logit contributions | |
elt | -0.020 |
Sur | -0.020 |
cr | -0.019 |
ring | -0.019 |
OOOO | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
gly | +0.013 |
irl | +0.013 |
professor | +0.013 |
concert | +0.013 |
tutor | +0.012 |
Neg logit contributions | |
elt | -0.024 |
ring | -0.023 |
cr | -0.023 |
Sur | -0.023 |
OOOO | -0.022 |
Token | seeing |
Token ID | 4379 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
irl | +0.012 |
gly | +0.012 |
professor | +0.011 |
concert | +0.011 |
therapist | +0.011 |
Neg logit contributions | |
elt | -0.019 |
ring | -0.019 |
cr | -0.018 |
Sur | -0.018 |
umbs | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
elt | +0.103 |
ring | +0.100 |
OOOO | +0.096 |
cr | +0.095 |
Sur | +0.094 |
Neg logit contributions | |
irl | -0.058 |
gly | -0.057 |
professor | -0.056 |
tutor | -0.054 |
stage | -0.054 |
Token | share |
Token ID | 2648 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
elt | +0.000 |
cr | +0.000 |
ring | +0.000 |
Sur | +0.000 |
OOOO | +0.000 |
Neg logit contributions | |
irl | -0.000 |
gly | -0.000 |
concert | -0.000 |
professor | -0.000 |
tutor | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +8.12e-04 |
Pos logit contributions | |
gly | +0.034 |
irl | +0.033 |
professor | +0.032 |
concert | +0.032 |
tutor | +0.031 |
Neg logit contributions | |
elt | -0.046 |
ring | -0.043 |
cr | -0.043 |
Sur | -0.041 |
OOOO | -0.041 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
gly | +0.001 |
irl | +0.001 |
professor | +0.001 |
concert | +0.001 |
tutor | +0.001 |
Neg logit contributions | |
elt | -0.001 |
ring | -0.001 |
cr | -0.001 |
Sur | -0.001 |
OOOO | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
gly | +0.017 |
irl | +0.017 |
therapist | +0.016 |
ricia | +0.016 |
issa | +0.016 |
Neg logit contributions | |
cr | -0.015 |
ring | -0.015 |
elt | -0.015 |
Sur | -0.013 |
lette | -0.013 |
Token | other |
Token ID | 584 |
Feature activation | -6.96e-03 |
Pos logit contributions | |
gly | +0.058 |
irl | +0.057 |
concert | +0.056 |
professor | +0.056 |
therapist | +0.055 |
Neg logit contributions | |
elt | -0.086 |
ring | -0.082 |
cr | -0.081 |
Sur | -0.078 |
OOOO | -0.078 |
Token | kids |
Token ID | 3988 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
elt | +0.014 |
cr | +0.014 |
ring | +0.013 |
OOOO | +0.013 |
umbs | +0.013 |
Neg logit contributions | |
gly | -0.008 |
professor | -0.008 |
tutor | -0.008 |
concert | -0.008 |
irl | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
elt | +0.067 |
ring | +0.066 |
cr | +0.064 |
lette | +0.059 |
OOOO | +0.058 |
Neg logit contributions | |
irl | -0.070 |
therapist | -0.069 |
gly | -0.069 |
concert | -0.067 |
professor | -0.067 |
Token | One |
Token ID | 1881 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
gly | +0.010 |
irl | +0.009 |
professor | +0.009 |
tutor | +0.009 |
therapist | +0.009 |
Neg logit contributions | |
elt | -0.012 |
ring | -0.011 |
cr | -0.011 |
Sur | -0.011 |
OOOO | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
gly | +0.047 |
irl | +0.045 |
professor | +0.043 |
concert | +0.043 |
therapist | +0.042 |
Neg logit contributions | |
elt | -0.103 |
ring | -0.099 |
cr | -0.098 |
Sur | -0.096 |
OOOO | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
gly | +0.035 |
irl | +0.032 |
therapist | +0.029 |
professor | +0.029 |
tutor | +0.029 |
Neg logit contributions | |
ring | -0.098 |
elt | -0.097 |
cr | -0.092 |
Sur | -0.091 |
lette | -0.091 |
Token | he |
Token ID | 339 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
gly | +0.029 |
irl | +0.028 |
professor | +0.027 |
tutor | +0.027 |
therapist | +0.027 |
Neg logit contributions | |
elt | -0.040 |
ring | -0.039 |
cr | -0.036 |
Sur | -0.036 |
OOOO | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
gly | +0.129 |
irl | +0.125 |
concert | +0.122 |
professor | +0.122 |
therapist | +0.120 |
Neg logit contributions | |
elt | -0.135 |
ring | -0.125 |
cr | -0.124 |
Sur | -0.119 |
OOOO | -0.118 |
Token | He |
Token ID | 679 |
Feature activation | -1.01e-04 |
Pos logit contributions | |
ring | +0.005 |
lette | +0.005 |
cr | +0.005 |
OOOO | +0.005 |
pulp | +0.005 |
Neg logit contributions | |
up | -0.003 |
gly | -0.003 |
aisle | -0.003 |
irl | -0.003 |
shop | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
elt | +0.000 |
cr | +0.000 |
ring | +0.000 |
Sur | +0.000 |
OOOO | +0.000 |
Neg logit contributions | |
gly | -0.000 |
irl | -0.000 |
concert | -0.000 |
tutor | -0.000 |
professor | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ring | +0.091 |
elt | +0.087 |
OOOO | +0.085 |
cr | +0.082 |
umbs | +0.081 |
Neg logit contributions | |
gly | -0.077 |
professor | -0.075 |
tutor | -0.075 |
concert | -0.074 |
Hood | -0.074 |
Token | yellow |
Token ID | 7872 |
Feature activation | +5.74e-03 |
Pos logit contributions | |
gly | +0.023 |
irl | +0.022 |
Hood | +0.021 |
acio | +0.021 |
therapist | +0.020 |
Neg logit contributions | |
elt | -0.023 |
Sur | -0.022 |
cr | -0.022 |
ring | -0.020 |
OOOO | -0.020 |
Token | roof |
Token ID | 9753 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.008 |
concert | +0.008 |
therapist | +0.008 |
Neg logit contributions | |
elt | -0.010 |
ring | -0.010 |
cr | -0.010 |
Sur | -0.009 |
OOOO | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
elt | +0.165 |
Sur | +0.157 |
cr | +0.156 |
ring | +0.156 |
OOOO | +0.155 |
Neg logit contributions | |
irl | -0.102 |
gly | -0.102 |
concert | -0.099 |
professor | -0.098 |
aisle | -0.097 |
Token | He |
Token ID | 679 |
Feature activation | +6.29e-04 |
Pos logit contributions | |
ring | +0.048 |
lette | +0.045 |
cr | +0.043 |
OOOO | +0.042 |
pulp | +0.041 |
Neg logit contributions | |
gly | -0.034 |
aisle | -0.033 |
shop | -0.032 |
Bruno | -0.032 |
up | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
irl | +0.001 |
gly | +0.001 |
issa | +0.001 |
therapist | +0.001 |
ela | +0.001 |
Neg logit contributions | |
ring | -0.001 |
elt | -0.001 |
umbs | -0.001 |
cr | -0.001 |
OOOO | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
irl | +0.017 |
stage | +0.017 |
up | +0.017 |
professor | +0.016 |
closely | +0.016 |
Neg logit contributions | |
elt | -0.022 |
OOOO | -0.022 |
Sur | -0.021 |
ring | -0.021 |
cr | -0.021 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ring | +0.052 |
elt | +0.050 |
tern | +0.049 |
OOOO | +0.048 |
cr | +0.048 |
Neg logit contributions | |
irl | -0.023 |
closely | -0.019 |
up | -0.018 |
stage | -0.018 |
ela | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
gly | +0.028 |
irl | +0.028 |
professor | +0.026 |
tutor | +0.026 |
therapist | +0.025 |
Neg logit contributions | |
elt | -0.042 |
ring | -0.042 |
cr | -0.040 |
Sur | -0.039 |
OOOO | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
elt | +0.047 |
ring | +0.044 |
cr | +0.044 |
Sur | +0.043 |
OOOO | +0.042 |
Neg logit contributions | |
gly | -0.043 |
irl | -0.043 |
professor | -0.042 |
concert | -0.041 |
tutor | -0.041 |
Token | The |
Token ID | 464 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
elt | +0.038 |
ring | +0.036 |
cr | +0.034 |
OOOO | +0.033 |
lette | +0.031 |
Neg logit contributions | |
gly | -0.051 |
irl | -0.051 |
professor | -0.049 |
concert | -0.049 |
therapist | -0.049 |
Token | children |
Token ID | 1751 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
Sur | +0.039 |
elt | +0.034 |
ring | +0.034 |
cr | +0.033 |
eight | +0.031 |
Neg logit contributions | |
ines | -0.055 |
gly | -0.053 |
acio | -0.051 |
ches | -0.051 |
irl | -0.051 |
Token | never |
Token ID | 1239 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
elt | +0.124 |
ring | +0.117 |
cr | +0.116 |
Sur | +0.111 |
OOOO | +0.109 |
Neg logit contributions | |
gly | -0.119 |
irl | -0.116 |
professor | -0.113 |
concert | -0.113 |
tutor | -0.111 |
Token | forgot |
Token ID | 16453 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
elt | +0.059 |
umbs | +0.058 |
OOOO | +0.057 |
lette | +0.056 |
cr | +0.056 |
Neg logit contributions | |
concert | -0.043 |
professor | -0.042 |
therapist | -0.039 |
gly | -0.039 |
mun | -0.038 |
Token | that |
Token ID | 326 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
elt | +0.170 |
ring | +0.161 |
cr | +0.160 |
Sur | +0.154 |
OOOO | +0.152 |
Neg logit contributions | |
gly | -0.141 |
irl | -0.138 |
professor | -0.134 |
concert | -0.132 |
therapist | -0.130 |
Token | special |
Token ID | 2041 |
Feature activation | -8.41e-04 |
Pos logit contributions | |
gly | +0.023 |
irl | +0.023 |
Hood | +0.021 |
ches | +0.021 |
ricia | +0.021 |
Neg logit contributions | |
elt | -0.026 |
cr | -0.026 |
ring | -0.025 |
Sur | -0.024 |
lette | -0.022 |
Token | day |
Token ID | 1110 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
elt | +0.001 |
cr | +0.001 |
ring | +0.001 |
Sur | +0.001 |
lette | +0.001 |
Neg logit contributions | |
gly | -0.001 |
irl | -0.001 |
Hood | -0.001 |
acio | -0.001 |
professor | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
gly | +0.025 |
irl | +0.024 |
professor | +0.023 |
concert | +0.023 |
tutor | +0.023 |
Neg logit contributions | |
elt | -0.041 |
ring | -0.039 |
cr | -0.039 |
Sur | -0.038 |
OOOO | -0.037 |
Token | how |
Token ID | 703 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
elt | +0.038 |
ring | +0.036 |
cr | +0.036 |
Sur | +0.035 |
OOOO | +0.034 |
Neg logit contributions | |
gly | -0.029 |
irl | -0.029 |
professor | -0.028 |
concert | -0.028 |
therapist | -0.027 |
Token | there |
Token ID | 612 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
elt | +0.093 |
cr | +0.084 |
ring | +0.084 |
Sur | +0.081 |
lette | +0.078 |
Neg logit contributions | |
gly | -0.072 |
irl | -0.069 |
professor | -0.067 |
concert | -0.066 |
therapist | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
elt | +0.009 |
ring | +0.008 |
cr | +0.008 |
Sur | +0.008 |
OOOO | +0.008 |
Neg logit contributions | |
gly | -0.004 |
irl | -0.004 |
professor | -0.004 |
concert | -0.004 |
tutor | -0.004 |
Token | Clara |
Token ID | 27443 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
gly | +0.008 |
irl | +0.008 |
professor | +0.007 |
concert | +0.007 |
therapist | +0.007 |
Neg logit contributions | |
elt | -0.014 |
ring | -0.013 |
cr | -0.013 |
Sur | -0.013 |
OOOO | -0.012 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
elt | +0.043 |
ring | +0.041 |
cr | +0.040 |
Sur | +0.039 |
OOOO | +0.039 |
Neg logit contributions | |
gly | -0.032 |
irl | -0.031 |
professor | -0.030 |
concert | -0.030 |
therapist | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
elt | +0.099 |
cr | +0.092 |
ring | +0.092 |
Sur | +0.088 |
OOOO | +0.084 |
Neg logit contributions | |
gly | -0.104 |
irl | -0.103 |
professor | -0.100 |
concert | -0.099 |
tutor | -0.097 |
Token | sand |
Token ID | 6450 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
elt | +0.007 |
cr | +0.007 |
ring | +0.006 |
Sur | +0.006 |
lette | +0.006 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
acio | -0.006 |
professor | -0.006 |
ela | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
elt | +0.159 |
ring | +0.151 |
cr | +0.146 |
Sur | +0.145 |
OOOO | +0.143 |
Neg logit contributions | |
gly | -0.145 |
irl | -0.144 |
concert | -0.138 |
professor | -0.137 |
therapist | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
gly | +0.023 |
irl | +0.022 |
professor | +0.021 |
concert | +0.021 |
therapist | +0.020 |
Neg logit contributions | |
elt | -0.026 |
cr | -0.025 |
ring | -0.025 |
Sur | -0.024 |
OOOO | -0.023 |
Token | sun |
Token ID | 4252 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
elt | +0.007 |
ring | +0.007 |
cr | +0.006 |
OOOO | +0.006 |
Sur | +0.006 |
Neg logit contributions | |
gly | -0.006 |
irl | -0.006 |
concert | -0.006 |
professor | -0.006 |
therapist | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
elt | +0.199 |
Sur | +0.196 |
OOOO | +0.195 |
ring | +0.187 |
cr | +0.186 |
Neg logit contributions | |
irl | -0.077 |
therapist | -0.076 |
concert | -0.075 |
gly | -0.074 |
aisle | -0.073 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ring | +0.026 |
elt | +0.026 |
OOOO | +0.026 |
umbs | +0.025 |
cr | +0.025 |
Neg logit contributions | |
irl | -0.013 |
therapist | -0.013 |
gly | -0.013 |
stage | -0.013 |
concert | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
elt | +0.021 |
cr | +0.020 |
ring | +0.020 |
Sur | +0.020 |
OOOO | +0.020 |
Neg logit contributions | |
gly | -0.008 |
tutor | -0.008 |
irl | -0.008 |
professor | -0.008 |
concert | -0.008 |
Token | Eleven |
Token ID | 37339 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ring | +0.013 |
elt | +0.013 |
cr | +0.013 |
OOOO | +0.012 |
lette | +0.012 |
Neg logit contributions | |
gly | -0.013 |
irl | -0.012 |
professor | -0.012 |
tutor | -0.012 |
concert | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
gly | +0.012 |
irl | +0.011 |
professor | +0.011 |
concert | +0.010 |
therapist | +0.010 |
Neg logit contributions | |
elt | -0.025 |
ring | -0.023 |
cr | -0.023 |
Sur | -0.023 |
OOOO | -0.022 |
Token | twelve |
Token ID | 14104 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
gly | +0.034 |
poster | +0.033 |
professor | +0.033 |
concert | +0.033 |
tutor | +0.033 |
Neg logit contributions | |
elt | -0.033 |
cr | -0.030 |
ring | -0.030 |
OOOO | -0.028 |
umbs | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
elt | +0.188 |
cr | +0.179 |
ring | +0.178 |
Sur | +0.172 |
OOOO | +0.171 |
Neg logit contributions | |
irl | -0.077 |
gly | -0.077 |
professor | -0.070 |
concert | -0.069 |
stage | -0.069 |
Token | thirteen |
Token ID | 28306 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
poster | +0.035 |
gly | +0.035 |
irl | +0.034 |
stage | +0.034 |
concert | +0.033 |
Neg logit contributions | |
elt | -0.030 |
cr | -0.027 |
ring | -0.026 |
OOOO | -0.026 |
umbs | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
elt | +0.253 |
ring | +0.241 |
cr | +0.237 |
Sur | +0.233 |
OOOO | +0.228 |
Neg logit contributions | |
irl | -0.092 |
gly | -0.087 |
ls | -0.079 |
stage | -0.078 |
poster | -0.078 |
Token | fourteen |
Token ID | 29167 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
poster | +0.035 |
irl | +0.035 |
closely | +0.034 |
gly | +0.034 |
ls | +0.034 |
Neg logit contributions | |
elt | -0.032 |
ring | -0.030 |
cr | -0.029 |
OOOO | -0.029 |
lette | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ring | +0.222 |
elt | +0.221 |
cr | +0.208 |
OOOO | +0.206 |
umbs | +0.201 |
Neg logit contributions | |
gly | -0.069 |
irl | -0.068 |
ls | -0.067 |
stage | -0.063 |
poster | -0.062 |
Token | fifteen |
Token ID | 17280 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
poster | +0.027 |
ls | +0.025 |
first | +0.025 |
show | +0.025 |
closely | +0.025 |
Neg logit contributions | |
elt | -0.027 |
ring | -0.025 |
OOOO | -0.023 |
umbs | -0.023 |
lette | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -7.10e-03 |
Pos logit contributions | |
elt | +0.193 |
ring | +0.185 |
cr | +0.180 |
OOOO | +0.171 |
lette | +0.168 |
Neg logit contributions | |
irl | -0.055 |
ls | -0.053 |
gly | -0.051 |
poster | -0.049 |
ines | -0.049 |
Token | little |
Token ID | 1310 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
elt | +0.006 |
cr | +0.006 |
ring | +0.006 |
Sur | +0.006 |
lette | +0.005 |
Neg logit contributions | |
gly | -0.008 |
irl | -0.008 |
acio | -0.008 |
professor | -0.008 |
concert | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
elt | +0.099 |
ring | +0.092 |
cr | +0.091 |
Sur | +0.087 |
OOOO | +0.085 |
Neg logit contributions | |
gly | -0.088 |
irl | -0.086 |
professor | -0.083 |
concert | -0.082 |
tutor | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
elt | +0.053 |
ring | +0.050 |
cr | +0.049 |
Sur | +0.048 |
OOOO | +0.047 |
Neg logit contributions | |
gly | -0.054 |
irl | -0.052 |
professor | -0.051 |
concert | -0.050 |
tutor | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
elt | +0.023 |
ring | +0.023 |
cr | +0.022 |
Sur | +0.021 |
lette | +0.020 |
Neg logit contributions | |
irl | -0.021 |
gly | -0.021 |
ines | -0.019 |
ches | -0.019 |
concert | -0.019 |
Token | family |
Token ID | 1641 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
elt | +0.020 |
cr | +0.018 |
ring | +0.018 |
lette | +0.018 |
Sur | +0.018 |
Neg logit contributions | |
irl | -0.026 |
acio | -0.026 |
roads | -0.026 |
gly | -0.025 |
ches | -0.025 |
Token | woke |
Token ID | 19092 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
elt | +0.092 |
ring | +0.086 |
cr | +0.085 |
Sur | +0.081 |
OOOO | +0.080 |
Neg logit contributions | |
gly | -0.107 |
irl | -0.105 |
professor | -0.102 |
concert | -0.102 |
tutor | -0.100 |
Token | up |
Token ID | 510 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
elt | +0.211 |
ring | +0.206 |
lette | +0.196 |
OOOO | +0.194 |
Sur | +0.192 |
Neg logit contributions | |
gly | -0.093 |
professor | -0.091 |
therapist | -0.087 |
ela | -0.084 |
irl | -0.080 |
Token | feeling |
Token ID | 4203 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
gly | +0.106 |
irl | +0.103 |
professor | +0.100 |
concert | +0.099 |
therapist | +0.097 |
Neg logit contributions | |
elt | -0.139 |
ring | -0.131 |
cr | -0.130 |
Sur | -0.126 |
OOOO | -0.124 |
Token | very |
Token ID | 845 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
elt | +0.028 |
cr | +0.026 |
ring | +0.026 |
Sur | +0.025 |
lette | +0.024 |
Neg logit contributions | |
gly | -0.025 |
irl | -0.023 |
professor | -0.023 |
concert | -0.023 |
tutor | -0.023 |
Token | un |
Token ID | 555 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
gly | +0.061 |
professor | +0.058 |
irl | +0.057 |
concert | +0.057 |
therapist | +0.056 |
Neg logit contributions | |
elt | -0.066 |
ring | -0.063 |
cr | -0.062 |
Sur | -0.060 |
OOOO | -0.059 |
Token | well |
Token ID | 4053 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
irl | +0.016 |
gly | +0.015 |
tutor | +0.015 |
concert | +0.015 |
stage | +0.015 |
Neg logit contributions | |
elt | -0.015 |
ring | -0.014 |
cr | -0.013 |
lette | -0.013 |
Sur | -0.012 |