Token | sad |
Token ID | 6507 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
cel | +0.002 |
stru | +0.002 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
dad | -0.002 |
Token | because |
Token ID | 780 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
stru | +0.013 |
fulfilled | +0.013 |
cel | +0.013 |
unlike | +0.013 |
since | +0.012 |
Neg logit contributions | |
moms | -0.018 |
slide | -0.015 |
dad | -0.015 |
dads | -0.015 |
truck | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
Mill | +0.002 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
towels | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
since | +0.024 |
fulfilled | +0.023 |
unlike | +0.023 |
stru | +0.023 |
cel | +0.022 |
Neg logit contributions | |
moms | -0.020 |
eps | -0.015 |
slide | -0.015 |
dads | -0.015 |
says | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
since | +0.005 |
stru | +0.005 |
fulfilled | +0.005 |
unlike | +0.005 |
cel | +0.005 |
Neg logit contributions | |
moms | -0.005 |
dads | -0.004 |
eps | -0.004 |
slide | -0.004 |
dad | -0.004 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
stru | +0.056 |
since | +0.056 |
cel | +0.056 |
Nice | +0.056 |
unlike | +0.053 |
Neg logit contributions | |
moms | -0.047 |
eps | -0.043 |
dads | -0.041 |
dad | -0.040 |
snow | -0.038 |
Token | oming |
Token ID | 3383 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
since | +0.189 |
unlike | +0.184 |
discovering | +0.182 |
knowing | +0.181 |
Mill | +0.179 |
Neg logit contributions | |
moms | -0.246 |
eps | -0.225 |
towels | -0.203 |
fountain | -0.203 |
outed | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
stru | +0.146 |
cel | +0.143 |
fulfilled | +0.138 |
ulent | +0.135 |
unlike | +0.134 |
Neg logit contributions | |
moms | -0.105 |
slide | -0.087 |
truck | -0.082 |
snow | -0.080 |
fountain | -0.080 |
Token | It |
Token ID | 632 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
since | +0.013 |
unlike | +0.012 |
fulfilled | +0.012 |
stru | +0.012 |
cel | +0.011 |
Neg logit contributions | |
moms | -0.020 |
dads | -0.017 |
eps | -0.016 |
slide | -0.016 |
truck | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.007 |
eps | -0.006 |
slide | -0.006 |
towels | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
moms | +0.047 |
dads | +0.040 |
slide | +0.039 |
dad | +0.039 |
snow | +0.038 |
Neg logit contributions | |
cel | -0.023 |
since | -0.021 |
unlike | -0.021 |
stru | -0.021 |
fulfilled | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
since | +0.007 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.007 |
unlike | +0.007 |
Neg logit contributions | |
moms | -0.010 |
dads | -0.008 |
slide | -0.008 |
eps | -0.008 |
towels | -0.008 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.016 |
eps | +0.015 |
slide | +0.015 |
truck | +0.015 |
Neg logit contributions | |
since | -0.013 |
unlike | -0.012 |
fulfilled | -0.012 |
stru | -0.012 |
cel | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.016 |
slide | +0.015 |
dad | +0.015 |
Tom | +0.014 |
Neg logit contributions | |
unlike | -0.016 |
since | -0.016 |
cel | -0.016 |
stru | -0.016 |
fulfilled | -0.015 |
Token | garden |
Token ID | 11376 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
since | +0.027 |
unlike | +0.026 |
fulfilled | +0.026 |
stru | +0.025 |
cel | +0.025 |
Neg logit contributions | |
moms | -0.022 |
dads | -0.018 |
eps | -0.016 |
slide | -0.016 |
truck | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +9.21e-03 |
Pos logit contributions | |
since | +0.100 |
stru | +0.098 |
fulfilled | +0.096 |
unlike | +0.096 |
cel | +0.094 |
Neg logit contributions | |
moms | -0.081 |
dads | -0.063 |
slide | -0.061 |
truck | -0.059 |
towels | -0.059 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
stru | +0.014 |
cel | +0.014 |
Nice | +0.014 |
cess | +0.013 |
since | +0.013 |
Neg logit contributions | |
moms | -0.016 |
eps | -0.014 |
also | -0.013 |
slide | -0.013 |
dads | -0.013 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
Nice | +0.195 |
unlike | +0.193 |
since | +0.191 |
knowing | +0.188 |
cess | +0.188 |
Neg logit contributions | |
eps | -0.192 |
moms | -0.189 |
towels | -0.183 |
fountain | -0.178 |
ack | -0.168 |
Token | with |
Token ID | 351 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
cel | +0.110 |
stru | +0.109 |
fulfilled | +0.104 |
since | +0.104 |
unlike | +0.103 |
Neg logit contributions | |
moms | -0.110 |
slide | -0.095 |
towels | -0.091 |
dads | -0.090 |
fountain | -0.089 |
Token | all |
Token ID | 477 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.007 |
eps | -0.007 |
slide | -0.006 |
towels | -0.006 |
Token | sorts |
Token ID | 10524 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
moms | +0.009 |
dads | +0.008 |
slide | +0.008 |
eps | +0.007 |
towels | +0.007 |
Neg logit contributions | |
cel | -0.009 |
since | -0.008 |
unlike | -0.008 |
stru | -0.008 |
fulfilled | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
cel | +0.011 |
cess | +0.010 |
unlike | +0.010 |
since | +0.010 |
OUT | +0.010 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
towels | -0.009 |
cream | -0.009 |
says | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.009 |
eps | +0.008 |
slide | +0.008 |
truck | +0.008 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.010 |
fulfilled | -0.010 |
stru | -0.009 |
cel | -0.009 |
Token | wealthy |
Token ID | 11574 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.010 |
fulfilled | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
eps | -0.009 |
sled | -0.009 |
slide | -0.009 |
Token | flower |
Token ID | 15061 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
moms | +0.012 |
dads | +0.009 |
slide | +0.009 |
eps | +0.008 |
truck | +0.008 |
Neg logit contributions | |
since | -0.014 |
unlike | -0.013 |
fulfilled | -0.013 |
stru | -0.013 |
cel | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.010 |
fulfilled | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
eps | -0.009 |
slide | -0.008 |
sled | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
since | +0.063 |
cel | +0.060 |
unlike | +0.060 |
stru | +0.059 |
Nice | +0.058 |
Neg logit contributions | |
moms | -0.067 |
dads | -0.055 |
eps | -0.054 |
slide | -0.053 |
towels | -0.051 |
Token | bloom |
Token ID | 29955 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
since | +0.022 |
cel | +0.022 |
unlike | +0.021 |
stru | +0.021 |
Nice | +0.021 |
Neg logit contributions | |
moms | -0.026 |
dads | -0.023 |
eps | -0.022 |
slide | -0.022 |
dad | -0.021 |
Token | ed |
Token ID | 276 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
unlike | +0.201 |
cel | +0.200 |
stru | +0.195 |
since | +0.195 |
Mill | +0.194 |
Neg logit contributions | |
moms | -0.194 |
eps | -0.165 |
slide | -0.160 |
cream | -0.156 |
dads | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
stru | +0.053 |
cel | +0.052 |
unlike | +0.051 |
fulfilled | +0.050 |
since | +0.049 |
Neg logit contributions | |
moms | -0.050 |
dads | -0.041 |
slide | -0.040 |
towels | -0.040 |
eps | -0.040 |
Token | The |
Token ID | 383 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
unlike | +0.015 |
stru | +0.015 |
fulfilled | +0.015 |
cel | +0.015 |
since | +0.015 |
Neg logit contributions | |
moms | -0.018 |
Tom | -0.015 |
says | -0.014 |
Mom | -0.014 |
dads | -0.014 |
Token | other |
Token ID | 584 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.006 |
eps | +0.006 |
sled | +0.005 |
slide | +0.005 |
Neg logit contributions | |
since | -0.006 |
unlike | -0.005 |
fulfilled | -0.005 |
stru | -0.005 |
cel | -0.005 |
Token | flowers |
Token ID | 12734 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
moms | +0.119 |
dads | +0.097 |
slide | +0.091 |
eps | +0.091 |
towels | +0.086 |
Neg logit contributions | |
since | -0.129 |
unlike | -0.127 |
fulfilled | -0.126 |
stru | -0.121 |
cel | -0.120 |
Token | bridge |
Token ID | 7696 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
moms | +0.022 |
dads | +0.019 |
eps | +0.018 |
towels | +0.016 |
says | +0.016 |
Neg logit contributions | |
since | -0.024 |
unlike | -0.023 |
fulfilled | -0.022 |
stru | -0.021 |
cel | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.84e-04 |
Pos logit contributions | |
moms | +0.030 |
dads | +0.026 |
eps | +0.025 |
slide | +0.024 |
towels | +0.024 |
Neg logit contributions | |
since | -0.023 |
unlike | -0.022 |
fulfilled | -0.022 |
stru | -0.021 |
cel | -0.020 |
Token | It |
Token ID | 632 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
moms | +0.001 |
Tom | +0.001 |
Mom | +0.001 |
slide | +0.001 |
truck | +0.001 |
Neg logit contributions | |
fulfilled | -0.001 |
stru | -0.001 |
since | -0.001 |
lifetime | -0.001 |
unlike | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.009 |
eps | +0.008 |
towels | +0.008 |
sled | +0.008 |
Neg logit contributions | |
unlike | -0.009 |
since | -0.009 |
fulfilled | -0.008 |
cel | -0.008 |
stru | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
moms | +0.021 |
dads | +0.017 |
eps | +0.017 |
slide | +0.016 |
towels | +0.016 |
Neg logit contributions | |
since | -0.020 |
stru | -0.020 |
fulfilled | -0.020 |
cel | -0.019 |
unlike | -0.019 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
since | +0.048 |
stru | +0.047 |
cel | +0.047 |
fulfilled | +0.046 |
Nice | +0.046 |
Neg logit contributions | |
moms | -0.040 |
dads | -0.036 |
eps | -0.035 |
slide | -0.034 |
snow | -0.033 |
Token | oming |
Token ID | 3383 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
since | +0.175 |
unlike | +0.170 |
knowing | +0.164 |
Mill | +0.158 |
fulfilled | +0.157 |
Neg logit contributions | |
moms | -0.244 |
eps | -0.222 |
towels | -0.205 |
dads | -0.205 |
fountain | -0.204 |
Token | yet |
Token ID | 1865 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
stru | +0.133 |
cel | +0.133 |
fulfilled | +0.129 |
zing | +0.122 |
unlike | +0.122 |
Neg logit contributions | |
moms | -0.100 |
slide | -0.086 |
truck | -0.079 |
snow | -0.079 |
Tom | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
moms | +0.018 |
dads | +0.015 |
slide | +0.015 |
eps | +0.015 |
towels | +0.014 |
Neg logit contributions | |
since | -0.016 |
fulfilled | -0.016 |
stru | -0.016 |
unlike | -0.016 |
cel | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
fulfilled | +0.010 |
stru | +0.010 |
unlike | +0.010 |
since | +0.010 |
discovering | +0.009 |
Neg logit contributions | |
moms | -0.011 |
Tom | -0.010 |
Mom | -0.009 |
says | -0.009 |
slide | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
since | +0.043 |
unlike | +0.041 |
stru | +0.039 |
fulfilled | +0.038 |
cel | +0.035 |
Neg logit contributions | |
moms | -0.057 |
dads | -0.050 |
towels | -0.049 |
microwave | -0.048 |
slide | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.009 |
such | +0.009 |
cel | +0.009 |
Mill | +0.008 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.016 |
eps | -0.015 |
agree | -0.014 |
slide | -0.014 |
Token | herb |
Token ID | 21047 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
unlike | +0.042 |
since | +0.042 |
fulfilled | +0.039 |
knowing | +0.037 |
cel | +0.036 |
Neg logit contributions | |
moms | -0.046 |
dads | -0.039 |
eps | -0.039 |
towels | -0.034 |
Rex | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
since | +0.093 |
unlike | +0.091 |
fulfilled | +0.090 |
stru | +0.088 |
cel | +0.085 |
Neg logit contributions | |
moms | -0.111 |
dads | -0.094 |
eps | -0.089 |
slide | -0.089 |
truck | -0.087 |
Token | It |
Token ID | 632 |
Feature activation | +1.05e-04 |
Pos logit contributions | |
since | +0.015 |
unlike | +0.014 |
fulfilled | +0.014 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.021 |
dads | -0.018 |
eps | -0.017 |
slide | -0.017 |
truck | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
since | +0.000 |
unlike | +0.000 |
fulfilled | +0.000 |
cel | +0.000 |
stru | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
sled | -0.000 |
Token | lav |
Token ID | 21606 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
moms | +0.041 |
dads | +0.034 |
eps | +0.033 |
slide | +0.032 |
sled | +0.031 |
Neg logit contributions | |
since | -0.037 |
unlike | -0.037 |
fulfilled | -0.035 |
cel | -0.033 |
stru | -0.033 |
Token | ender |
Token ID | 2194 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
since | +0.225 |
fulfilled | +0.207 |
Nice | +0.200 |
knowing | +0.195 |
unlike | +0.192 |
Neg logit contributions | |
moms | -0.202 |
eps | -0.177 |
towels | -0.169 |
dads | -0.158 |
says | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
since | +0.104 |
fulfilled | +0.102 |
unlike | +0.102 |
stru | +0.100 |
cel | +0.095 |
Neg logit contributions | |
moms | -0.126 |
dads | -0.106 |
slide | -0.101 |
eps | -0.101 |
towels | -0.098 |
Token | " |
Token ID | 366 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.014 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.019 |
dads | -0.016 |
eps | -0.016 |
slide | -0.016 |
truck | -0.015 |
Token | That |
Token ID | 2504 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
since | +0.028 |
unlike | +0.027 |
fulfilled | +0.026 |
cel | +0.026 |
stru | +0.025 |
Neg logit contributions | |
moms | -0.032 |
dads | -0.028 |
truck | -0.026 |
eps | -0.026 |
slide | -0.025 |
Token | is |
Token ID | 318 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
moms | +0.059 |
dads | +0.044 |
slide | +0.044 |
eps | +0.041 |
truck | +0.041 |
Neg logit contributions | |
since | -0.093 |
fulfilled | -0.092 |
unlike | -0.090 |
stru | -0.090 |
cel | -0.086 |
Token | was |
Token ID | 373 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
since | +0.105 |
unlike | +0.104 |
fulfilled | +0.102 |
stru | +0.099 |
cel | +0.098 |
Neg logit contributions | |
moms | -0.096 |
dads | -0.079 |
eps | -0.077 |
slide | -0.074 |
truck | -0.071 |
Token | walking |
Token ID | 6155 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
since | +0.009 |
unlike | +0.009 |
stru | +0.009 |
Nice | +0.008 |
cel | +0.008 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.010 |
eps | -0.010 |
slide | -0.009 |
dad | -0.009 |
Token | through |
Token ID | 832 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
unlike | +0.051 |
stru | +0.051 |
cel | +0.051 |
fulfilled | +0.050 |
since | +0.050 |
Neg logit contributions | |
moms | -0.062 |
slide | -0.052 |
dads | -0.052 |
truck | -0.051 |
eps | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -8.23e-04 |
Pos logit contributions | |
unlike | +0.045 |
stru | +0.045 |
fulfilled | +0.044 |
since | +0.043 |
cel | +0.043 |
Neg logit contributions | |
moms | -0.035 |
slide | -0.029 |
towels | -0.027 |
fountain | -0.027 |
dad | -0.026 |
Token | fair |
Token ID | 3148 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
moms | +0.002 |
dads | +0.001 |
eps | +0.001 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
stru | -0.001 |
cel | -0.001 |
Token | yt |
Token ID | 20760 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
unlike | +0.009 |
since | +0.009 |
fulfilled | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.010 |
slide | -0.009 |
eps | -0.009 |
truck | -0.009 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.42e-04 |
Pos logit contributions | |
unlike | +0.223 |
cel | +0.217 |
fulfilled | +0.212 |
since | +0.210 |
stru | +0.202 |
Neg logit contributions | |
moms | -0.195 |
dads | -0.163 |
eps | -0.156 |
truck | -0.146 |
towels | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
since | +0.000 |
fulfilled | +0.000 |
unlike | +0.000 |
cel | +0.000 |
stru | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
sled | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
stru | +0.007 |
unlike | +0.007 |
since | +0.007 |
fulfilled | +0.007 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.010 |
dads | -0.008 |
slide | -0.008 |
Tom | -0.008 |
dad | -0.008 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
since | +0.050 |
fulfilled | +0.048 |
unlike | +0.047 |
stru | +0.045 |
cel | +0.044 |
Neg logit contributions | |
moms | -0.054 |
dads | -0.046 |
eps | -0.044 |
truck | -0.042 |
slide | -0.042 |
Token | asleep |
Token ID | 16039 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
since | +0.013 |
stru | +0.013 |
unlike | +0.013 |
fulfilled | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.025 |
slide | -0.022 |
dads | -0.022 |
sled | -0.022 |
eps | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
since | +0.022 |
unlike | +0.021 |
fulfilled | +0.021 |
stru | +0.020 |
cel | +0.019 |
Neg logit contributions | |
moms | -0.029 |
dads | -0.025 |
eps | -0.025 |
slide | -0.023 |
truck | -0.023 |
Token | garden |
Token ID | 11376 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
since | +0.029 |
unlike | +0.028 |
fulfilled | +0.028 |
stru | +0.027 |
cel | +0.027 |
Neg logit contributions | |
moms | -0.021 |
dads | -0.017 |
slide | -0.016 |
eps | -0.016 |
truck | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
unlike | +0.075 |
since | +0.074 |
fulfilled | +0.074 |
stru | +0.073 |
cel | +0.071 |
Neg logit contributions | |
moms | -0.083 |
slide | -0.069 |
dads | -0.069 |
eps | -0.066 |
truck | -0.066 |
Token | it |
Token ID | 340 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
since | +0.006 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.007 |
eps | -0.007 |
slide | -0.007 |
truck | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
since | +0.011 |
fulfilled | +0.011 |
stru | +0.011 |
cess | +0.010 |
unlike | +0.010 |
Neg logit contributions | |
moms | -0.006 |
slide | -0.005 |
eps | -0.005 |
says | -0.005 |
truck | -0.005 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.004 |
eps | +0.004 |
slide | +0.004 |
dad | +0.004 |
Neg logit contributions | |
stru | -0.006 |
since | -0.006 |
cel | -0.006 |
fulfilled | -0.006 |
cess | -0.006 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
since | +0.185 |
unlike | +0.181 |
knowing | +0.178 |
cess | +0.171 |
Nice | +0.166 |
Neg logit contributions | |
eps | -0.202 |
moms | -0.200 |
fountain | -0.183 |
slide | -0.174 |
towels | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
cel | +0.113 |
stru | +0.113 |
fulfilled | +0.110 |
since | +0.109 |
unlike | +0.106 |
Neg logit contributions | |
moms | -0.094 |
slide | -0.080 |
truck | -0.075 |
eps | -0.074 |
snow | -0.074 |
Token | It |
Token ID | 632 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
fulfilled | +0.007 |
since | +0.007 |
stru | +0.007 |
unlike | +0.007 |
knowing | +0.007 |
Neg logit contributions | |
moms | -0.008 |
Tom | -0.007 |
slide | -0.007 |
Mom | -0.006 |
truck | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
since | +0.004 |
fulfilled | +0.004 |
unlike | +0.004 |
stru | +0.003 |
cel | +0.003 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
truck | -0.002 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
since | +0.076 |
cel | +0.075 |
cess | +0.074 |
stru | +0.072 |
Nice | +0.072 |
Neg logit contributions | |
moms | -0.056 |
slide | -0.044 |
snow | -0.042 |
dads | -0.042 |
eps | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
moms | +0.029 |
dads | +0.024 |
eps | +0.024 |
towels | +0.023 |
slide | +0.022 |
Neg logit contributions | |
since | -0.026 |
unlike | -0.024 |
fulfilled | -0.024 |
stru | -0.023 |
knowing | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
moms | +0.013 |
dads | +0.011 |
eps | +0.011 |
slide | +0.010 |
truck | +0.010 |
Neg logit contributions | |
since | -0.009 |
unlike | -0.009 |
fulfilled | -0.008 |
stru | -0.008 |
cel | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +9.21e-04 |
Pos logit contributions | |
cel | +0.020 |
stru | +0.019 |
fulfilled | +0.019 |
since | +0.018 |
unlike | +0.018 |
Neg logit contributions | |
moms | -0.026 |
dads | -0.021 |
slide | -0.021 |
dad | -0.021 |
truck | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
fulfilled | +0.001 |
stru | +0.001 |
cel | +0.001 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.001 |
eps | -0.001 |
slide | -0.001 |
towels | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
since | +0.032 |
unlike | +0.031 |
Nice | +0.031 |
stru | +0.031 |
fulfilled | +0.031 |
Neg logit contributions | |
moms | -0.023 |
eps | -0.019 |
slide | -0.018 |
dads | -0.017 |
says | -0.017 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
since | +0.003 |
cel | +0.003 |
stru | +0.003 |
Nice | +0.003 |
unlike | +0.003 |
Neg logit contributions | |
moms | -0.004 |
eps | -0.003 |
dads | -0.003 |
dad | -0.003 |
slide | -0.003 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
since | +0.185 |
unlike | +0.181 |
Bun | +0.170 |
Nice | +0.169 |
cess | +0.167 |
Neg logit contributions | |
moms | -0.179 |
eps | -0.178 |
towels | -0.167 |
fountain | -0.167 |
ack | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
since | +0.091 |
stru | +0.090 |
cel | +0.090 |
unlike | +0.089 |
fulfilled | +0.089 |
Neg logit contributions | |
moms | -0.113 |
slide | -0.095 |
dads | -0.095 |
eps | -0.092 |
truck | -0.092 |
Token | growing |
Token ID | 3957 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
since | +0.019 |
unlike | +0.019 |
fulfilled | +0.018 |
stru | +0.018 |
cel | +0.017 |
Neg logit contributions | |
moms | -0.030 |
dads | -0.026 |
eps | -0.025 |
slide | -0.025 |
truck | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
cel | +0.097 |
cess | +0.093 |
since | +0.090 |
ulent | +0.088 |
Nice | +0.088 |
Neg logit contributions | |
moms | -0.083 |
cream | -0.074 |
fountain | -0.072 |
snow | -0.072 |
towels | -0.070 |
Token | Even |
Token ID | 3412 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
since | +0.004 |
unlike | +0.004 |
fulfilled | +0.004 |
stru | +0.003 |
cel | +0.003 |
Neg logit contributions | |
moms | -0.004 |
dads | -0.004 |
eps | -0.004 |
slide | -0.004 |
towels | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
fulfilled | +0.015 |
since | +0.015 |
unlike | +0.015 |
stru | +0.014 |
knowing | +0.013 |
Neg logit contributions | |
moms | -0.020 |
dads | -0.017 |
eps | -0.016 |
slide | -0.016 |
truck | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
cel | +0.009 |
fulfilled | +0.009 |
stru | +0.009 |
unlike | +0.008 |
ulent | +0.008 |
Neg logit contributions | |
moms | -0.007 |
dad | -0.006 |
dads | -0.006 |
slide | -0.006 |
truck | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
moms | +0.018 |
dads | +0.015 |
eps | +0.014 |
slide | +0.014 |
truck | +0.013 |
Neg logit contributions | |
since | -0.017 |
unlike | -0.017 |
fulfilled | -0.016 |
stru | -0.016 |
cel | -0.016 |
Token | flower |
Token ID | 15061 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
moms | +0.027 |
dads | +0.023 |
eps | +0.022 |
slide | +0.021 |
truck | +0.020 |
Neg logit contributions | |
since | -0.033 |
unlike | -0.032 |
fulfilled | -0.032 |
stru | -0.031 |
cel | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
since | +0.058 |
unlike | +0.056 |
fulfilled | +0.056 |
stru | +0.054 |
cel | +0.053 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.042 |
eps | -0.040 |
slide | -0.039 |
truck | -0.038 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
since | +0.003 |
cel | +0.003 |
Nice | +0.003 |
stru | +0.003 |
unlike | +0.003 |
Neg logit contributions | |
moms | -0.003 |
eps | -0.003 |
dads | -0.003 |
dad | -0.003 |
also | -0.003 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
since | +0.176 |
unlike | +0.174 |
cess | +0.166 |
Nice | +0.164 |
solving | +0.164 |
Neg logit contributions | |
moms | -0.198 |
eps | -0.193 |
towels | -0.183 |
fountain | -0.178 |
outed | -0.165 |
Token | again |
Token ID | 757 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
stru | +0.092 |
cel | +0.092 |
since | +0.091 |
fulfilled | +0.090 |
unlike | +0.090 |
Neg logit contributions | |
moms | -0.114 |
slide | -0.096 |
dads | -0.095 |
truck | -0.093 |
eps | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
eps | +0.006 |
slide | +0.006 |
truck | +0.006 |
Neg logit contributions | |
unlike | -0.005 |
since | -0.005 |
fulfilled | -0.005 |
stru | -0.005 |
cel | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
since | +0.006 |
stru | +0.006 |
unlike | +0.006 |
fulfilled | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.007 |
dads | -0.006 |
slide | -0.006 |
truck | -0.006 |
eps | -0.006 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
moms | +0.020 |
dads | +0.017 |
eps | +0.017 |
slide | +0.016 |
towels | +0.016 |
Neg logit contributions | |
since | -0.017 |
fulfilled | -0.016 |
unlike | -0.016 |
stru | -0.015 |
knowing | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
since | +0.056 |
fulfilled | +0.052 |
stru | +0.051 |
unlike | +0.050 |
cel | +0.048 |
Neg logit contributions | |
moms | -0.047 |
dads | -0.039 |
snowball | -0.037 |
microwave | -0.036 |
eps | -0.036 |
Token | like |
Token ID | 588 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
cel | +0.070 |
since | +0.070 |
unlike | +0.069 |
stru | +0.067 |
Nice | +0.065 |
Neg logit contributions | |
moms | -0.062 |
dads | -0.051 |
dad | -0.049 |
eps | -0.049 |
slide | -0.048 |
Token | they |
Token ID | 484 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
eps | +0.005 |
slide | +0.005 |
truck | +0.005 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.010 |
fulfilled | -0.010 |
cel | -0.009 |
stru | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
since | +0.023 |
unlike | +0.022 |
fulfilled | +0.022 |
stru | +0.021 |
cel | +0.021 |
Neg logit contributions | |
moms | -0.022 |
dads | -0.018 |
eps | -0.018 |
slide | -0.017 |
truck | -0.016 |
Token | been |
Token ID | 587 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Nice | +0.073 |
unlike | +0.071 |
since | +0.070 |
cel | +0.069 |
stru | +0.067 |
Neg logit contributions | |
moms | -0.075 |
eps | -0.064 |
dads | -0.063 |
dad | -0.059 |
towels | -0.058 |
Token | transported |
Token ID | 18665 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Nice | +0.038 |
since | +0.034 |
unlike | +0.034 |
umm | +0.033 |
osity | +0.033 |
Neg logit contributions | |
moms | -0.033 |
eps | -0.031 |
dads | -0.030 |
dad | -0.029 |
slide | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
cel | +0.153 |
unlike | +0.142 |
fulfilled | +0.133 |
since | +0.128 |
stru | +0.128 |
Neg logit contributions | |
moms | -0.274 |
dads | -0.247 |
eps | -0.232 |
dad | -0.232 |
towels | -0.228 |
Token | a |
Token ID | 257 |
Feature activation | -5.51e-03 |
Pos logit contributions | |
since | +0.060 |
unlike | +0.059 |
fulfilled | +0.058 |
stru | +0.056 |
cel | +0.056 |
Neg logit contributions | |
moms | -0.056 |
dads | -0.047 |
slide | -0.045 |
eps | -0.044 |
towels | -0.042 |
Token | land |
Token ID | 1956 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.009 |
eps | +0.009 |
slide | +0.009 |
truck | +0.008 |
Neg logit contributions | |
since | -0.008 |
unlike | -0.008 |
fulfilled | -0.008 |
stru | -0.007 |
cel | -0.007 |
Token | far |
Token ID | 1290 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
since | +0.054 |
unlike | +0.053 |
fulfilled | +0.052 |
stru | +0.050 |
cel | +0.049 |
Neg logit contributions | |
moms | -0.078 |
dads | -0.067 |
eps | -0.064 |
slide | -0.063 |
truck | -0.062 |
Token | away |
Token ID | 1497 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
moms | +0.004 |
slide | +0.003 |
dads | +0.003 |
truck | +0.003 |
eps | +0.003 |
Neg logit contributions | |
unlike | -0.006 |
cel | -0.006 |
stru | -0.006 |
fulfilled | -0.006 |
ulent | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
moms | +0.058 |
dads | +0.048 |
slide | +0.047 |
eps | +0.046 |
says | +0.045 |
Neg logit contributions | |
unlike | -0.049 |
since | -0.048 |
cel | -0.048 |
fulfilled | -0.047 |
stru | -0.046 |
Token | other |
Token ID | 584 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.014 |
stru | +0.014 |
cel | +0.014 |
Neg logit contributions | |
moms | -0.012 |
dads | -0.009 |
slide | -0.009 |
eps | -0.009 |
towels | -0.008 |
Token | flowers |
Token ID | 12734 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
moms | +0.106 |
dads | +0.083 |
slide | +0.079 |
eps | +0.076 |
says | +0.073 |
Neg logit contributions | |
unlike | -0.125 |
fulfilled | -0.125 |
since | -0.125 |
cel | -0.121 |
stru | -0.120 |
Token | were |
Token ID | 547 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
since | +0.049 |
unlike | +0.048 |
fulfilled | +0.047 |
stru | +0.045 |
cel | +0.045 |
Neg logit contributions | |
moms | -0.039 |
dads | -0.032 |
eps | -0.030 |
slide | -0.029 |
truck | -0.028 |
Token | already |
Token ID | 1541 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
moms | +0.033 |
dads | +0.028 |
eps | +0.027 |
slide | +0.026 |
towels | +0.025 |
Neg logit contributions | |
since | -0.033 |
unlike | -0.032 |
stru | -0.032 |
fulfilled | -0.032 |
cel | -0.032 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
since | +0.054 |
stru | +0.053 |
cel | +0.053 |
unlike | +0.053 |
Nice | +0.052 |
Neg logit contributions | |
moms | -0.048 |
eps | -0.041 |
dads | -0.040 |
towels | -0.039 |
slide | -0.038 |
Token | oming |
Token ID | 3383 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
unlike | +0.186 |
since | +0.179 |
Nice | +0.173 |
cess | +0.171 |
knowing | +0.169 |
Neg logit contributions | |
moms | -0.199 |
eps | -0.195 |
towels | -0.182 |
fountain | -0.179 |
dads | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
stru | +0.102 |
cel | +0.101 |
unlike | +0.100 |
fulfilled | +0.100 |
since | +0.100 |
Neg logit contributions | |
moms | -0.088 |
slide | -0.071 |
eps | -0.070 |
dads | -0.070 |
towels | -0.070 |
Token | She |
Token ID | 1375 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.007 |
dads | -0.006 |
eps | -0.005 |
slide | -0.005 |
towels | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
since | +0.039 |
unlike | +0.036 |
fulfilled | +0.035 |
stru | +0.034 |
cel | +0.034 |
Neg logit contributions | |
moms | -0.043 |
dads | -0.038 |
sled | -0.035 |
truck | -0.035 |
eps | -0.035 |
Token | feeling |
Token ID | 4203 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.008 |
eps | +0.008 |
slide | +0.008 |
truck | +0.008 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.010 |
fulfilled | -0.010 |
stru | -0.010 |
cel | -0.010 |
Token | singing |
Token ID | 13777 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
moms | +0.059 |
dads | +0.051 |
eps | +0.050 |
slide | +0.048 |
truck | +0.047 |
Neg logit contributions | |
since | -0.042 |
unlike | -0.040 |
fulfilled | -0.039 |
stru | -0.039 |
cel | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
since | +0.062 |
cel | +0.061 |
stru | +0.060 |
unlike | +0.060 |
fulfilled | +0.060 |
Neg logit contributions | |
moms | -0.062 |
dads | -0.052 |
eps | -0.052 |
towels | -0.050 |
truck | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
since | +0.029 |
unlike | +0.028 |
fulfilled | +0.027 |
stru | +0.026 |
cel | +0.026 |
Neg logit contributions | |
moms | -0.036 |
dads | -0.031 |
eps | -0.030 |
slide | -0.029 |
truck | -0.028 |
Token | flowers |
Token ID | 12734 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
since | +0.026 |
unlike | +0.024 |
fulfilled | +0.024 |
exploring | +0.022 |
cel | +0.022 |
Neg logit contributions | |
moms | -0.029 |
eps | -0.025 |
dads | -0.025 |
agree | -0.023 |
sled | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
since | +0.061 |
unlike | +0.059 |
fulfilled | +0.059 |
stru | +0.057 |
cel | +0.056 |
Neg logit contributions | |
moms | -0.049 |
dads | -0.040 |
eps | -0.039 |
slide | -0.038 |
truck | -0.036 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
moms | +0.034 |
dads | +0.030 |
eps | +0.029 |
slide | +0.028 |
towels | +0.027 |
Neg logit contributions | |
since | -0.024 |
unlike | -0.023 |
fulfilled | -0.022 |
stru | -0.022 |
cel | -0.022 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
since | +0.176 |
unlike | +0.172 |
cess | +0.162 |
knowing | +0.159 |
Nice | +0.158 |
Neg logit contributions | |
eps | -0.207 |
moms | -0.198 |
towels | -0.191 |
microwave | -0.180 |
fountain | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
cel | +0.102 |
stru | +0.100 |
since | +0.099 |
fulfilled | +0.098 |
unlike | +0.098 |
Neg logit contributions | |
moms | -0.098 |
slide | -0.083 |
dads | -0.082 |
towels | -0.081 |
eps | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
since | +0.023 |
unlike | +0.023 |
fulfilled | +0.022 |
stru | +0.021 |
cel | +0.020 |
Neg logit contributions | |
moms | -0.026 |
dads | -0.022 |
eps | -0.021 |
slide | -0.021 |
truck | -0.020 |
Token | baby |
Token ID | 5156 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
since | +0.033 |
unlike | +0.032 |
fulfilled | +0.031 |
Mill | +0.029 |
exploring | +0.029 |
Neg logit contributions | |
moms | -0.037 |
eps | -0.032 |
dads | -0.032 |
sled | -0.029 |
agree | -0.029 |
Token | rabbits |
Token ID | 33043 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
moms | +0.032 |
dads | +0.027 |
eps | +0.026 |
slide | +0.025 |
towels | +0.024 |
Neg logit contributions | |
since | -0.031 |
unlike | -0.030 |
fulfilled | -0.029 |
stru | -0.028 |
cel | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
since | +0.023 |
unlike | +0.022 |
fulfilled | +0.021 |
Mill | +0.019 |
stru | +0.019 |
Neg logit contributions | |
moms | -0.033 |
dads | -0.029 |
eps | -0.029 |
slide | -0.026 |
truck | -0.026 |
Token | world |
Token ID | 995 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
since | +0.040 |
unlike | +0.039 |
fulfilled | +0.038 |
stru | +0.037 |
cel | +0.037 |
Neg logit contributions | |
moms | -0.039 |
dads | -0.032 |
eps | -0.031 |
slide | -0.031 |
truck | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
since | +0.071 |
unlike | +0.070 |
fulfilled | +0.069 |
stru | +0.067 |
cel | +0.066 |
Neg logit contributions | |
moms | -0.082 |
dads | -0.069 |
slide | -0.067 |
eps | -0.067 |
truck | -0.064 |
Token | It |
Token ID | 632 |
Feature activation | +2.81e-04 |
Pos logit contributions | |
stru | +0.002 |
fulfilled | +0.002 |
unlike | +0.002 |
zing | +0.002 |
ulent | +0.002 |
Neg logit contributions | |
moms | -0.003 |
Tom | -0.002 |
Mom | -0.002 |
slide | -0.002 |
says | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
fulfilled | +0.001 |
stru | +0.000 |
cel | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
truck | -0.000 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
moms | +0.010 |
also | +0.008 |
dads | +0.008 |
dad | +0.008 |
snow | +0.008 |
Neg logit contributions | |
stru | -0.012 |
cel | -0.011 |
since | -0.011 |
cess | -0.011 |
fulfilled | -0.011 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
since | +0.188 |
knowing | +0.183 |
cess | +0.182 |
unlike | +0.180 |
solving | +0.174 |
Neg logit contributions | |
eps | -0.178 |
moms | -0.178 |
fountain | -0.166 |
ack | -0.156 |
towels | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
cel | +0.122 |
stru | +0.121 |
fulfilled | +0.116 |
cess | +0.116 |
zing | +0.112 |
Neg logit contributions | |
moms | -0.101 |
slide | -0.088 |
fountain | -0.084 |
towels | -0.084 |
snow | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
since | +0.039 |
unlike | +0.038 |
fulfilled | +0.038 |
stru | +0.036 |
cel | +0.036 |
Neg logit contributions | |
moms | -0.045 |
dads | -0.038 |
eps | -0.036 |
slide | -0.035 |
truck | -0.034 |
Token | sun |
Token ID | 4252 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
since | +0.043 |
unlike | +0.042 |
fulfilled | +0.041 |
stru | +0.041 |
cel | +0.040 |
Neg logit contributions | |
moms | -0.040 |
dads | -0.033 |
eps | -0.032 |
slide | -0.032 |
truck | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
since | +0.068 |
unlike | +0.066 |
fulfilled | +0.065 |
stru | +0.063 |
cel | +0.061 |
Neg logit contributions | |
moms | -0.090 |
dads | -0.077 |
eps | -0.074 |
slide | -0.073 |
truck | -0.071 |
Token | sad |
Token ID | 6507 |
Feature activation | +9.27e-03 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
cel | +0.007 |
stru | +0.007 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.006 |
eps | -0.006 |
slide | -0.006 |
dad | -0.006 |
Token | because |
Token ID | 780 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
fulfilled | +0.014 |
stru | +0.014 |
cel | +0.014 |
unlike | +0.013 |
since | +0.013 |
Neg logit contributions | |
moms | -0.017 |
slide | -0.014 |
dads | -0.014 |
truck | -0.014 |
dad | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
since | +0.003 |
unlike | +0.003 |
fulfilled | +0.003 |
Mill | +0.003 |
stru | +0.003 |
Neg logit contributions | |
moms | -0.004 |
dads | -0.004 |
eps | -0.004 |
slide | -0.003 |
towels | -0.003 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
since | +0.023 |
fulfilled | +0.022 |
unlike | +0.022 |
stru | +0.022 |
Nice | +0.021 |
Neg logit contributions | |
moms | -0.018 |
slide | -0.014 |
eps | -0.014 |
dads | -0.013 |
says | -0.013 |
Token | 't |
Token ID | 470 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
since | +0.048 |
unlike | +0.045 |
fulfilled | +0.045 |
stru | +0.044 |
cel | +0.044 |
Neg logit contributions | |
moms | -0.069 |
eps | -0.057 |
slide | -0.056 |
dads | -0.056 |
truck | -0.054 |
Token | bloom |
Token ID | 29955 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
unlike | +0.031 |
since | +0.031 |
stru | +0.030 |
cel | +0.030 |
fulfilled | +0.030 |
Neg logit contributions | |
moms | -0.024 |
eps | -0.020 |
slide | -0.020 |
dads | -0.020 |
agree | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
unlike | +0.196 |
since | +0.194 |
cel | +0.191 |
discovering | +0.187 |
fulfilled | +0.187 |
Neg logit contributions | |
moms | -0.189 |
eps | -0.162 |
dads | -0.151 |
slide | -0.149 |
towels | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
since | +0.008 |
stru | +0.008 |
unlike | +0.008 |
fulfilled | +0.008 |
cel | +0.008 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.007 |
dad | -0.007 |
slide | -0.007 |
truck | -0.006 |
Token | other |
Token ID | 584 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
since | +0.037 |
unlike | +0.036 |
fulfilled | +0.036 |
stru | +0.034 |
cel | +0.034 |
Neg logit contributions | |
moms | -0.036 |
dads | -0.030 |
eps | -0.029 |
slide | -0.027 |
truck | -0.027 |
Token | flowers |
Token ID | 12734 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
moms | +0.075 |
dads | +0.058 |
slide | +0.057 |
fountain | +0.052 |
eps | +0.052 |
Neg logit contributions | |
fulfilled | -0.089 |
since | -0.088 |
unlike | -0.088 |
stru | -0.085 |
cel | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
since | +0.058 |
unlike | +0.056 |
fulfilled | +0.055 |
stru | +0.053 |
cel | +0.052 |
Neg logit contributions | |
moms | -0.071 |
dads | -0.061 |
eps | -0.058 |
slide | -0.056 |
truck | -0.054 |
Token | opus |
Token ID | 25790 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
moms | +0.133 |
dads | +0.113 |
eps | +0.111 |
towels | +0.106 |
slide | +0.105 |
Neg logit contributions | |
since | -0.115 |
unlike | -0.113 |
fulfilled | -0.111 |
stru | -0.108 |
cel | -0.105 |
Token | why |
Token ID | 1521 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
moms | +0.117 |
dads | +0.101 |
eps | +0.098 |
slide | +0.096 |
truck | +0.093 |
Neg logit contributions | |
since | -0.073 |
unlike | -0.071 |
fulfilled | -0.069 |
stru | -0.066 |
cel | -0.064 |
Token | it |
Token ID | 340 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
moms | +0.082 |
dads | +0.070 |
eps | +0.069 |
slide | +0.064 |
towels | +0.064 |
Neg logit contributions | |
since | -0.068 |
unlike | -0.066 |
fulfilled | -0.064 |
stru | -0.061 |
cel | -0.058 |
Token | wasn |
Token ID | 2492 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
moms | +0.043 |
dads | +0.037 |
eps | +0.035 |
slide | +0.033 |
towels | +0.033 |
Neg logit contributions | |
since | -0.044 |
unlike | -0.043 |
fulfilled | -0.042 |
stru | -0.040 |
cel | -0.039 |
Token | 't |
Token ID | 470 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
since | +0.037 |
unlike | +0.035 |
fulfilled | +0.035 |
stru | +0.033 |
cel | +0.033 |
Neg logit contributions | |
moms | -0.062 |
dads | -0.054 |
eps | -0.053 |
slide | -0.052 |
truck | -0.050 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
cel | +0.029 |
since | +0.029 |
stru | +0.028 |
fulfilled | +0.028 |
unlike | +0.028 |
Neg logit contributions | |
moms | -0.032 |
dads | -0.030 |
eps | -0.029 |
slide | -0.028 |
dad | -0.027 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
unlike | +0.129 |
since | +0.129 |
cel | +0.128 |
fulfilled | +0.117 |
discovering | +0.116 |
Neg logit contributions | |
moms | -0.258 |
eps | -0.228 |
dads | -0.223 |
towels | -0.217 |
slide | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -9.82e-04 |
Pos logit contributions | |
stru | +0.101 |
cel | +0.101 |
fulfilled | +0.101 |
since | +0.100 |
unlike | +0.099 |
Neg logit contributions | |
moms | -0.110 |
dads | -0.091 |
slide | -0.091 |
truck | -0.087 |
eps | -0.087 |
Token | The |
Token ID | 383 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
moms | +0.002 |
dads | +0.002 |
slide | +0.002 |
truck | +0.002 |
eps | +0.002 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
stru | -0.001 |
cel | -0.001 |
Token | oct |
Token ID | 19318 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
moms | +0.019 |
eps | +0.018 |
dads | +0.017 |
towels | +0.016 |
sled | +0.016 |
Neg logit contributions | |
since | -0.015 |
unlike | -0.014 |
fulfilled | -0.014 |
stru | -0.013 |
Nice | -0.013 |
Token | opus |
Token ID | 25790 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
moms | +0.142 |
dads | +0.122 |
eps | +0.117 |
towels | +0.114 |
slide | +0.112 |
Neg logit contributions | |
unlike | -0.116 |
since | -0.115 |
fulfilled | -0.112 |
stru | -0.110 |
cel | -0.108 |
Token | This |
Token ID | 1212 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
since | +0.051 |
unlike | +0.049 |
fulfilled | +0.048 |
stru | +0.047 |
cel | +0.045 |
Neg logit contributions | |
moms | -0.048 |
dads | -0.041 |
eps | -0.039 |
truck | -0.038 |
slide | -0.038 |
Token | is |
Token ID | 318 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
moms | +0.043 |
dads | +0.035 |
eps | +0.034 |
towels | +0.030 |
slide | +0.030 |
Neg logit contributions | |
since | -0.057 |
unlike | -0.057 |
fulfilled | -0.055 |
cel | -0.054 |
stru | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
moms | +0.045 |
dads | +0.037 |
eps | +0.035 |
slide | +0.034 |
truck | +0.033 |
Neg logit contributions | |
since | -0.049 |
unlike | -0.048 |
fulfilled | -0.048 |
stru | -0.047 |
cel | -0.046 |
Token | cherry |
Token ID | 23612 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
since | +0.024 |
unlike | +0.024 |
fulfilled | +0.023 |
stru | +0.022 |
cel | +0.022 |
Neg logit contributions | |
moms | -0.027 |
dads | -0.023 |
eps | -0.023 |
slide | -0.021 |
towels | -0.021 |
Token | bl |
Token ID | 698 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
since | +0.068 |
unlike | +0.063 |
fulfilled | +0.061 |
cel | +0.058 |
stru | +0.056 |
Neg logit contributions | |
moms | -0.090 |
dads | -0.079 |
eps | -0.079 |
sled | -0.071 |
towels | -0.071 |
Token | ossom |
Token ID | 25548 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
since | +0.072 |
unlike | +0.069 |
fulfilled | +0.069 |
solving | +0.065 |
stru | +0.064 |
Neg logit contributions | |
moms | -0.082 |
dads | -0.069 |
eps | -0.065 |
slide | -0.064 |
truck | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
fulfilled | +0.184 |
stru | +0.183 |
since | +0.183 |
unlike | +0.181 |
cel | +0.173 |
Neg logit contributions | |
moms | -0.216 |
dads | -0.180 |
slide | -0.177 |
truck | -0.169 |
towels | -0.167 |
Token | It |
Token ID | 632 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
fulfilled | +0.017 |
since | +0.017 |
stru | +0.017 |
unlike | +0.017 |
zing | +0.016 |
Neg logit contributions | |
moms | -0.024 |
dads | -0.019 |
says | -0.019 |
slide | -0.019 |
Tom | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.004 |
eps | +0.004 |
slide | +0.004 |
towels | +0.004 |
Neg logit contributions | |
since | -0.007 |
unlike | -0.007 |
fulfilled | -0.007 |
stru | -0.007 |
cel | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
moms | +0.033 |
dads | +0.028 |
eps | +0.026 |
slide | +0.026 |
truck | +0.025 |
Neg logit contributions | |
since | -0.031 |
unlike | -0.030 |
fulfilled | -0.030 |
stru | -0.029 |
cel | -0.028 |
Token | special |
Token ID | 2041 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
since | +0.028 |
unlike | +0.027 |
fulfilled | +0.027 |
cel | +0.025 |
stru | +0.025 |
Neg logit contributions | |
moms | -0.033 |
dads | -0.028 |
eps | -0.027 |
towels | -0.025 |
slide | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-04 |
Pos logit contributions | |
moms | +0.031 |
dads | +0.026 |
Tom | +0.024 |
dad | +0.024 |
slide | +0.023 |
Neg logit contributions | |
unlike | -0.027 |
cel | -0.027 |
stru | -0.027 |
fulfilled | -0.026 |
since | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
moms | +0.001 |
dads | +0.001 |
eps | +0.001 |
slide | +0.001 |
truck | +0.001 |
Neg logit contributions | |
since | -0.000 |
unlike | -0.000 |
fulfilled | -0.000 |
stru | -0.000 |
cel | -0.000 |
Token | whole |
Token ID | 2187 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
since | +0.006 |
fulfilled | +0.006 |
unlike | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.007 |
dads | -0.006 |
eps | -0.006 |
sled | -0.006 |
snowball | -0.006 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
moms | +0.044 |
dads | +0.037 |
eps | +0.036 |
slide | +0.035 |
truck | +0.034 |
Neg logit contributions | |
since | -0.037 |
unlike | -0.036 |
fulfilled | -0.035 |
stru | -0.034 |
cel | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
since | +0.070 |
unlike | +0.068 |
fulfilled | +0.067 |
stru | +0.066 |
cel | +0.066 |
Neg logit contributions | |
moms | -0.060 |
dads | -0.048 |
slide | -0.045 |
eps | -0.045 |
truck | -0.044 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
stru | +0.008 |
cel | +0.008 |
since | +0.008 |
Nice | +0.008 |
cess | +0.008 |
Neg logit contributions | |
moms | -0.010 |
eps | -0.009 |
dads | -0.009 |
towels | -0.009 |
slide | -0.009 |
Token | oming |
Token ID | 3383 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
unlike | +0.180 |
since | +0.179 |
cess | +0.175 |
cel | +0.174 |
Nice | +0.172 |
Neg logit contributions | |
moms | -0.175 |
eps | -0.168 |
towels | -0.165 |
fountain | -0.160 |
tub | -0.151 |
Token | in |
Token ID | 287 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
cel | +0.092 |
stru | +0.092 |
since | +0.090 |
fulfilled | +0.090 |
unlike | +0.089 |
Neg logit contributions | |
moms | -0.106 |
slide | -0.089 |
dads | -0.088 |
towels | -0.087 |
eps | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
since | +0.032 |
unlike | +0.032 |
fulfilled | +0.031 |
stru | +0.031 |
cel | +0.030 |
Neg logit contributions | |
moms | -0.035 |
dads | -0.029 |
eps | -0.028 |
slide | -0.027 |
towels | -0.027 |
Token | new |
Token ID | 649 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.005 |
eps | +0.005 |
slide | +0.005 |
truck | +0.005 |
Neg logit contributions | |
since | -0.005 |
unlike | -0.005 |
fulfilled | -0.005 |
stru | -0.004 |
cel | -0.004 |
Token | fashion |
Token ID | 6977 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
moms | +0.010 |
slide | +0.009 |
dads | +0.009 |
fountain | +0.008 |
towels | +0.008 |
Neg logit contributions | |
unlike | -0.011 |
stru | -0.011 |
fulfilled | -0.010 |
since | -0.010 |
cel | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
fulfilled | +0.084 |
unlike | +0.084 |
since | +0.084 |
stru | +0.083 |
cel | +0.082 |
Neg logit contributions | |
moms | -0.069 |
dads | -0.055 |
dad | -0.055 |
towels | -0.054 |
slide | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-04 |
Pos logit contributions | |
moms | +0.055 |
slide | +0.046 |
dads | +0.045 |
eps | +0.045 |
towels | +0.045 |
Neg logit contributions | |
unlike | -0.046 |
since | -0.046 |
fulfilled | -0.044 |
cel | -0.044 |
stru | -0.043 |
Token | she |
Token ID | 673 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
since | +0.000 |
unlike | +0.000 |
fulfilled | +0.000 |
stru | +0.000 |
Mill | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
truck | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
since | +0.048 |
unlike | +0.047 |
fulfilled | +0.046 |
stru | +0.044 |
cel | +0.043 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.043 |
eps | -0.041 |
slide | -0.040 |
truck | -0.039 |
Token | been |
Token ID | 587 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
since | +0.061 |
unlike | +0.060 |
cel | +0.059 |
stru | +0.058 |
Nice | +0.058 |
Neg logit contributions | |
moms | -0.059 |
dads | -0.049 |
eps | -0.048 |
slide | -0.046 |
dad | -0.045 |
Token | transported |
Token ID | 18665 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Nice | +0.025 |
since | +0.024 |
unlike | +0.023 |
stru | +0.022 |
cel | +0.022 |
Neg logit contributions | |
moms | -0.028 |
eps | -0.027 |
dads | -0.025 |
dad | -0.024 |
slide | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
cel | +0.171 |
unlike | +0.149 |
cess | +0.142 |
fulfilled | +0.140 |
zing | +0.138 |
Neg logit contributions | |
moms | -0.237 |
dads | -0.209 |
dad | -0.205 |
eps | -0.203 |
Tom | -0.201 |
Token | a |
Token ID | 257 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
since | +0.053 |
unlike | +0.053 |
fulfilled | +0.051 |
stru | +0.051 |
cel | +0.050 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.043 |
eps | -0.041 |
slide | -0.041 |
towels | -0.038 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
moms | +0.014 |
dads | +0.012 |
slide | +0.011 |
eps | +0.011 |
truck | +0.011 |
Neg logit contributions | |
since | -0.009 |
unlike | -0.009 |
fulfilled | -0.008 |
stru | -0.008 |
cel | -0.008 |
Token | place |
Token ID | 1295 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
stru | +0.045 |
unlike | +0.044 |
fulfilled | +0.043 |
since | +0.043 |
cel | +0.043 |
Neg logit contributions | |
moms | -0.044 |
slide | -0.038 |
truck | -0.037 |
fountain | -0.036 |
snow | -0.036 |
Token | with |
Token ID | 351 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
cel | +0.032 |
stru | +0.032 |
unlike | +0.032 |
fulfilled | +0.031 |
since | +0.031 |
Neg logit contributions | |
moms | -0.036 |
slide | -0.031 |
dads | -0.030 |
truck | -0.030 |
eps | -0.030 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
since | +0.034 |
unlike | +0.034 |
fulfilled | +0.033 |
stru | +0.031 |
cel | +0.030 |
Neg logit contributions | |
moms | -0.043 |
dads | -0.037 |
eps | -0.035 |
slide | -0.034 |
truck | -0.033 |
Token | oming |
Token ID | 3383 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
since | +0.122 |
unlike | +0.118 |
fulfilled | +0.105 |
knowing | +0.104 |
cel | +0.102 |
Neg logit contributions | |
moms | -0.236 |
eps | -0.218 |
truck | -0.208 |
microwave | -0.206 |
towels | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
since | +0.065 |
unlike | +0.063 |
fulfilled | +0.061 |
stru | +0.058 |
cel | +0.057 |
Neg logit contributions | |
moms | -0.087 |
dads | -0.075 |
eps | -0.072 |
slide | -0.069 |
truck | -0.067 |
Token | It |
Token ID | 632 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.007 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.015 |
eps | -0.015 |
slide | -0.014 |
truck | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.005 |
eps | +0.004 |
sled | +0.004 |
towels | +0.004 |
Neg logit contributions | |
unlike | -0.005 |
since | -0.005 |
fulfilled | -0.005 |
cel | -0.005 |
stru | -0.005 |
Token | blo |
Token ID | 24924 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
moms | +0.037 |
dads | +0.032 |
eps | +0.030 |
slide | +0.029 |
truck | +0.029 |
Neg logit contributions | |
unlike | -0.028 |
since | -0.028 |
fulfilled | -0.027 |
cel | -0.025 |
stru | -0.024 |
Token | oming |
Token ID | 3383 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
since | +0.152 |
unlike | +0.139 |
knowing | +0.135 |
cess | +0.126 |
fulfilled | +0.124 |
Neg logit contributions | |
moms | -0.240 |
eps | -0.231 |
towels | -0.215 |
microwave | -0.211 |
truck | -0.209 |
Token | now |
Token ID | 783 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
since | +0.085 |
unlike | +0.083 |
fulfilled | +0.082 |
stru | +0.079 |
cel | +0.077 |
Neg logit contributions | |
moms | -0.107 |
dads | -0.091 |
eps | -0.088 |
slide | -0.086 |
truck | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.034 |
eps | +0.033 |
slide | +0.032 |
truck | +0.031 |
Neg logit contributions | |
since | -0.031 |
unlike | -0.030 |
fulfilled | -0.029 |
stru | -0.027 |
cel | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +2.31e-04 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.013 |
stru | +0.012 |
cel | +0.012 |
Neg logit contributions | |
moms | -0.022 |
dads | -0.019 |
eps | -0.019 |
slide | -0.018 |
truck | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
unlike | +0.000 |
since | +0.000 |
fulfilled | +0.000 |
cel | +0.000 |
stru | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
sled | -0.000 |
towels | -0.000 |
Token | tool |
Token ID | 2891 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
unlike | +0.003 |
fulfilled | +0.003 |
since | +0.003 |
cel | +0.003 |
knowing | +0.003 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
eps | -0.002 |
agree | -0.002 |
towels | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
since | +0.035 |
unlike | +0.034 |
fulfilled | +0.032 |
cel | +0.032 |
knowing | +0.030 |
Neg logit contributions | |
moms | -0.048 |
dads | -0.043 |
eps | -0.040 |
slide | -0.037 |
towels | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
since | +0.015 |
unlike | +0.014 |
fulfilled | +0.014 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.018 |
dads | -0.016 |
eps | -0.015 |
slide | -0.015 |
truck | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
moms | +0.021 |
dads | +0.018 |
eps | +0.017 |
slide | +0.016 |
towels | +0.016 |
Neg logit contributions | |
since | -0.027 |
unlike | -0.027 |
fulfilled | -0.026 |
cel | -0.026 |
stru | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.034 |
eps | +0.032 |
slide | +0.032 |
towels | +0.031 |
Neg logit contributions | |
since | -0.032 |
unlike | -0.031 |
fulfilled | -0.031 |
stru | -0.029 |
cel | -0.029 |
Token | gard |
Token ID | 16985 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
fulfilled | +0.025 |
unlike | +0.025 |
since | +0.025 |
knowing | +0.024 |
cel | +0.023 |
Neg logit contributions | |
moms | -0.026 |
eps | -0.022 |
dads | -0.021 |
towels | -0.020 |
says | -0.019 |
Token | ener |
Token ID | 877 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
since | +0.157 |
unlike | +0.153 |
fulfilled | +0.150 |
stru | +0.142 |
cel | +0.138 |
Neg logit contributions | |
moms | -0.243 |
dads | -0.211 |
eps | -0.203 |
slide | -0.199 |
truck | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
since | +0.127 |
unlike | +0.122 |
fulfilled | +0.120 |
stru | +0.115 |
cel | +0.114 |
Neg logit contributions | |
moms | -0.154 |
dads | -0.131 |
eps | -0.126 |
slide | -0.122 |
truck | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
since | +0.022 |
unlike | +0.021 |
fulfilled | +0.021 |
stru | +0.020 |
cel | +0.020 |
Neg logit contributions | |
moms | -0.022 |
dads | -0.018 |
eps | -0.017 |
slide | -0.017 |
truck | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +6.76e-04 |
Pos logit contributions | |
since | +0.003 |
fulfilled | +0.003 |
unlike | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.003 |
eps | -0.003 |
slide | -0.003 |
towels | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
fulfilled | +0.001 |
stru | +0.001 |
cel | +0.001 |
Neg logit contributions | |
moms | -0.001 |
dads | -0.001 |
eps | -0.001 |
slide | -0.001 |
truck | -0.001 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
moms | +0.002 |
dads | +0.002 |
eps | +0.002 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.003 |
unlike | -0.003 |
fulfilled | -0.003 |
stru | -0.003 |
cel | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
since | +0.021 |
unlike | +0.020 |
fulfilled | +0.020 |
stru | +0.019 |
cel | +0.019 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.024 |
eps | -0.024 |
slide | -0.023 |
truck | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
since | +0.006 |
unlike | +0.006 |
fulfilled | +0.005 |
stru | +0.005 |
Nice | +0.005 |
Neg logit contributions | |
moms | -0.007 |
eps | -0.006 |
dads | -0.006 |
towels | -0.005 |
slide | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
since | +0.003 |
fulfilled | +0.003 |
unlike | +0.003 |
stru | +0.003 |
Nice | +0.003 |
Neg logit contributions | |
moms | -0.004 |
dads | -0.003 |
eps | -0.003 |
towels | -0.003 |
truck | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
since | +0.006 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.005 |
Neg logit contributions | |
moms | -0.006 |
dads | -0.005 |
eps | -0.005 |
towels | -0.005 |
slide | -0.005 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
since | +0.047 |
Nice | +0.041 |
unlike | +0.041 |
fulfilled | +0.041 |
cel | +0.039 |
Neg logit contributions | |
moms | -0.052 |
dads | -0.049 |
eps | -0.048 |
towels | -0.045 |
dad | -0.044 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
moms | +0.281 |
dads | +0.241 |
slide | +0.236 |
eps | +0.235 |
truck | +0.229 |
Neg logit contributions | |
since | -0.187 |
unlike | -0.183 |
fulfilled | -0.183 |
stru | -0.175 |
cel | -0.175 |
Token | Tom |
Token ID | 4186 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
moms | +0.066 |
eps | +0.065 |
dads | +0.058 |
towels | +0.053 |
slide | +0.051 |
Neg logit contributions | |
since | -0.088 |
unlike | -0.082 |
fulfilled | -0.076 |
stru | -0.075 |
Mill | -0.075 |
Token | says |
Token ID | 1139 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
moms | +0.062 |
dads | +0.051 |
eps | +0.049 |
towels | +0.046 |
sled | +0.044 |
Neg logit contributions | |
since | -0.117 |
unlike | -0.110 |
stru | -0.109 |
fulfilled | -0.105 |
solving | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-04 |
Pos logit contributions | |
moms | +0.072 |
dads | +0.057 |
dad | +0.056 |
truck | +0.055 |
slide | +0.055 |
Neg logit contributions | |
unlike | -0.081 |
since | -0.080 |
fulfilled | -0.080 |
cel | -0.078 |
stru | -0.077 |
Token | He |
Token ID | 679 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
moms | +0.002 |
eps | +0.002 |
dads | +0.001 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
stru | -0.001 |
Nice | -0.001 |
Token | fight |
Token ID | 1907 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
since | +0.029 |
fulfilled | +0.026 |
unlike | +0.026 |
solving | +0.026 |
cel | +0.026 |
Neg logit contributions | |
moms | -0.034 |
dads | -0.028 |
eps | -0.027 |
microwave | -0.026 |
truck | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
moms | +0.083 |
dads | +0.075 |
eps | +0.070 |
slide | +0.068 |
sled | +0.068 |
Neg logit contributions | |
since | -0.048 |
unlike | -0.042 |
fulfilled | -0.042 |
solving | -0.039 |
knowing | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
fulfilled | +0.010 |
stru | +0.010 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
eps | -0.014 |
slide | -0.013 |
sled | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
since | +0.007 |
fulfilled | +0.006 |
unlike | +0.006 |
This | +0.006 |
stru | +0.006 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.010 |
eps | -0.010 |
slide | -0.010 |
sandbox | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
since | +0.007 |
fulfilled | +0.006 |
unlike | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.010 |
dads | -0.009 |
slide | -0.008 |
eps | -0.008 |
sled | -0.008 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
since | +0.048 |
unlike | +0.046 |
fulfilled | +0.043 |
cel | +0.042 |
stru | +0.042 |
Neg logit contributions | |
moms | -0.058 |
dads | -0.053 |
sled | -0.052 |
truck | -0.051 |
dad | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +6.60e-04 |
Pos logit contributions | |
moms | +0.279 |
dads | +0.240 |
slide | +0.234 |
eps | +0.234 |
truck | +0.227 |
Neg logit contributions | |
since | -0.184 |
fulfilled | -0.180 |
unlike | -0.179 |
stru | -0.172 |
cel | -0.170 |
Token | mine |
Token ID | 6164 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
cel | +0.001 |
This | +0.001 |
solving | +0.001 |
Neg logit contributions | |
moms | -0.001 |
dads | -0.001 |
eps | -0.001 |
agree | -0.001 |
towels | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
moms | +0.097 |
dads | +0.085 |
eps | +0.082 |
slide | +0.080 |
towels | +0.078 |
Neg logit contributions | |
since | -0.051 |
unlike | -0.049 |
fulfilled | -0.047 |
stru | -0.045 |
cel | -0.044 |
Token | mine |
Token ID | 6164 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
unlike | +0.001 |
since | +0.001 |
This | +0.001 |
cel | +0.001 |
Nice | +0.001 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
eps | -0.002 |
towels | -0.002 |
agree | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
moms | +0.101 |
dads | +0.089 |
eps | +0.086 |
slide | +0.084 |
towels | +0.082 |
Neg logit contributions | |
since | -0.049 |
unlike | -0.047 |
fulfilled | -0.045 |
stru | -0.043 |
cel | -0.042 |
Token | his |
Token ID | 465 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
moms | +0.018 |
dads | +0.015 |
eps | +0.015 |
slide | +0.014 |
truck | +0.013 |
Neg logit contributions | |
since | -0.016 |
unlike | -0.015 |
fulfilled | -0.015 |
stru | -0.014 |
cel | -0.014 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.007 |
eps | +0.006 |
Ben | +0.006 |
ila | +0.006 |
Neg logit contributions | |
unlike | -0.009 |
since | -0.009 |
fulfilled | -0.009 |
cel | -0.009 |
exploring | -0.008 |
Token | car |
Token ID | 1097 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
since | +0.021 |
unlike | +0.021 |
cel | +0.020 |
Nice | +0.019 |
fulfilled | +0.019 |
Neg logit contributions | |
moms | -0.013 |
dads | -0.011 |
eps | -0.011 |
agree | -0.009 |
says | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
moms | +0.085 |
dads | +0.073 |
eps | +0.070 |
slide | +0.067 |
towels | +0.066 |
Neg logit contributions | |
since | -0.062 |
unlike | -0.060 |
fulfilled | -0.058 |
stru | -0.056 |
cel | -0.055 |
Token | " |
Token ID | 366 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.003 |
eps | -0.003 |
slide | -0.003 |
truck | -0.003 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
unlike | +0.029 |
since | +0.029 |
stru | +0.026 |
fulfilled | +0.026 |
cel | +0.024 |
Neg logit contributions | |
moms | -0.040 |
dads | -0.036 |
says | -0.033 |
truck | -0.033 |
towels | -0.032 |
Token | can |
Token ID | 460 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
moms | +0.245 |
dads | +0.204 |
slide | +0.202 |
eps | +0.201 |
truck | +0.196 |
Neg logit contributions | |
since | -0.213 |
fulfilled | -0.211 |
unlike | -0.207 |
stru | -0.205 |
cel | -0.204 |
Token | zoom |
Token ID | 19792 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.017 |
eps | +0.015 |
towels | +0.015 |
microwave | +0.014 |
Neg logit contributions | |
since | -0.019 |
unlike | -0.019 |
fulfilled | -0.018 |
stru | -0.017 |
cel | -0.017 |
Token | faster |
Token ID | 5443 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
since | +0.012 |
fulfilled | +0.012 |
unlike | +0.012 |
stru | +0.011 |
cel | +0.011 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.014 |
eps | -0.014 |
slide | -0.014 |
truck | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
moms | +0.063 |
dads | +0.055 |
eps | +0.053 |
slide | +0.052 |
towels | +0.050 |
Neg logit contributions | |
since | -0.035 |
unlike | -0.034 |
fulfilled | -0.033 |
stru | -0.031 |
cel | -0.030 |
Token | louder |
Token ID | 27089 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
moms | +0.002 |
dads | +0.002 |
eps | +0.002 |
slide | +0.002 |
towels | +0.002 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
stru | -0.001 |
cel | -0.001 |
Token | car |
Token ID | 1097 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
since | +0.023 |
unlike | +0.022 |
fulfilled | +0.022 |
Nice | +0.020 |
stru | +0.020 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.015 |
eps | -0.014 |
agree | -0.012 |
towels | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
moms | +0.103 |
dads | +0.089 |
eps | +0.084 |
slide | +0.081 |
towels | +0.080 |
Neg logit contributions | |
since | -0.071 |
unlike | -0.067 |
fulfilled | -0.065 |
stru | -0.062 |
cel | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
since | +0.010 |
This | +0.010 |
unlike | +0.010 |
fulfilled | +0.009 |
Nice | +0.009 |
Neg logit contributions | |
moms | -0.015 |
eps | -0.014 |
dads | -0.014 |
slide | -0.013 |
sled | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
since | +0.011 |
fulfilled | +0.010 |
unlike | +0.010 |
Nice | +0.010 |
stru | +0.009 |
Neg logit contributions | |
moms | -0.018 |
dads | -0.016 |
eps | -0.015 |
slide | -0.015 |
sandbox | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
since | +0.013 |
fulfilled | +0.012 |
unlike | +0.012 |
zing | +0.011 |
stru | +0.011 |
Neg logit contributions | |
moms | -0.018 |
dads | -0.016 |
eps | -0.016 |
slide | -0.015 |
truck | -0.015 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
since | +0.047 |
unlike | +0.043 |
fulfilled | +0.040 |
Gr | +0.039 |
cel | +0.039 |
Neg logit contributions | |
moms | -0.065 |
dads | -0.062 |
says | -0.056 |
truck | -0.055 |
dad | -0.055 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
moms | +0.291 |
dads | +0.253 |
eps | +0.245 |
slide | +0.242 |
truck | +0.235 |
Neg logit contributions | |
since | -0.171 |
unlike | -0.165 |
fulfilled | -0.163 |
stru | -0.155 |
cel | -0.153 |
Token | Anna |
Token ID | 11735 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
moms | +0.062 |
eps | +0.061 |
dads | +0.055 |
sled | +0.052 |
slide | +0.051 |
Neg logit contributions | |
since | -0.085 |
unlike | -0.076 |
fulfilled | -0.074 |
Grace | -0.073 |
Grac | -0.072 |
Token | says |
Token ID | 1139 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
moms | +0.009 |
dads | +0.007 |
eps | +0.007 |
sled | +0.006 |
cream | +0.006 |
Neg logit contributions | |
since | -0.021 |
unlike | -0.020 |
stru | -0.019 |
fulfilled | -0.019 |
Nice | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-04 |
Pos logit contributions | |
moms | +0.076 |
dads | +0.064 |
eps | +0.061 |
slide | +0.060 |
truck | +0.059 |
Neg logit contributions | |
since | -0.068 |
unlike | -0.067 |
fulfilled | -0.065 |
stru | -0.063 |
cel | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
since | +0.000 |
unlike | +0.000 |
fulfilled | +0.000 |
stru | +0.000 |
cel | +0.000 |
Neg logit contributions | |
moms | -0.001 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
truck | -0.000 |
Token | fight |
Token ID | 1907 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
moms | +0.010 |
eps | +0.009 |
microwave | +0.009 |
dads | +0.008 |
snowball | +0.008 |
Neg logit contributions | |
since | -0.011 |
solving | -0.010 |
fulfilled | -0.010 |
giving | -0.010 |
unlike | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
moms | +0.091 |
dads | +0.081 |
eps | +0.076 |
slide | +0.075 |
sled | +0.074 |
Neg logit contributions | |
since | -0.059 |
unlike | -0.055 |
fulfilled | -0.054 |
stru | -0.050 |
solving | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
This | +0.006 |
fulfilled | +0.006 |
Mill | +0.006 |
Neg logit contributions | |
moms | -0.010 |
eps | -0.009 |
dads | -0.009 |
slide | -0.009 |
cream | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
since | +0.004 |
fulfilled | +0.004 |
This | +0.004 |
With | +0.004 |
unlike | +0.004 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.008 |
sandbox | -0.008 |
slide | -0.008 |
microwave | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
since | +0.007 |
fulfilled | +0.006 |
shadow | +0.006 |
unlike | +0.006 |
solving | +0.006 |
Neg logit contributions | |
moms | -0.008 |
microwave | -0.007 |
elbow | -0.007 |
slide | -0.007 |
dads | -0.007 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
since | +0.037 |
unlike | +0.036 |
Gr | +0.033 |
cel | +0.032 |
EX | +0.032 |
Neg logit contributions | |
moms | -0.055 |
dads | -0.053 |
sled | -0.052 |
truck | -0.051 |
dad | -0.051 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
moms | +0.277 |
dads | +0.239 |
eps | +0.231 |
slide | +0.227 |
truck | +0.221 |
Neg logit contributions | |
since | -0.182 |
unlike | -0.177 |
fulfilled | -0.174 |
stru | -0.167 |
cel | -0.164 |
Token | Mine |
Token ID | 11517 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
moms | +0.002 |
eps | +0.002 |
dads | +0.002 |
slide | +0.002 |
towels | +0.002 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
Nice | -0.001 |
stru | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
moms | +0.140 |
dads | +0.121 |
eps | +0.116 |
slide | +0.112 |
towels | +0.112 |
Neg logit contributions | |
since | -0.091 |
unlike | -0.086 |
fulfilled | -0.084 |
stru | -0.080 |
cel | -0.078 |
Token | Tom |
Token ID | 4186 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
moms | +0.061 |
eps | +0.058 |
dads | +0.054 |
slide | +0.053 |
sled | +0.053 |
Neg logit contributions | |
since | -0.088 |
unlike | -0.085 |
Mill | -0.083 |
This | -0.080 |
Emmy | -0.079 |
Token | said |
Token ID | 531 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
moms | +0.089 |
dads | +0.074 |
sled | +0.073 |
eps | +0.071 |
microwave | +0.071 |
Neg logit contributions | |
since | -0.113 |
unlike | -0.098 |
knowing | -0.090 |
stru | -0.089 |
fulfilled | -0.087 |
Token | leaf |
Token ID | 12835 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
moms | +0.014 |
dads | +0.012 |
eps | +0.012 |
Rex | +0.011 |
oyd | +0.011 |
Neg logit contributions | |
unlike | -0.013 |
fulfilled | -0.013 |
since | -0.012 |
knowing | -0.011 |
stru | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
since | +0.063 |
unlike | +0.060 |
fulfilled | +0.057 |
stru | +0.053 |
cel | +0.052 |
Neg logit contributions | |
moms | -0.116 |
dads | -0.103 |
eps | -0.095 |
says | -0.092 |
agree | -0.090 |
Token | top |
Token ID | 1353 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
since | +0.019 |
unlike | +0.019 |
fulfilled | +0.016 |
cel | +0.016 |
Mill | +0.016 |
Neg logit contributions | |
moms | -0.026 |
dads | -0.024 |
eps | -0.023 |
agree | -0.021 |
towels | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
moms | +0.050 |
dads | +0.045 |
eps | +0.043 |
towels | +0.040 |
slide | +0.040 |
Neg logit contributions | |
since | -0.025 |
unlike | -0.023 |
fulfilled | -0.021 |
stru | -0.019 |
solving | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
Nice | +0.006 |
stru | +0.006 |
Neg logit contributions | |
moms | -0.013 |
dads | -0.012 |
eps | -0.012 |
slide | -0.011 |
towels | -0.011 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
since | +0.028 |
unlike | +0.028 |
fulfilled | +0.027 |
stru | +0.026 |
cel | +0.026 |
Neg logit contributions | |
moms | -0.031 |
dads | -0.027 |
eps | -0.024 |
truck | -0.024 |
towels | -0.024 |
Token | has |
Token ID | 468 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
moms | +0.267 |
slide | +0.228 |
dads | +0.227 |
eps | +0.221 |
truck | +0.221 |
Neg logit contributions | |
since | -0.187 |
fulfilled | -0.187 |
unlike | -0.182 |
stru | -0.181 |
cel | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
since | +0.074 |
unlike | +0.072 |
fulfilled | +0.072 |
stru | +0.071 |
cel | +0.069 |
Neg logit contributions | |
moms | -0.057 |
dads | -0.046 |
eps | -0.044 |
slide | -0.043 |
truck | -0.041 |
Token | flower |
Token ID | 15061 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
unlike | +0.015 |
since | +0.014 |
fulfilled | +0.014 |
cel | +0.013 |
knowing | +0.013 |
Neg logit contributions | |
moms | -0.014 |
dads | -0.013 |
eps | -0.012 |
towels | -0.011 |
Rex | -0.010 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
since | +0.068 |
unlike | +0.065 |
fulfilled | +0.062 |
cel | +0.059 |
stru | +0.058 |
Neg logit contributions | |
moms | -0.120 |
dads | -0.106 |
eps | -0.103 |
slide | -0.098 |
towels | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
moms | +0.076 |
eps | +0.071 |
dads | +0.068 |
towels | +0.062 |
slide | +0.062 |
Neg logit contributions | |
since | -0.053 |
unlike | -0.048 |
Mill | -0.045 |
fulfilled | -0.044 |
Nice | -0.043 |
Token | yell |
Token ID | 28946 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.000 |
fulfilled | +0.000 |
solving | +0.000 |
cel | +0.000 |
Neg logit contributions | |
moms | -0.001 |
dads | -0.000 |
microwave | -0.000 |
eps | -0.000 |
cream | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
moms | +0.052 |
dads | +0.043 |
eps | +0.043 |
truck | +0.041 |
slide | +0.041 |
Neg logit contributions | |
since | -0.047 |
fulfilled | -0.047 |
unlike | -0.046 |
stru | -0.046 |
cel | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
This | +0.010 |
fulfilled | +0.010 |
Nice | +0.010 |
Neg logit contributions | |
moms | -0.015 |
eps | -0.015 |
dads | -0.014 |
slide | -0.013 |
truck | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.009 |
fulfilled | +0.009 |
stru | +0.009 |
Nice | +0.009 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.015 |
eps | -0.014 |
sandbox | -0.014 |
microwave | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.010 |
fulfilled | +0.010 |
stru | +0.010 |
zing | +0.009 |
Neg logit contributions | |
moms | -0.018 |
eps | -0.016 |
dads | -0.016 |
microwave | -0.016 |
truck | -0.016 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
since | +0.049 |
unlike | +0.047 |
fulfilled | +0.041 |
EX | +0.040 |
Nice | +0.040 |
Neg logit contributions | |
moms | -0.061 |
dads | -0.056 |
says | -0.055 |
truck | -0.054 |
eps | -0.053 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
moms | +0.287 |
dads | +0.250 |
eps | +0.242 |
slide | +0.238 |
truck | +0.231 |
Neg logit contributions | |
since | -0.169 |
unlike | -0.163 |
fulfilled | -0.160 |
stru | -0.153 |
cel | -0.150 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
eps | +0.055 |
moms | +0.053 |
truck | +0.045 |
dads | +0.044 |
snowball | +0.044 |
Neg logit contributions | |
since | -0.085 |
unlike | -0.080 |
Mill | -0.077 |
Grac | -0.074 |
This | -0.074 |
Token | says |
Token ID | 1139 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
moms | +0.027 |
eps | +0.021 |
dads | +0.020 |
sled | +0.019 |
slide | +0.017 |
Neg logit contributions | |
since | -0.061 |
unlike | -0.058 |
fulfilled | -0.055 |
Nice | -0.054 |
stru | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +8.09e-04 |
Pos logit contributions | |
moms | +0.071 |
dads | +0.060 |
eps | +0.057 |
slide | +0.056 |
truck | +0.055 |
Neg logit contributions | |
since | -0.064 |
unlike | -0.063 |
fulfilled | -0.063 |
stru | -0.061 |
cel | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
unlike | +0.001 |
since | +0.001 |
fulfilled | +0.001 |
stru | +0.001 |
Nice | +0.001 |
Neg logit contributions | |
moms | -0.002 |
eps | -0.002 |
dads | -0.002 |
towels | -0.001 |
slide | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
moms | +0.047 |
dads | +0.040 |
eps | +0.038 |
slide | +0.037 |
towels | +0.036 |
Neg logit contributions | |
since | -0.038 |
unlike | -0.037 |
fulfilled | -0.035 |
stru | -0.034 |
cel | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.013 |
fulfilled | +0.013 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.018 |
dads | -0.015 |
eps | -0.014 |
slide | -0.014 |
truck | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
since | +0.003 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.003 |
eps | -0.003 |
slide | -0.003 |
towels | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
since | +0.005 |
fulfilled | +0.005 |
unlike | +0.005 |
stru | +0.005 |
Nice | +0.004 |
Neg logit contributions | |
moms | -0.006 |
dads | -0.005 |
eps | -0.005 |
slide | -0.004 |
truck | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.008 |
fulfilled | +0.008 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
eps | -0.009 |
slide | -0.009 |
truck | -0.009 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
since | +0.049 |
unlike | +0.044 |
cel | +0.042 |
fulfilled | +0.042 |
Nice | +0.042 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.048 |
eps | -0.044 |
sled | -0.042 |
says | -0.041 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
moms | +0.266 |
dads | +0.226 |
slide | +0.225 |
eps | +0.221 |
truck | +0.218 |
Neg logit contributions | |
since | -0.187 |
fulfilled | -0.185 |
unlike | -0.183 |
stru | -0.178 |
cel | -0.178 |
Token | he |
Token ID | 339 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
moms | +0.078 |
eps | +0.070 |
dads | +0.068 |
slide | +0.064 |
sled | +0.063 |
Neg logit contributions | |
since | -0.071 |
unlike | -0.065 |
fulfilled | -0.063 |
Mill | -0.059 |
cel | -0.059 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
moms | +0.036 |
dads | +0.030 |
sled | +0.029 |
eps | +0.028 |
microwave | +0.028 |
Neg logit contributions | |
since | -0.058 |
unlike | -0.055 |
stru | -0.052 |
fulfilled | -0.052 |
cel | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
moms | +0.066 |
dads | +0.054 |
dad | +0.053 |
truck | +0.052 |
Tom | +0.051 |
Neg logit contributions | |
since | -0.068 |
unlike | -0.068 |
fulfilled | -0.068 |
stru | -0.066 |
cel | -0.064 |
Token | " |
Token ID | 366 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
truck | -0.002 |
Token | too |
Token ID | 1165 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
since | +0.027 |
unlike | +0.026 |
fulfilled | +0.026 |
stru | +0.025 |
cel | +0.025 |
Neg logit contributions | |
moms | -0.031 |
dads | -0.026 |
eps | -0.025 |
slide | -0.025 |
truck | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
moms | +0.030 |
dads | +0.026 |
eps | +0.026 |
slide | +0.024 |
towels | +0.024 |
Neg logit contributions | |
since | -0.021 |
unlike | -0.019 |
fulfilled | -0.019 |
stru | -0.018 |
knowing | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-04 |
Pos logit contributions | |
since | +0.006 |
unlike | +0.006 |
fulfilled | +0.006 |
Nice | +0.006 |
stru | +0.006 |
Neg logit contributions | |
moms | -0.011 |
eps | -0.010 |
dads | -0.010 |
slide | -0.009 |
towels | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
since | +0.000 |
fulfilled | +0.000 |
unlike | +0.000 |
stru | +0.000 |
Nice | +0.000 |
Neg logit contributions | |
moms | -0.000 |
dads | -0.000 |
eps | -0.000 |
slide | -0.000 |
truck | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
since | +0.002 |
fulfilled | +0.002 |
unlike | +0.002 |
zing | +0.002 |
stru | +0.002 |
Neg logit contributions | |
moms | -0.005 |
dads | -0.004 |
eps | -0.004 |
slide | -0.004 |
truck | -0.004 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
since | +0.046 |
unlike | +0.041 |
fulfilled | +0.041 |
Nice | +0.041 |
cel | +0.039 |
Neg logit contributions | |
moms | -0.044 |
eps | -0.042 |
dads | -0.041 |
sled | -0.037 |
agree | -0.037 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
moms | +0.253 |
dads | +0.214 |
slide | +0.212 |
eps | +0.205 |
truck | +0.205 |
Neg logit contributions | |
since | -0.199 |
fulfilled | -0.198 |
unlike | -0.197 |
stru | -0.191 |
cel | -0.190 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
moms | +0.063 |
eps | +0.061 |
dads | +0.055 |
slide | +0.049 |
sled | +0.049 |
Neg logit contributions | |
since | -0.094 |
unlike | -0.086 |
fulfilled | -0.084 |
Grac | -0.081 |
Nice | -0.081 |
Token | shouted |
Token ID | 17293 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
moms | +0.045 |
dads | +0.037 |
eps | +0.035 |
slide | +0.033 |
sled | +0.033 |
Neg logit contributions | |
since | -0.071 |
unlike | -0.067 |
fulfilled | -0.064 |
stru | -0.063 |
cel | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
moms | +0.071 |
dads | +0.058 |
dad | +0.056 |
truck | +0.055 |
Tom | +0.054 |
Neg logit contributions | |
unlike | -0.074 |
since | -0.074 |
fulfilled | -0.074 |
stru | -0.071 |
cel | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
since | +0.004 |
unlike | +0.004 |
fulfilled | +0.004 |
stru | +0.004 |
cel | +0.004 |
Neg logit contributions | |
moms | -0.006 |
dads | -0.005 |
eps | -0.005 |
slide | -0.005 |
truck | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.013 |
stru | +0.013 |
cel | +0.012 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
eps | -0.013 |
slide | -0.012 |
says | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.001 |
cel | +0.001 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
towels | -0.002 |
Token | yell |
Token ID | 28946 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
moms | +0.020 |
dads | +0.017 |
eps | +0.016 |
omo | +0.015 |
outed | +0.015 |
Neg logit contributions | |
since | -0.016 |
unlike | -0.013 |
fulfilled | -0.013 |
cel | -0.013 |
solving | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
moms | +0.057 |
dads | +0.047 |
eps | +0.047 |
truck | +0.045 |
slide | +0.044 |
Neg logit contributions | |
since | -0.051 |
fulfilled | -0.050 |
unlike | -0.050 |
stru | -0.049 |
cel | -0.047 |
Token | " |
Token ID | 366 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
since | +0.019 |
unlike | +0.019 |
fulfilled | +0.018 |
stru | +0.017 |
cel | +0.017 |
Neg logit contributions | |
moms | -0.038 |
dads | -0.034 |
eps | -0.033 |
slide | -0.032 |
towels | -0.031 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
since | +0.042 |
unlike | +0.041 |
stru | +0.038 |
fulfilled | +0.038 |
cel | +0.037 |
Neg logit contributions | |
moms | -0.039 |
dads | -0.035 |
dad | -0.031 |
towels | -0.030 |
truck | -0.029 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
moms | +0.285 |
dads | +0.248 |
slide | +0.239 |
eps | +0.239 |
truck | +0.234 |
Neg logit contributions | |
since | -0.169 |
fulfilled | -0.165 |
unlike | -0.164 |
stru | -0.157 |
cel | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
moms | +0.073 |
eps | +0.067 |
dads | +0.064 |
slide | +0.061 |
sled | +0.060 |
Neg logit contributions | |
since | -0.065 |
unlike | -0.058 |
fulfilled | -0.057 |
cel | -0.053 |
knowing | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
moms | +0.018 |
dads | +0.016 |
eps | +0.016 |
slide | +0.015 |
truck | +0.015 |
Neg logit contributions | |
since | -0.013 |
fulfilled | -0.012 |
unlike | -0.012 |
stru | -0.011 |
Nice | -0.011 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
eps | +0.006 |
truck | +0.006 |
slide | +0.006 |
Neg logit contributions | |
since | -0.007 |
fulfilled | -0.006 |
unlike | -0.006 |
stru | -0.006 |
cel | -0.006 |
Token | hears |
Token ID | 23180 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
moms | +0.024 |
dads | +0.020 |
sled | +0.019 |
eps | +0.018 |
snowball | +0.018 |
Neg logit contributions | |
since | -0.025 |
fulfilled | -0.023 |
cel | -0.022 |
solving | -0.022 |
unlike | -0.022 |
Token | says |
Token ID | 1139 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
moms | +0.015 |
eps | +0.012 |
dads | +0.011 |
kin | +0.011 |
sled | +0.009 |
Neg logit contributions | |
since | -0.033 |
Nice | -0.030 |
unlike | -0.030 |
fulfilled | -0.029 |
stru | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
moms | +0.069 |
dads | +0.058 |
eps | +0.054 |
slide | +0.054 |
truck | +0.053 |
Neg logit contributions | |
since | -0.068 |
unlike | -0.067 |
fulfilled | -0.066 |
cel | -0.063 |
stru | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
unlike | +0.004 |
since | +0.004 |
Nice | +0.004 |
fulfilled | +0.004 |
stru | +0.004 |
Neg logit contributions | |
moms | -0.008 |
eps | -0.008 |
dads | -0.008 |
slide | -0.007 |
towels | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
moms | +0.013 |
dads | +0.012 |
eps | +0.012 |
sandbox | +0.011 |
slide | +0.011 |
Neg logit contributions | |
since | -0.008 |
fulfilled | -0.007 |
unlike | -0.007 |
stru | -0.007 |
Nice | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
moms | +0.008 |
dads | +0.007 |
eps | +0.007 |
microwave | +0.007 |
slide | +0.007 |
Neg logit contributions | |
since | -0.004 |
fulfilled | -0.004 |
unlike | -0.003 |
stru | -0.003 |
cel | -0.003 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
unlike | +0.040 |
since | +0.040 |
Nice | +0.038 |
fulfilled | +0.037 |
stru | +0.036 |
Neg logit contributions | |
moms | -0.050 |
eps | -0.045 |
dads | -0.044 |
microwave | -0.043 |
truck | -0.042 |
Token | is |
Token ID | 318 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
moms | +0.274 |
dads | +0.237 |
eps | +0.229 |
slide | +0.225 |
truck | +0.219 |
Neg logit contributions | |
since | -0.179 |
unlike | -0.173 |
fulfilled | -0.171 |
stru | -0.163 |
cel | -0.161 |
Token | faster |
Token ID | 5443 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
moms | +0.039 |
dads | +0.033 |
eps | +0.032 |
slide | +0.031 |
truck | +0.030 |
Neg logit contributions | |
since | -0.031 |
unlike | -0.030 |
fulfilled | -0.029 |
stru | -0.028 |
cel | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
moms | +0.017 |
dads | +0.015 |
eps | +0.015 |
slide | +0.014 |
towels | +0.014 |
Neg logit contributions | |
since | -0.007 |
unlike | -0.007 |
fulfilled | -0.006 |
stru | -0.006 |
cel | -0.005 |
Token | watch |
Token ID | 2342 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
since | +0.017 |
unlike | +0.016 |
Nice | +0.013 |
knowing | +0.012 |
fulfilled | +0.012 |
Neg logit contributions | |
moms | -0.031 |
dads | -0.028 |
eps | -0.028 |
towels | -0.026 |
oyd | -0.025 |
Token | this |
Token ID | 428 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
eps | +0.006 |
towels | +0.005 |
sandbox | +0.005 |
Neg logit contributions | |
since | -0.004 |
unlike | -0.004 |
cel | -0.003 |
fulfilled | -0.003 |
solving | -0.003 |
Token | lamp |
Token ID | 20450 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
unlike | +0.010 |
since | +0.010 |
fulfilled | +0.010 |
cel | +0.010 |
stru | +0.009 |
Neg logit contributions | |
moms | -0.010 |
dads | -0.009 |
eps | -0.008 |
agree | -0.008 |
Tom | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.036 |
eps | +0.034 |
Tom | +0.031 |
slide | +0.031 |
Neg logit contributions | |
since | -0.020 |
unlike | -0.019 |
fulfilled | -0.016 |
stru | -0.016 |
Mill | -0.015 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
moms | +0.030 |
dads | +0.026 |
eps | +0.023 |
truck | +0.022 |
microwave | +0.022 |
Neg logit contributions | |
since | -0.024 |
unlike | -0.019 |
fulfilled | -0.019 |
cel | -0.018 |
knowing | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
moms | +0.054 |
dads | +0.045 |
dad | +0.044 |
truck | +0.044 |
towels | +0.043 |
Neg logit contributions | |
since | -0.053 |
fulfilled | -0.053 |
unlike | -0.051 |
stru | -0.051 |
cel | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
since | +0.016 |
unlike | +0.015 |
fulfilled | +0.015 |
stru | +0.015 |
cel | +0.014 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.025 |
eps | -0.024 |
slide | -0.024 |
truck | -0.023 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
since | +0.029 |
unlike | +0.028 |
stru | +0.026 |
fulfilled | +0.026 |
cel | +0.025 |
Neg logit contributions | |
moms | -0.033 |
dads | -0.030 |
dad | -0.027 |
truck | -0.027 |
towels | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | -2.94e-04 |
Pos logit contributions | |
moms | +0.278 |
dads | +0.240 |
slide | +0.236 |
eps | +0.232 |
truck | +0.230 |
Neg logit contributions | |
since | -0.171 |
fulfilled | -0.170 |
unlike | -0.167 |
stru | -0.164 |
cel | -0.161 |
Token | Mine |
Token ID | 11517 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
moms | +0.001 |
dads | +0.001 |
eps | +0.001 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.000 |
unlike | -0.000 |
fulfilled | -0.000 |
Nice | -0.000 |
cel | -0.000 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
moms | +0.146 |
dads | +0.126 |
eps | +0.122 |
slide | +0.121 |
truck | +0.117 |
Neg logit contributions | |
since | -0.102 |
unlike | -0.099 |
fulfilled | -0.098 |
stru | -0.094 |
cel | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
moms | +0.074 |
eps | +0.069 |
dads | +0.067 |
slide | +0.062 |
towels | +0.060 |
Neg logit contributions | |
since | -0.053 |
unlike | -0.050 |
Mill | -0.046 |
This | -0.046 |
fulfilled | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.018 |
sandbox | +0.017 |
slide | +0.016 |
microwave | +0.016 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.009 |
Mill | -0.009 |
Mill | -0.009 |
fulfilled | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
slide | +0.006 |
eps | +0.006 |
microwave | +0.006 |
Neg logit contributions | |
since | -0.005 |
cel | -0.004 |
unlike | -0.004 |
fulfilled | -0.004 |
such | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
since | +0.018 |
unlike | +0.017 |
fulfilled | +0.017 |
stru | +0.016 |
cel | +0.015 |
Neg logit contributions | |
moms | -0.026 |
dads | -0.023 |
eps | -0.022 |
slide | -0.021 |
towels | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.010 |
fulfilled | +0.010 |
stru | +0.010 |
Nice | +0.009 |
Neg logit contributions | |
moms | -0.013 |
eps | -0.012 |
dads | -0.012 |
slide | -0.011 |
sled | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +6.36e-03 |
Pos logit contributions | |
since | +0.008 |
fulfilled | +0.007 |
stru | +0.007 |
unlike | +0.007 |
Mill | +0.006 |
Neg logit contributions | |
moms | -0.012 |
dads | -0.011 |
eps | -0.010 |
truck | -0.010 |
sandbox | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
since | +0.011 |
fulfilled | +0.010 |
unlike | +0.010 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
truck | -0.009 |
eps | -0.009 |
slide | -0.009 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
since | +0.050 |
unlike | +0.047 |
cel | +0.046 |
fulfilled | +0.044 |
Gr | +0.043 |
Neg logit contributions | |
moms | -0.059 |
dads | -0.053 |
sled | -0.051 |
truck | -0.048 |
says | -0.048 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
moms | +0.269 |
dads | +0.231 |
slide | +0.227 |
eps | +0.226 |
truck | +0.222 |
Neg logit contributions | |
since | -0.179 |
fulfilled | -0.175 |
unlike | -0.174 |
stru | -0.169 |
cel | -0.168 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
moms | +0.058 |
eps | +0.052 |
dads | +0.048 |
sled | +0.047 |
slide | +0.046 |
Neg logit contributions | |
since | -0.095 |
unlike | -0.088 |
fulfilled | -0.087 |
Grac | -0.083 |
Mill | -0.083 |
Token | shouted |
Token ID | 17293 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
moms | +0.035 |
dads | +0.027 |
eps | +0.026 |
slide | +0.025 |
sled | +0.024 |
Neg logit contributions | |
since | -0.065 |
unlike | -0.061 |
fulfilled | -0.058 |
stru | -0.057 |
cel | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-04 |
Pos logit contributions | |
moms | +0.074 |
dads | +0.061 |
eps | +0.058 |
truck | +0.057 |
dad | +0.057 |
Neg logit contributions | |
since | -0.073 |
unlike | -0.073 |
fulfilled | -0.072 |
stru | -0.069 |
cel | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
fulfilled | +0.001 |
stru | +0.000 |
cel | +0.000 |
Neg logit contributions | |
moms | -0.001 |
dads | -0.001 |
eps | -0.001 |
slide | -0.001 |
towels | -0.001 |
Token | shout |
Token ID | 9191 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.008 |
eps | +0.008 |
microwave | +0.007 |
cream | +0.007 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.009 |
fulfilled | -0.009 |
cel | -0.009 |
solving | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +9.24e-03 |
Pos logit contributions | |
moms | +0.052 |
dads | +0.043 |
eps | +0.042 |
truck | +0.041 |
towels | +0.041 |
Neg logit contributions | |
fulfilled | -0.053 |
since | -0.053 |
unlike | -0.053 |
stru | -0.052 |
Mill | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.012 |
fulfilled | +0.011 |
Nice | +0.011 |
This | +0.011 |
Neg logit contributions | |
moms | -0.018 |
eps | -0.016 |
dads | -0.016 |
slide | -0.015 |
cream | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
since | +0.008 |
fulfilled | +0.007 |
unlike | +0.007 |
Mill | +0.007 |
This | +0.007 |
Neg logit contributions | |
moms | -0.014 |
dads | -0.013 |
sandbox | -0.013 |
slide | -0.012 |
eps | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
since | +0.009 |
fulfilled | +0.008 |
shadow | +0.007 |
unlike | +0.007 |
zing | +0.007 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
microwave | -0.014 |
slide | -0.014 |
elbow | -0.014 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
since | +0.036 |
unlike | +0.034 |
EX | +0.031 |
unre | +0.030 |
Gr | +0.030 |
Neg logit contributions | |
moms | -0.059 |
dads | -0.057 |
dad | -0.054 |
truck | -0.053 |
says | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
moms | +0.288 |
dads | +0.251 |
eps | +0.243 |
slide | +0.239 |
truck | +0.233 |
Neg logit contributions | |
since | -0.160 |
unlike | -0.155 |
fulfilled | -0.152 |
stru | -0.144 |
cel | -0.141 |
Token | mine |
Token ID | 6164 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
unlike | +0.002 |
since | +0.002 |
This | +0.002 |
Nice | +0.002 |
My | +0.002 |
Neg logit contributions | |
moms | -0.002 |
eps | -0.002 |
dads | -0.002 |
sandbox | -0.002 |
towels | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
moms | +0.106 |
dads | +0.094 |
eps | +0.091 |
slide | +0.088 |
towels | +0.087 |
Neg logit contributions | |
since | -0.053 |
unlike | -0.051 |
fulfilled | -0.049 |
stru | -0.046 |
cel | -0.045 |
Token | mine |
Token ID | 6164 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
moms | +0.004 |
eps | +0.004 |
dads | +0.004 |
towels | +0.003 |
sandbox | +0.003 |
Neg logit contributions | |
unlike | -0.003 |
since | -0.003 |
Nice | -0.002 |
This | -0.002 |
My | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
moms | +0.112 |
dads | +0.099 |
eps | +0.096 |
slide | +0.092 |
towels | +0.091 |
Neg logit contributions | |
since | -0.052 |
unlike | -0.050 |
fulfilled | -0.048 |
stru | -0.045 |
cel | -0.043 |
Token | shout |
Token ID | 9191 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.035 |
omo | +0.031 |
microwave | +0.030 |
eps | +0.030 |
Neg logit contributions | |
since | -0.032 |
solving | -0.027 |
fulfilled | -0.026 |
unlike | -0.026 |
cel | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
moms | +0.065 |
dads | +0.054 |
eps | +0.053 |
truck | +0.052 |
slide | +0.051 |
Neg logit contributions | |
since | -0.062 |
fulfilled | -0.061 |
unlike | -0.061 |
stru | -0.060 |
cel | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.013 |
fulfilled | +0.012 |
Nice | +0.012 |
This | +0.012 |
Neg logit contributions | |
moms | -0.018 |
eps | -0.016 |
dads | -0.016 |
slide | -0.015 |
sled | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
since | +0.011 |
fulfilled | +0.010 |
unlike | +0.009 |
stru | +0.009 |
Mill | +0.009 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.016 |
eps | -0.015 |
slide | -0.015 |
sandbox | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
since | +0.013 |
fulfilled | +0.011 |
unlike | +0.011 |
stru | +0.011 |
cel | +0.011 |
Neg logit contributions | |
moms | -0.019 |
dads | -0.017 |
eps | -0.016 |
slide | -0.016 |
truck | -0.016 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
since | +0.042 |
unlike | +0.039 |
EX | +0.035 |
Gr | +0.035 |
cel | +0.034 |
Neg logit contributions | |
moms | -0.054 |
dads | -0.050 |
says | -0.048 |
sled | -0.047 |
truck | -0.047 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
moms | +0.288 |
dads | +0.252 |
eps | +0.244 |
slide | +0.238 |
truck | +0.232 |
Neg logit contributions | |
since | -0.159 |
unlike | -0.154 |
fulfilled | -0.150 |
stru | -0.142 |
cel | -0.139 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
moms | +0.061 |
eps | +0.056 |
dads | +0.051 |
slide | +0.049 |
sled | +0.049 |
Neg logit contributions | |
since | -0.079 |
unlike | -0.073 |
fulfilled | -0.071 |
Mill | -0.069 |
Grac | -0.069 |
Token | says |
Token ID | 1139 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.004 |
eps | +0.004 |
sled | +0.004 |
towels | +0.003 |
Neg logit contributions | |
since | -0.014 |
unlike | -0.013 |
fulfilled | -0.013 |
stru | -0.012 |
cel | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
moms | +0.073 |
dads | +0.062 |
eps | +0.060 |
slide | +0.058 |
truck | +0.057 |
Neg logit contributions | |
since | -0.062 |
unlike | -0.060 |
fulfilled | -0.059 |
stru | -0.057 |
cel | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +7.90e-04 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.008 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.015 |
dads | -0.013 |
eps | -0.013 |
slide | -0.012 |
towels | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
moms | +0.046 |
dads | +0.040 |
eps | +0.038 |
slide | +0.037 |
truck | +0.036 |
Neg logit contributions | |
since | -0.033 |
unlike | -0.031 |
fulfilled | -0.030 |
stru | -0.029 |
cel | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
fulfilled | +0.009 |
unlike | +0.009 |
since | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
slide | -0.009 |
truck | -0.009 |
eps | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.001 |
fulfilled | +0.001 |
cel | +0.001 |
Mill | +0.001 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
sled | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
since | +0.003 |
fulfilled | +0.003 |
unlike | +0.003 |
stru | +0.003 |
Mill | +0.003 |
Neg logit contributions | |
moms | -0.004 |
dads | -0.004 |
slide | -0.004 |
eps | -0.004 |
truck | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
since | +0.006 |
fulfilled | +0.005 |
unlike | +0.005 |
cel | +0.005 |
zing | +0.005 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.008 |
slide | -0.007 |
microwave | -0.007 |
truck | -0.007 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
since | +0.038 |
cel | +0.035 |
unlike | +0.035 |
EX | +0.035 |
fulfilled | +0.034 |
Neg logit contributions | |
moms | -0.052 |
dads | -0.049 |
eps | -0.045 |
sled | -0.044 |
dad | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
moms | +0.272 |
dads | +0.234 |
slide | +0.229 |
eps | +0.226 |
truck | +0.222 |
Neg logit contributions | |
since | -0.174 |
fulfilled | -0.171 |
unlike | -0.170 |
stru | -0.163 |
cel | -0.163 |
Token | mine |
Token ID | 6164 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
This | +0.006 |
Nice | +0.006 |
grant | +0.006 |
Neg logit contributions | |
moms | -0.012 |
eps | -0.012 |
dads | -0.011 |
microwave | -0.010 |
snowball | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
moms | +0.101 |
dads | +0.088 |
eps | +0.085 |
slide | +0.084 |
truck | +0.082 |
Neg logit contributions | |
since | -0.059 |
unlike | -0.057 |
fulfilled | -0.056 |
stru | -0.054 |
cel | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
Nice | +0.002 |
fulfilled | +0.001 |
This | +0.001 |
Neg logit contributions | |
moms | -0.004 |
eps | -0.004 |
dads | -0.004 |
microwave | -0.003 |
snowball | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
moms | +0.009 |
dads | +0.007 |
eps | +0.007 |
slide | +0.007 |
towels | +0.006 |
Neg logit contributions | |
since | -0.011 |
unlike | -0.010 |
fulfilled | -0.010 |
stru | -0.010 |
cel | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
since | +0.017 |
unlike | +0.017 |
fulfilled | +0.016 |
stru | +0.016 |
cel | +0.016 |
Neg logit contributions | |
moms | -0.020 |
dads | -0.017 |
eps | -0.016 |
slide | -0.016 |
truck | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.005 |
eps | +0.005 |
slide | +0.005 |
towels | +0.005 |
Neg logit contributions | |
since | -0.004 |
unlike | -0.004 |
fulfilled | -0.004 |
stru | -0.004 |
knowing | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -6.55e-03 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.005 |
eps | +0.005 |
sled | +0.004 |
snowball | +0.004 |
Neg logit contributions | |
since | -0.005 |
fulfilled | -0.005 |
unlike | -0.005 |
cel | -0.005 |
stru | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
moms | +0.013 |
dads | +0.012 |
eps | +0.011 |
slide | +0.011 |
truck | +0.011 |
Neg logit contributions | |
since | -0.009 |
unlike | -0.009 |
fulfilled | -0.009 |
stru | -0.008 |
cel | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
since | +0.018 |
unlike | +0.017 |
fulfilled | +0.017 |
stru | +0.016 |
cel | +0.016 |
Neg logit contributions | |
moms | -0.033 |
dads | -0.028 |
eps | -0.027 |
slide | -0.027 |
truck | -0.026 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
since | +0.042 |
unlike | +0.037 |
fulfilled | +0.036 |
stru | +0.035 |
cel | +0.034 |
Neg logit contributions | |
moms | -0.046 |
dads | -0.042 |
eps | -0.038 |
towels | -0.038 |
sled | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
moms | +0.238 |
dads | +0.200 |
slide | +0.197 |
eps | +0.193 |
truck | +0.191 |
Neg logit contributions | |
since | -0.201 |
fulfilled | -0.198 |
unlike | -0.198 |
stru | -0.193 |
cel | -0.191 |
Token | Mine |
Token ID | 11517 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.012 |
dads | -0.011 |
eps | -0.011 |
slide | -0.010 |
towels | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
moms | +0.115 |
dads | +0.094 |
eps | +0.090 |
slide | +0.087 |
truck | +0.083 |
Neg logit contributions | |
since | -0.134 |
unlike | -0.131 |
fulfilled | -0.129 |
stru | -0.125 |
cel | -0.123 |
Token | Mine |
Token ID | 11517 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.006 |
cel | +0.006 |
stru | +0.006 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.008 |
eps | -0.008 |
slide | -0.008 |
towels | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
moms | +0.114 |
dads | +0.093 |
eps | +0.088 |
slide | +0.085 |
towels | +0.081 |
Neg logit contributions | |
since | -0.142 |
unlike | -0.138 |
fulfilled | -0.137 |
stru | -0.132 |
cel | -0.131 |
Token | pull |
Token ID | 2834 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
moms | +0.020 |
dads | +0.018 |
eps | +0.017 |
omo | +0.016 |
Dad | +0.016 |
Neg logit contributions | |
since | -0.016 |
unlike | -0.014 |
fulfilled | -0.013 |
grant | -0.013 |
solving | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
moms | +0.093 |
dads | +0.083 |
eps | +0.076 |
slide | +0.075 |
sandbox | +0.073 |
Neg logit contributions | |
since | -0.060 |
unlike | -0.054 |
fulfilled | -0.051 |
stru | -0.050 |
solving | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-03 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.007 |
fulfilled | +0.007 |
This | +0.007 |
Nice | +0.007 |
Neg logit contributions | |
moms | -0.010 |
eps | -0.009 |
dads | -0.009 |
slide | -0.009 |
cream | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
since | +0.006 |
fulfilled | +0.005 |
unlike | +0.005 |
stru | +0.005 |
Mill | +0.005 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.008 |
eps | -0.008 |
slide | -0.008 |
truck | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
since | +0.010 |
fulfilled | +0.008 |
unlike | +0.008 |
cel | +0.008 |
zing | +0.008 |
Neg logit contributions | |
moms | -0.014 |
dads | -0.013 |
truck | -0.012 |
eps | -0.012 |
slide | -0.012 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
since | +0.036 |
unlike | +0.034 |
EX | +0.032 |
Gr | +0.031 |
fulfilled | +0.031 |
Neg logit contributions | |
moms | -0.052 |
dads | -0.051 |
eps | -0.047 |
sled | -0.046 |
dad | -0.045 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
moms | +0.265 |
dads | +0.227 |
eps | +0.220 |
slide | +0.220 |
truck | +0.214 |
Neg logit contributions | |
since | -0.177 |
unlike | -0.172 |
fulfilled | -0.171 |
stru | -0.164 |
cel | -0.162 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
moms | +0.075 |
eps | +0.071 |
dads | +0.066 |
sled | +0.063 |
slide | +0.062 |
Neg logit contributions | |
since | -0.069 |
unlike | -0.062 |
Mill | -0.060 |
Grac | -0.059 |
fulfilled | -0.057 |
Token | says |
Token ID | 1139 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.005 |
eps | +0.005 |
sled | +0.004 |
towels | +0.003 |
Neg logit contributions | |
since | -0.018 |
unlike | -0.017 |
fulfilled | -0.016 |
stru | -0.016 |
cel | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
moms | +0.075 |
dads | +0.063 |
eps | +0.060 |
slide | +0.059 |
truck | +0.057 |
Neg logit contributions | |
since | -0.068 |
unlike | -0.067 |
fulfilled | -0.066 |
stru | -0.064 |
cel | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.008 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.013 |
dads | -0.011 |
eps | -0.011 |
slide | -0.011 |
towels | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
moms | +0.015 |
dads | +0.012 |
eps | +0.012 |
slide | +0.011 |
truck | +0.011 |
Neg logit contributions | |
since | -0.016 |
unlike | -0.015 |
fulfilled | -0.015 |
stru | -0.014 |
cel | -0.014 |
Token | Baby |
Token ID | 36534 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.005 |
eps | +0.005 |
slide | +0.005 |
truck | +0.005 |
Neg logit contributions | |
since | -0.009 |
unlike | -0.009 |
fulfilled | -0.008 |
stru | -0.008 |
cel | -0.008 |
Token | replied |
Token ID | 8712 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
moms | +0.026 |
dads | +0.022 |
eps | +0.021 |
towels | +0.020 |
slide | +0.020 |
Neg logit contributions | |
since | -0.028 |
unlike | -0.026 |
fulfilled | -0.026 |
stru | -0.025 |
cel | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
slide | -0.002 |
truck | -0.002 |
dad | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
since | +0.015 |
unlike | +0.015 |
fulfilled | +0.014 |
stru | +0.014 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.025 |
eps | -0.024 |
slide | -0.023 |
truck | -0.023 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
since | +0.048 |
unlike | +0.046 |
fulfilled | +0.042 |
stru | +0.041 |
cel | +0.040 |
Neg logit contributions | |
moms | -0.042 |
dads | -0.037 |
eps | -0.034 |
slide | -0.033 |
says | -0.033 |
Token | ? |
Token ID | 30 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
moms | +0.263 |
slide | +0.228 |
dads | +0.226 |
truck | +0.224 |
eps | +0.221 |
Neg logit contributions | |
since | -0.168 |
fulfilled | -0.167 |
stru | -0.165 |
unlike | -0.164 |
cel | -0.163 |
Token | Please |
Token ID | 4222 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.008 |
fulfilled | +0.008 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.019 |
dads | -0.017 |
eps | -0.017 |
slide | -0.016 |
truck | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
moms | +0.052 |
dads | +0.044 |
eps | +0.043 |
slide | +0.040 |
towels | +0.040 |
Neg logit contributions | |
since | -0.047 |
fulfilled | -0.044 |
unlike | -0.044 |
cel | -0.042 |
stru | -0.042 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
moms | +0.026 |
eps | +0.024 |
dads | +0.021 |
ep | +0.018 |
towels | +0.018 |
Neg logit contributions | |
since | -0.046 |
unlike | -0.043 |
fulfilled | -0.041 |
Mill | -0.041 |
Nice | -0.040 |
Token | my |
Token ID | 1820 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.033 |
eps | +0.031 |
slide | +0.030 |
towels | +0.029 |
Neg logit contributions | |
since | -0.047 |
unlike | -0.044 |
fulfilled | -0.043 |
cel | -0.041 |
stru | -0.041 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
moms | +0.046 |
dads | +0.039 |
eps | +0.038 |
slide | +0.037 |
truck | +0.036 |
Neg logit contributions | |
since | -0.037 |
unlike | -0.036 |
fulfilled | -0.036 |
stru | -0.034 |
cel | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
moms | +0.051 |
dads | +0.042 |
slide | +0.042 |
eps | +0.042 |
truck | +0.041 |
Neg logit contributions | |
since | -0.045 |
fulfilled | -0.044 |
unlike | -0.043 |
stru | -0.043 |
cel | -0.042 |
Token | said |
Token ID | 531 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
moms | +0.016 |
dads | +0.013 |
eps | +0.013 |
slide | +0.013 |
truck | +0.012 |
Neg logit contributions | |
since | -0.012 |
unlike | -0.012 |
fulfilled | -0.011 |
stru | -0.011 |
cel | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
moms | +0.014 |
dad | +0.012 |
slide | +0.012 |
truck | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
since | -0.017 |
cel | -0.016 |
fulfilled | -0.016 |
stru | -0.015 |
generations | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
since | +0.019 |
fulfilled | +0.019 |
stru | +0.018 |
unlike | +0.018 |
cel | +0.017 |
Neg logit contributions | |
moms | -0.021 |
slide | -0.018 |
truck | -0.018 |
dad | -0.018 |
dads | -0.018 |
Token | Mine |
Token ID | 24461 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
since | +0.058 |
fulfilled | +0.057 |
unlike | +0.057 |
stru | +0.054 |
cel | +0.054 |
Neg logit contributions | |
moms | -0.045 |
eps | -0.036 |
dads | -0.036 |
slide | -0.035 |
towels | -0.032 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
moms | +0.232 |
slide | +0.211 |
truck | +0.203 |
dads | +0.194 |
says | +0.191 |
Neg logit contributions | |
fulfilled | -0.191 |
stru | -0.189 |
cel | -0.187 |
since | -0.184 |
granting | -0.178 |
Token | He |
Token ID | 679 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
moms | +0.082 |
dads | +0.071 |
eps | +0.068 |
slide | +0.066 |
towels | +0.063 |
Neg logit contributions | |
since | -0.061 |
unlike | -0.058 |
fulfilled | -0.057 |
stru | -0.054 |
cel | -0.053 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
moms | +0.055 |
dads | +0.048 |
eps | +0.044 |
slide | +0.043 |
towels | +0.043 |
Neg logit contributions | |
since | -0.052 |
unlike | -0.051 |
fulfilled | -0.049 |
stru | -0.048 |
cel | -0.046 |
Token | towards |
Token ID | 3371 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
moms | +0.004 |
truck | +0.004 |
slide | +0.004 |
Tom | +0.004 |
sled | +0.004 |
Neg logit contributions | |
cel | -0.005 |
fulfilled | -0.004 |
unlike | -0.004 |
ulent | -0.004 |
cess | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
moms | +0.060 |
dads | +0.051 |
eps | +0.049 |
slide | +0.048 |
truck | +0.046 |
Neg logit contributions | |
since | -0.055 |
unlike | -0.054 |
fulfilled | -0.053 |
stru | -0.051 |
cel | -0.050 |
Token | Stella |
Token ID | 45856 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
unlike | +0.105 |
fulfilled | +0.103 |
since | +0.101 |
stru | +0.101 |
cel | +0.095 |
Neg logit contributions | |
moms | -0.071 |
dads | -0.055 |
Tom | -0.053 |
slide | -0.052 |
dad | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
unlike | +0.056 |
fulfilled | +0.054 |
since | +0.054 |
stru | +0.051 |
cel | +0.051 |
Neg logit contributions | |
moms | -0.050 |
dads | -0.041 |
slide | -0.039 |
eps | -0.039 |
truck | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
stru | +0.016 |
unlike | +0.016 |
since | +0.016 |
fulfilled | +0.015 |
cel | +0.015 |
Neg logit contributions | |
moms | -0.025 |
slide | -0.021 |
dads | -0.021 |
Tom | -0.020 |
truck | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
since | +0.057 |
unlike | +0.056 |
fulfilled | +0.055 |
stru | +0.054 |
cel | +0.052 |
Neg logit contributions | |
moms | -0.039 |
slide | -0.031 |
dads | -0.030 |
eps | -0.029 |
dad | -0.027 |
Token | three |
Token ID | 1115 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
moms | +0.007 |
dads | +0.006 |
dad | +0.006 |
slide | +0.006 |
also | +0.005 |
Neg logit contributions | |
since | -0.010 |
fulfilled | -0.010 |
cel | -0.010 |
unlike | -0.010 |
stru | -0.009 |
Token | years |
Token ID | 812 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
since | +0.031 |
unlike | +0.031 |
fulfilled | +0.030 |
stru | +0.029 |
cel | +0.027 |
Neg logit contributions | |
moms | -0.057 |
dads | -0.050 |
eps | -0.048 |
slide | -0.047 |
truck | -0.046 |
Token | old |
Token ID | 1468 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
unlike | +0.164 |
cel | +0.162 |
since | +0.161 |
fulfilled | +0.159 |
stru | +0.157 |
Neg logit contributions | |
moms | -0.167 |
dads | -0.137 |
dad | -0.136 |
truck | -0.130 |
slide | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
unlike | +0.006 |
fulfilled | +0.006 |
since | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.007 |
dads | -0.005 |
slide | -0.005 |
truck | -0.005 |
eps | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.011 |
fulfilled | +0.011 |
stru | +0.011 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.012 |
dads | -0.010 |
eps | -0.010 |
slide | -0.009 |
towels | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
moms | +0.077 |
dads | +0.068 |
slide | +0.065 |
dad | +0.065 |
snow | +0.064 |
Neg logit contributions | |
since | -0.040 |
fulfilled | -0.038 |
cel | -0.038 |
unlike | -0.038 |
stru | -0.036 |
Token | rub |
Token ID | 6437 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
since | +0.050 |
unlike | +0.049 |
fulfilled | +0.049 |
stru | +0.047 |
cel | +0.046 |
Neg logit contributions | |
moms | -0.039 |
dads | -0.032 |
eps | -0.031 |
slide | -0.028 |
truck | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
moms | +0.013 |
dads | +0.011 |
eps | +0.011 |
dad | +0.011 |
slide | +0.010 |
Neg logit contributions | |
stru | -0.011 |
cel | -0.011 |
since | -0.011 |
fulfilled | -0.011 |
unlike | -0.010 |
Token | best |
Token ID | 1266 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
since | +0.057 |
unlike | +0.055 |
fulfilled | +0.054 |
stru | +0.049 |
knowing | +0.048 |
Neg logit contributions | |
moms | -0.071 |
eps | -0.062 |
dads | -0.061 |
says | -0.056 |
towels | -0.056 |
Token | food |
Token ID | 2057 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.012 |
fulfilled | +0.011 |
stru | +0.011 |
cel | +0.011 |
Neg logit contributions | |
moms | -0.008 |
dads | -0.007 |
eps | -0.006 |
slide | -0.006 |
truck | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
since | +0.005 |
fulfilled | +0.005 |
unlike | +0.005 |
stru | +0.005 |
cel | +0.005 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.008 |
slide | -0.008 |
truck | -0.008 |
eps | -0.007 |
Token | ever |
Token ID | 1683 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
unlike | +0.090 |
since | +0.088 |
cel | +0.087 |
andel | +0.087 |
stru | +0.086 |
Neg logit contributions | |
moms | -0.095 |
dads | -0.081 |
eps | -0.078 |
slide | -0.077 |
dad | -0.076 |
Token | tasted |
Token ID | 29187 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
unlike | +0.045 |
Nice | +0.042 |
cel | +0.042 |
stru | +0.041 |
fulfilled | +0.041 |
Neg logit contributions | |
moms | -0.033 |
eps | -0.028 |
dads | -0.028 |
slide | -0.027 |
says | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
cel | +0.129 |
stru | +0.123 |
cess | +0.117 |
osity | +0.115 |
fulfilled | +0.115 |
Neg logit contributions | |
moms | -0.123 |
slide | -0.111 |
cream | -0.110 |
fountain | -0.100 |
dads | -0.100 |
Token | She |
Token ID | 1375 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
unlike | +0.003 |
since | +0.003 |
fulfilled | +0.003 |
stru | +0.003 |
cel | +0.003 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.002 |
slide | -0.002 |
says | -0.002 |
dad | -0.002 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
since | +0.052 |
unlike | +0.050 |
fulfilled | +0.050 |
stru | +0.047 |
cel | +0.046 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.043 |
eps | -0.042 |
slide | -0.040 |
truck | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
cel | +0.013 |
fulfilled | +0.012 |
since | +0.012 |
stru | +0.012 |
cess | +0.012 |
Neg logit contributions | |
moms | -0.010 |
dad | -0.008 |
slide | -0.008 |
Tom | -0.008 |
dads | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
since | +0.115 |
unlike | +0.112 |
fulfilled | +0.110 |
stru | +0.106 |
cel | +0.104 |
Neg logit contributions | |
moms | -0.116 |
dads | -0.098 |
eps | -0.091 |
slide | -0.089 |
towels | -0.087 |
Token | pretend |
Token ID | 16614 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
since | +0.032 |
unlike | +0.030 |
fulfilled | +0.030 |
cel | +0.029 |
stru | +0.028 |
Neg logit contributions | |
moms | -0.037 |
dads | -0.031 |
eps | -0.030 |
truck | -0.028 |
microwave | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
moms | +0.021 |
slide | +0.017 |
truck | +0.017 |
dads | +0.017 |
dad | +0.016 |
Neg logit contributions | |
since | -0.022 |
fulfilled | -0.022 |
stru | -0.022 |
cel | -0.021 |
unlike | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
since | +0.019 |
unlike | +0.019 |
fulfilled | +0.019 |
stru | +0.018 |
cel | +0.018 |
Neg logit contributions | |
moms | -0.015 |
dads | -0.012 |
eps | -0.012 |
slide | -0.012 |
truck | -0.011 |
Token | an |
Token ID | 281 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
since | +0.002 |
stru | +0.002 |
cel | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
Neg logit contributions | |
moms | -0.002 |
dads | -0.001 |
eps | -0.001 |
slide | -0.001 |
dad | -0.001 |
Token | iron |
Token ID | 6953 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
fulfilled | +0.066 |
cel | +0.064 |
unlike | +0.063 |
since | +0.062 |
Nice | +0.062 |
Neg logit contributions | |
moms | -0.073 |
dads | -0.064 |
truck | -0.062 |
dad | -0.062 |
slide | -0.061 |
Token | er |
Token ID | 263 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
fulfilled | +0.071 |
unlike | +0.069 |
since | +0.069 |
stru | +0.068 |
cel | +0.066 |
Neg logit contributions | |
moms | -0.070 |
truck | -0.060 |
slide | -0.060 |
dads | -0.058 |
eps | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
fulfilled | +0.107 |
since | +0.106 |
unlike | +0.104 |
stru | +0.102 |
cel | +0.098 |
Neg logit contributions | |
moms | -0.122 |
dads | -0.104 |
slide | -0.101 |
truck | -0.100 |
eps | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.009 |
fulfilled | +0.008 |
Nice | +0.008 |
This | +0.008 |
Neg logit contributions | |
moms | -0.017 |
eps | -0.015 |
towels | -0.015 |
dads | -0.015 |
cream | -0.014 |
Token | imagined |
Token ID | 15758 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
moms | +0.027 |
dads | +0.024 |
eps | +0.022 |
towels | +0.021 |
microwave | +0.021 |
Neg logit contributions | |
since | -0.024 |
unlike | -0.022 |
fulfilled | -0.022 |
stru | -0.021 |
cel | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
since | +0.031 |
unlike | +0.030 |
fulfilled | +0.030 |
stru | +0.029 |
cel | +0.029 |
Neg logit contributions | |
moms | -0.033 |
dads | -0.028 |
eps | -0.027 |
slide | -0.026 |
truck | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
moms | +0.018 |
dads | +0.016 |
eps | +0.015 |
slide | +0.014 |
towels | +0.014 |
Neg logit contributions | |
since | -0.015 |
unlike | -0.015 |
fulfilled | -0.014 |
stru | -0.013 |
cel | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
moms | +0.014 |
dads | +0.012 |
slide | +0.011 |
truck | +0.011 |
sled | +0.011 |
Neg logit contributions | |
since | -0.012 |
fulfilled | -0.012 |
unlike | -0.012 |
stru | -0.012 |
cel | -0.011 |
Token | Carl |
Token ID | 8124 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
since | +0.011 |
fulfilled | +0.011 |
unlike | +0.011 |
cel | +0.011 |
stru | +0.011 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.009 |
slide | -0.009 |
eps | -0.009 |
truck | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
moms | +0.031 |
dads | +0.026 |
eps | +0.025 |
slide | +0.025 |
truck | +0.023 |
Neg logit contributions | |
unlike | -0.034 |
since | -0.033 |
fulfilled | -0.033 |
stru | -0.032 |
cel | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
moms | +0.016 |
dads | +0.013 |
eps | +0.012 |
slide | +0.012 |
dad | +0.012 |
Neg logit contributions | |
since | -0.017 |
cel | -0.016 |
unlike | -0.016 |
Nice | -0.016 |
stru | -0.016 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
unlike | +0.026 |
since | +0.026 |
cel | +0.026 |
stru | +0.025 |
fulfilled | +0.025 |
Neg logit contributions | |
moms | -0.024 |
dads | -0.020 |
slide | -0.019 |
dad | -0.019 |
truck | -0.019 |
Token | cater |
Token ID | 20825 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
since | +0.027 |
unlike | +0.027 |
fulfilled | +0.027 |
stru | +0.027 |
cel | +0.027 |
Neg logit contributions | |
moms | -0.021 |
dads | -0.017 |
slide | -0.016 |
dad | -0.015 |
truck | -0.015 |
Token | pillar |
Token ID | 41643 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
unlike | +0.098 |
fulfilled | +0.096 |
since | +0.094 |
stru | +0.092 |
cel | +0.087 |
Neg logit contributions | |
moms | -0.157 |
slide | -0.140 |
dads | -0.134 |
truck | -0.131 |
fountain | -0.129 |
Token | who |
Token ID | 508 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
unlike | +0.090 |
fulfilled | +0.088 |
stru | +0.088 |
cel | +0.085 |
since | +0.085 |
Neg logit contributions | |
moms | -0.091 |
slide | -0.077 |
dads | -0.075 |
truck | -0.075 |
Rex | -0.070 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.016 |
eps | +0.015 |
slide | +0.015 |
truck | +0.015 |
Neg logit contributions | |
since | -0.020 |
unlike | -0.019 |
fulfilled | -0.019 |
stru | -0.018 |
cel | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
moms | +0.084 |
dads | +0.074 |
slide | +0.070 |
eps | +0.070 |
truck | +0.069 |
Neg logit contributions | |
since | -0.047 |
fulfilled | -0.046 |
unlike | -0.045 |
stru | -0.043 |
cel | -0.043 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
since | +0.056 |
unlike | +0.054 |
fulfilled | +0.054 |
stru | +0.051 |
cel | +0.051 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.043 |
eps | -0.042 |
slide | -0.038 |
truck | -0.038 |
Token | day |
Token ID | 1110 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
moms | +0.024 |
eps | +0.020 |
dads | +0.020 |
slide | +0.018 |
towels | +0.018 |
Neg logit contributions | |
since | -0.023 |
unlike | -0.022 |
fulfilled | -0.021 |
stru | -0.020 |
knowing | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
unlike | +0.046 |
stru | +0.044 |
since | +0.044 |
cel | +0.044 |
fulfilled | +0.044 |
Neg logit contributions | |
moms | -0.073 |
dads | -0.065 |
slide | -0.063 |
truck | -0.061 |
eps | -0.061 |
Token | they |
Token ID | 484 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
moms | +0.034 |
dads | +0.028 |
slide | +0.027 |
eps | +0.027 |
truck | +0.027 |
Neg logit contributions | |
since | -0.029 |
unlike | -0.029 |
fulfilled | -0.028 |
stru | -0.028 |
cel | -0.028 |
Token | would |
Token ID | 561 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.008 |
eps | +0.008 |
slide | +0.008 |
truck | +0.008 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.010 |
fulfilled | -0.010 |
stru | -0.009 |
cel | -0.009 |
Token | never |
Token ID | 1239 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
since | +0.010 |
fulfilled | +0.010 |
unlike | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.011 |
eps | -0.009 |
dads | -0.009 |
truck | -0.008 |
towels | -0.008 |
Token | forget |
Token ID | 6044 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
since | +0.042 |
unlike | +0.042 |
fulfilled | +0.040 |
stru | +0.039 |
cel | +0.039 |
Neg logit contributions | |
moms | -0.047 |
dads | -0.040 |
slide | -0.038 |
eps | -0.037 |
truck | -0.035 |
Token | ! |
Token ID | 0 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
since | +0.124 |
unlike | +0.119 |
fulfilled | +0.117 |
stru | +0.112 |
cel | +0.109 |
Neg logit contributions | |
moms | -0.167 |
dads | -0.143 |
eps | -0.138 |
slide | -0.134 |
truck | -0.130 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.008 |
fulfilled | +0.008 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.006 |
dads | -0.005 |
eps | -0.004 |
slide | -0.004 |
truck | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
since | +0.003 |
fulfilled | +0.002 |
unlike | +0.002 |
cel | +0.002 |
stru | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
towels | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
since | +0.029 |
unlike | +0.026 |
fulfilled | +0.025 |
stru | +0.024 |
Mill | +0.024 |
Neg logit contributions | |
moms | -0.054 |
dads | -0.048 |
eps | -0.047 |
slide | -0.045 |
towels | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
since | +0.041 |
unlike | +0.038 |
fulfilled | +0.036 |
Mill | +0.035 |
stru | +0.035 |
Neg logit contributions | |
moms | -0.049 |
dads | -0.043 |
eps | -0.042 |
towels | -0.038 |
microwave | -0.038 |
Token | at |
Token ID | 379 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
since | +0.050 |
unlike | +0.048 |
fulfilled | +0.047 |
stru | +0.045 |
cel | +0.043 |
Neg logit contributions | |
moms | -0.071 |
dads | -0.061 |
eps | -0.058 |
slide | -0.057 |
truck | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
eps | +0.008 |
timer | +0.008 |
microwave | +0.008 |
moms | +0.008 |
ep | +0.007 |
Neg logit contributions | |
since | -0.005 |
such | -0.004 |
Bun | -0.003 |
wherever | -0.003 |
Ros | -0.003 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
unlike | +0.026 |
since | +0.026 |
fulfilled | +0.026 |
knowing | +0.026 |
healing | +0.026 |
Neg logit contributions | |
dads | -0.019 |
moms | -0.019 |
agree | -0.017 |
Deal | -0.014 |
argue | -0.013 |
Token | pl |
Token ID | 458 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
moms | +0.098 |
dads | +0.094 |
agree | +0.083 |
eps | +0.083 |
Ben | +0.078 |
Neg logit contributions | |
unlike | -0.059 |
since | -0.058 |
knowing | -0.055 |
cel | -0.051 |
among | -0.050 |
Token | ow |
Token ID | 322 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
stru | +0.018 |
unlike | +0.018 |
since | +0.017 |
fulfilled | +0.017 |
cel | +0.017 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.024 |
slide | -0.023 |
towels | -0.022 |
dad | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
moms | +0.067 |
dads | +0.060 |
eps | +0.055 |
slide | +0.054 |
sandbox | +0.053 |
Neg logit contributions | |
since | -0.038 |
unlike | -0.035 |
fulfilled | -0.034 |
zing | -0.033 |
stru | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
unlike | +0.010 |
since | +0.010 |
fulfilled | +0.009 |
Nice | +0.009 |
This | +0.009 |
Neg logit contributions | |
moms | -0.014 |
eps | -0.013 |
dads | -0.013 |
slide | -0.012 |
sled | -0.011 |
Token | driver |
Token ID | 4639 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
dads | +0.009 |
moms | +0.009 |
agree | +0.008 |
illas | +0.007 |
argue | +0.007 |
Neg logit contributions | |
healing | -0.011 |
knowing | -0.010 |
since | -0.010 |
fulfilled | -0.010 |
unlike | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
moms | +0.087 |
dads | +0.082 |
sunscreen | +0.071 |
towels | +0.069 |
sled | +0.067 |
Neg logit contributions | |
since | -0.073 |
fulfilled | -0.069 |
stru | -0.068 |
unlike | -0.066 |
granted | -0.064 |
Token | them |
Token ID | 606 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
moms | +0.045 |
eps | +0.042 |
dads | +0.040 |
sled | +0.039 |
oyd | +0.037 |
Neg logit contributions | |
since | -0.037 |
such | -0.033 |
unlike | -0.032 |
giving | -0.032 |
knowing | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
moms | +0.044 |
dads | +0.039 |
eps | +0.035 |
Ben | +0.033 |
microwave | +0.033 |
Neg logit contributions | |
since | -0.025 |
unlike | -0.022 |
fulfilled | -0.022 |
knowing | -0.021 |
exploring | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
since | +0.021 |
unlike | +0.020 |
fulfilled | +0.020 |
stru | +0.019 |
cel | +0.019 |
Neg logit contributions | |
moms | -0.023 |
dads | -0.020 |
eps | -0.019 |
slide | -0.018 |
towels | -0.018 |
Token | walking |
Token ID | 6155 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.013 |
fulfilled | +0.013 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
eps | -0.014 |
slide | -0.013 |
truck | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
unlike | +0.057 |
fulfilled | +0.056 |
since | +0.056 |
cel | +0.056 |
stru | +0.053 |
Neg logit contributions | |
moms | -0.072 |
dads | -0.062 |
slide | -0.061 |
truck | -0.059 |
sled | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
since | +0.047 |
unlike | +0.046 |
fulfilled | +0.045 |
stru | +0.044 |
cel | +0.043 |
Neg logit contributions | |
moms | -0.049 |
dads | -0.041 |
eps | -0.039 |
slide | -0.039 |
truck | -0.037 |
Token | woods |
Token ID | 16479 |
Feature activation | +1.41e-04 |
Pos logit contributions | |
since | +0.045 |
fulfilled | +0.043 |
unlike | +0.042 |
exploring | +0.039 |
stru | +0.039 |
Neg logit contributions | |
moms | -0.045 |
dads | -0.039 |
eps | -0.038 |
towels | -0.035 |
agree | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
cel | +0.000 |
fulfilled | +0.000 |
unlike | +0.000 |
since | +0.000 |
stru | +0.000 |
Neg logit contributions | |
moms | -0.000 |
slide | -0.000 |
truck | -0.000 |
dads | -0.000 |
eps | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
since | +0.025 |
fulfilled | +0.025 |
stru | +0.024 |
cel | +0.024 |
unlike | +0.024 |
Neg logit contributions | |
moms | -0.029 |
Tom | -0.025 |
slide | -0.025 |
dads | -0.024 |
truck | -0.024 |
Token | came |
Token ID | 1625 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
moms | +0.012 |
dads | +0.010 |
eps | +0.009 |
towels | +0.009 |
slide | +0.008 |
Neg logit contributions | |
since | -0.014 |
unlike | -0.014 |
fulfilled | -0.013 |
stru | -0.013 |
cel | -0.013 |
Token | across |
Token ID | 1973 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
cel | +0.086 |
unlike | +0.075 |
since | +0.071 |
cess | +0.070 |
Emmy | +0.070 |
Neg logit contributions | |
moms | -0.103 |
dads | -0.091 |
eps | -0.090 |
also | -0.087 |
dad | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
moms | +0.016 |
dads | +0.013 |
eps | +0.012 |
slide | +0.012 |
truck | +0.011 |
Neg logit contributions | |
since | -0.019 |
unlike | -0.019 |
fulfilled | -0.018 |
stru | -0.018 |
cel | -0.018 |
Token | small |
Token ID | 1402 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
moms | +0.026 |
dads | +0.022 |
eps | +0.021 |
towels | +0.020 |
says | +0.019 |
Neg logit contributions | |
since | -0.021 |
unlike | -0.020 |
fulfilled | -0.020 |
cel | -0.018 |
stru | -0.018 |
Token | fly |
Token ID | 6129 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.017 |
eps | +0.016 |
microwave | +0.015 |
towels | +0.014 |
Neg logit contributions | |
fulfilled | -0.019 |
since | -0.018 |
unlike | -0.018 |
stru | -0.017 |
solving | -0.017 |
Token | away |
Token ID | 1497 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
since | +0.045 |
fulfilled | +0.042 |
unlike | +0.041 |
stru | +0.038 |
knowing | +0.036 |
Neg logit contributions | |
moms | -0.073 |
dads | -0.065 |
eps | -0.061 |
microwave | -0.059 |
slide | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.002 |
eps | -0.002 |
slide | -0.002 |
truck | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
since | +0.008 |
This | +0.008 |
Nice | +0.008 |
unlike | +0.008 |
fulfilled | +0.008 |
Neg logit contributions | |
moms | -0.012 |
eps | -0.012 |
dads | -0.011 |
cream | -0.011 |
slide | -0.011 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
eps | +0.018 |
dads | +0.018 |
Jacob | +0.017 |
olo | +0.017 |
moms | +0.017 |
Neg logit contributions | |
healing | -0.008 |
fulfilled | -0.008 |
unlike | -0.007 |
exploring | -0.007 |
giving | -0.007 |
Token | thanks |
Token ID | 5176 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
moms | +0.003 |
dads | +0.003 |
eps | +0.003 |
towels | +0.002 |
dad | +0.002 |
Neg logit contributions | |
since | -0.003 |
fulfilled | -0.003 |
unlike | -0.003 |
stru | -0.003 |
cel | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
since | +0.094 |
unlike | +0.089 |
fulfilled | +0.087 |
knowing | +0.085 |
Mill | +0.084 |
Neg logit contributions | |
moms | -0.055 |
eps | -0.047 |
dads | -0.043 |
slide | -0.041 |
snowball | -0.038 |
Token | with |
Token ID | 351 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
moms | +0.024 |
dads | +0.020 |
eps | +0.019 |
slide | +0.019 |
truck | +0.019 |
Neg logit contributions | |
unlike | -0.021 |
since | -0.021 |
fulfilled | -0.020 |
cel | -0.019 |
stru | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
moms | +0.017 |
slide | +0.016 |
microwave | +0.016 |
eps | +0.015 |
dads | +0.015 |
Neg logit contributions | |
such | -0.012 |
fulfilled | -0.011 |
knowing | -0.011 |
unlike | -0.011 |
since | -0.010 |
Token | song |
Token ID | 3496 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
fulfilled | +0.009 |
unlike | +0.009 |
since | +0.009 |
stru | +0.008 |
knowing | +0.008 |
Neg logit contributions | |
moms | -0.010 |
eps | -0.008 |
dads | -0.008 |
towels | -0.007 |
Rex | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
since | +0.056 |
unlike | +0.052 |
fulfilled | +0.051 |
knowing | +0.048 |
stru | +0.046 |
Neg logit contributions | |
moms | -0.094 |
dads | -0.083 |
eps | -0.082 |
slide | -0.076 |
towels | -0.074 |
Token | it |
Token ID | 340 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
since | +0.021 |
fulfilled | +0.020 |
unlike | +0.020 |
stru | +0.020 |
cel | +0.019 |
Neg logit contributions | |
moms | -0.025 |
dads | -0.021 |
eps | -0.020 |
slide | -0.020 |
dad | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-03 |
Pos logit contributions | |
since | +0.047 |
unlike | +0.047 |
fulfilled | +0.046 |
stru | +0.046 |
cel | +0.045 |
Neg logit contributions | |
moms | -0.035 |
eps | -0.028 |
dads | -0.027 |
slide | -0.026 |
truck | -0.026 |
Token | true |
Token ID | 2081 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
moms | +0.002 |
dads | +0.002 |
eps | +0.002 |
dad | +0.002 |
slide | +0.002 |
Neg logit contributions | |
stru | -0.002 |
since | -0.002 |
cel | -0.002 |
unlike | -0.002 |
fulfilled | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
unlike | +0.102 |
stru | +0.101 |
cel | +0.100 |
fulfilled | +0.098 |
zing | +0.094 |
Neg logit contributions | |
moms | -0.114 |
dad | -0.095 |
dads | -0.093 |
truck | -0.091 |
towels | -0.089 |
Token | F |
Token ID | 376 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
cel | +0.011 |
since | +0.010 |
fulfilled | +0.010 |
unlike | +0.010 |
ulent | +0.010 |
Neg logit contributions | |
moms | -0.011 |
Mom | -0.010 |
says | -0.010 |
dad | -0.010 |
mom | -0.009 |
Token | ailing |
Token ID | 11608 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
moms | +0.064 |
dads | +0.054 |
eps | +0.053 |
slide | +0.051 |
towels | +0.049 |
Neg logit contributions | |
since | -0.051 |
unlike | -0.050 |
fulfilled | -0.050 |
stru | -0.047 |
cel | -0.047 |
Token | isn |
Token ID | 2125 |
Feature activation | -2.69e-03 |
Pos logit contributions | |
since | +0.023 |
unlike | +0.022 |
fulfilled | +0.022 |
stru | +0.022 |
cel | +0.022 |
Neg logit contributions | |
moms | -0.023 |
dads | -0.019 |
eps | -0.018 |
slide | -0.018 |
truck | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
moms | +0.005 |
eps | +0.004 |
slide | +0.004 |
dads | +0.004 |
truck | +0.004 |
Neg logit contributions | |
since | -0.004 |
fulfilled | -0.004 |
unlike | -0.004 |
cel | -0.003 |
stru | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
cel | +0.015 |
stru | +0.014 |
ulent | +0.014 |
Nice | +0.014 |
cess | +0.013 |
Neg logit contributions | |
moms | -0.011 |
snow | -0.010 |
dad | -0.010 |
dads | -0.010 |
eps | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +3.92e-03 |
Pos logit contributions | |
cel | +0.082 |
stru | +0.082 |
since | +0.082 |
unlike | +0.081 |
fulfilled | +0.079 |
Neg logit contributions | |
moms | -0.081 |
dads | -0.069 |
eps | -0.065 |
slide | -0.065 |
says | -0.063 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.007 |
dads | -0.006 |
slide | -0.005 |
eps | -0.005 |
truck | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
fulfilled | +0.010 |
stru | +0.010 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.018 |
dads | -0.016 |
eps | -0.015 |
slide | -0.015 |
truck | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
since | +0.057 |
fulfilled | +0.054 |
unlike | +0.052 |
stru | +0.049 |
knowing | +0.049 |
Neg logit contributions | |
moms | -0.042 |
dads | -0.039 |
sled | -0.036 |
slide | -0.035 |
eps | -0.034 |
Token | he |
Token ID | 339 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
moms | +0.011 |
dads | +0.009 |
slide | +0.009 |
eps | +0.009 |
dad | +0.009 |
Neg logit contributions | |
since | -0.009 |
unlike | -0.008 |
fulfilled | -0.008 |
stru | -0.008 |
cel | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
since | +0.020 |
fulfilled | +0.019 |
unlike | +0.019 |
cel | +0.018 |
stru | +0.018 |
Neg logit contributions | |
moms | -0.027 |
dads | -0.025 |
sled | -0.023 |
towels | -0.023 |
slide | -0.023 |
Token | depend |
Token ID | 4745 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.008 |
eps | +0.008 |
slide | +0.008 |
towels | +0.007 |
Neg logit contributions | |
since | -0.012 |
unlike | -0.011 |
fulfilled | -0.011 |
stru | -0.011 |
cel | -0.011 |
Token | able |
Token ID | 540 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
since | +0.076 |
fulfilled | +0.070 |
stru | +0.068 |
unlike | +0.066 |
cel | +0.064 |
Neg logit contributions | |
moms | -0.104 |
dads | -0.089 |
slide | -0.083 |
sled | -0.082 |
eps | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
since | +0.055 |
unlike | +0.055 |
fulfilled | +0.054 |
stru | +0.052 |
cel | +0.051 |
Neg logit contributions | |
moms | -0.065 |
dads | -0.055 |
eps | -0.052 |
slide | -0.051 |
truck | -0.050 |
Token | she |
Token ID | 673 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
fulfilled | +0.011 |
stru | +0.010 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.013 |
dads | -0.011 |
eps | -0.011 |
slide | -0.011 |
towels | -0.011 |
Token | missed |
Token ID | 6825 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
since | +0.083 |
fulfilled | +0.080 |
unlike | +0.080 |
stru | +0.076 |
cel | +0.074 |
Neg logit contributions | |
moms | -0.090 |
dads | -0.078 |
eps | -0.072 |
slide | -0.071 |
towels | -0.070 |
Token | him |
Token ID | 683 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
moms | +0.066 |
dads | +0.055 |
eps | +0.053 |
slide | +0.051 |
truck | +0.050 |
Neg logit contributions | |
since | -0.062 |
unlike | -0.060 |
fulfilled | -0.059 |
stru | -0.057 |
cel | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
moms | +0.069 |
dads | +0.060 |
eps | +0.057 |
slide | +0.055 |
towels | +0.053 |
Neg logit contributions | |
since | -0.049 |
fulfilled | -0.046 |
unlike | -0.046 |
stru | -0.042 |
cel | -0.042 |
Token | looks |
Token ID | 3073 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
moms | +0.050 |
dads | +0.042 |
eps | +0.040 |
towels | +0.037 |
slide | +0.036 |
Neg logit contributions | |
since | -0.054 |
unlike | -0.054 |
fulfilled | -0.053 |
stru | -0.051 |
cel | -0.049 |
Token | kind |
Token ID | 1611 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
since | +0.016 |
stru | +0.016 |
fulfilled | +0.016 |
unlike | +0.015 |
cel | +0.015 |
Neg logit contributions | |
moms | -0.014 |
eps | -0.012 |
slide | -0.012 |
dads | -0.012 |
truck | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
since | +0.051 |
unlike | +0.050 |
fulfilled | +0.049 |
cel | +0.047 |
stru | +0.047 |
Neg logit contributions | |
moms | -0.100 |
dads | -0.087 |
slide | -0.084 |
eps | -0.083 |
truck | -0.082 |
Token | scary |
Token ID | 14343 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
since | +0.018 |
unlike | +0.017 |
fulfilled | +0.017 |
stru | +0.016 |
cel | +0.016 |
Neg logit contributions | |
moms | -0.021 |
dads | -0.018 |
eps | -0.018 |
slide | -0.016 |
truck | -0.016 |
Token | ." |
Token ID | 526 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
moms | +0.058 |
dads | +0.049 |
slide | +0.046 |
eps | +0.046 |
truck | +0.045 |
Neg logit contributions | |
since | -0.058 |
unlike | -0.057 |
fulfilled | -0.057 |
stru | -0.055 |
cel | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
moms | +0.034 |
dads | +0.029 |
eps | +0.029 |
slide | +0.027 |
sled | +0.026 |
Neg logit contributions | |
since | -0.025 |
unlike | -0.024 |
fulfilled | -0.023 |
stru | -0.022 |
cel | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
moms | +0.015 |
dads | +0.013 |
eps | +0.012 |
slide | +0.012 |
towels | +0.011 |
Neg logit contributions | |
since | -0.014 |
unlike | -0.013 |
fulfilled | -0.013 |
stru | -0.013 |
cel | -0.013 |
Token | other |
Token ID | 584 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
eps | +0.022 |
microwave | +0.021 |
moms | +0.020 |
sled | +0.019 |
snowball | +0.019 |
Neg logit contributions | |
since | -0.020 |
exploring | -0.019 |
fulfilled | -0.019 |
Nice | -0.019 |
unlike | -0.018 |
Token | friend |
Token ID | 1545 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
moms | +0.111 |
eps | +0.102 |
microwave | +0.098 |
dads | +0.091 |
sled | +0.090 |
Neg logit contributions | |
since | -0.139 |
unlike | -0.126 |
fulfilled | -0.120 |
stru | -0.119 |
Nice | -0.118 |
Token | said |
Token ID | 531 |
Feature activation | -9.05e-03 |
Pos logit contributions | |
moms | +0.027 |
dads | +0.021 |
eps | +0.020 |
sled | +0.019 |
towels | +0.019 |
Neg logit contributions | |
since | -0.043 |
unlike | -0.039 |
fulfilled | -0.039 |
Mill | -0.038 |
stru | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
moms | +0.017 |
dads | +0.015 |
slide | +0.014 |
truck | +0.013 |
dad | +0.013 |
Neg logit contributions | |
since | -0.014 |
fulfilled | -0.014 |
unlike | -0.013 |
cel | -0.013 |
stru | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
moms | +0.011 |
dads | +0.009 |
eps | +0.009 |
slide | +0.009 |
truck | +0.009 |
Neg logit contributions | |
unlike | -0.010 |
since | -0.010 |
fulfilled | -0.009 |
stru | -0.009 |
cel | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
since | +0.004 |
unlike | +0.004 |
fulfilled | +0.003 |
stru | +0.003 |
cel | +0.003 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.003 |
eps | -0.002 |
slide | -0.002 |
truck | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
since | +0.048 |
fulfilled | +0.048 |
unlike | +0.047 |
stru | +0.045 |
cel | +0.044 |
Neg logit contributions | |
moms | -0.054 |
dads | -0.046 |
eps | -0.043 |
slide | -0.042 |
towels | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
since | +0.009 |
fulfilled | +0.009 |
unlike | +0.009 |
stru | +0.009 |
cel | +0.008 |
Neg logit contributions | |
moms | -0.009 |
dads | -0.007 |
eps | -0.007 |
slide | -0.007 |
truck | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -5.11e-03 |
Pos logit contributions | |
since | +0.009 |
fulfilled | +0.008 |
unlike | +0.008 |
stru | +0.008 |
cel | +0.008 |
Neg logit contributions | |
moms | -0.011 |
dads | -0.010 |
eps | -0.009 |
slide | -0.009 |
truck | -0.009 |
Token | End |
Token ID | 5268 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
moms | +0.008 |
eps | +0.008 |
microwave | +0.007 |
towels | +0.007 |
dads | +0.007 |
Neg logit contributions | |
since | -0.008 |
fulfilled | -0.008 |
unlike | -0.007 |
exploring | -0.007 |
hopping | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
moms | +0.015 |
dads | +0.013 |
eps | +0.012 |
slide | +0.012 |
truck | +0.012 |
Neg logit contributions | |
since | -0.013 |
unlike | -0.012 |
fulfilled | -0.012 |
stru | -0.012 |
cel | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
since | +0.006 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.006 |
dads | -0.005 |
eps | -0.005 |
slide | -0.004 |
truck | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.004 |
eps | +0.004 |
slide | +0.004 |
truck | +0.003 |
Neg logit contributions | |
since | -0.005 |
unlike | -0.005 |
fulfilled | -0.005 |
stru | -0.005 |
cel | -0.005 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
since | +0.026 |
unlike | +0.023 |
fulfilled | +0.023 |
stru | +0.022 |
Mill | +0.021 |
Neg logit contributions | |
moms | -0.051 |
dads | -0.045 |
eps | -0.044 |
slide | -0.042 |
towels | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
since | +0.020 |
fulfilled | +0.019 |
unlike | +0.019 |
zing | +0.018 |
stru | +0.018 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.024 |
eps | -0.022 |
truck | -0.022 |
slide | -0.021 |
Token | error |
Token ID | 4049 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
moms | +0.015 |
dads | +0.013 |
eps | +0.013 |
slide | +0.013 |
truck | +0.012 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.009 |
fulfilled | -0.009 |
stru | -0.009 |
cel | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
since | +0.013 |
unlike | +0.013 |
fulfilled | +0.013 |
stru | +0.012 |
cel | +0.012 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
eps | -0.013 |
slide | -0.013 |
truck | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
since | +0.007 |
unlike | +0.006 |
fulfilled | +0.006 |
stru | +0.006 |
cel | +0.006 |
Neg logit contributions | |
moms | -0.012 |
dads | -0.010 |
eps | -0.010 |
slide | -0.010 |
towels | -0.009 |
Token | decided |
Token ID | 3066 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
moms | +0.035 |
dads | +0.031 |
towels | +0.028 |
slide | +0.028 |
eps | +0.028 |
Neg logit contributions | |
since | -0.029 |
fulfilled | -0.027 |
unlike | -0.027 |
stru | -0.026 |
granted | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
unlike | +0.026 |
cel | +0.026 |
since | +0.026 |
fulfilled | +0.025 |
stru | +0.025 |
Neg logit contributions | |
moms | -0.056 |
dads | -0.049 |
slide | -0.047 |
dad | -0.047 |
truck | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
moms | +0.030 |
dads | +0.026 |
eps | +0.026 |
towels | +0.024 |
snowball | +0.024 |
Neg logit contributions | |
since | -0.022 |
unlike | -0.020 |
fulfilled | -0.019 |
solving | -0.018 |
exploring | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
moms | +0.028 |
dads | +0.023 |
eps | +0.022 |
slide | +0.022 |
truck | +0.021 |
Neg logit contributions | |
since | -0.025 |
unlike | -0.024 |
fulfilled | -0.024 |
stru | -0.023 |
cel | -0.023 |
Token | best |
Token ID | 1266 |
Feature activation | -8.13e-04 |
Pos logit contributions | |
since | +0.046 |
unlike | +0.044 |
fulfilled | +0.043 |
stru | +0.040 |
solving | +0.039 |
Neg logit contributions | |
moms | -0.055 |
dads | -0.048 |
eps | -0.045 |
towels | -0.043 |
slide | -0.043 |
Token | plan |
Token ID | 1410 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
moms | +0.001 |
dads | +0.001 |
slide | +0.001 |
truck | +0.001 |
eps | +0.001 |
Neg logit contributions | |
since | -0.001 |
fulfilled | -0.001 |
unlike | -0.001 |
stru | -0.001 |
cel | -0.001 |
Token | - |
Token ID | 532 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
fulfilled | +0.010 |
cel | +0.010 |
stru | +0.010 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.015 |
slide | -0.015 |
eps | -0.014 |
truck | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
moms | +0.020 |
dads | +0.017 |
eps | +0.016 |
slide | +0.016 |
truck | +0.016 |
Neg logit contributions | |
since | -0.016 |
unlike | -0.015 |
fulfilled | -0.015 |
stru | -0.014 |
cel | -0.014 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
moms | +0.006 |
dads | +0.005 |
sled | +0.005 |
towels | +0.005 |
snowball | +0.005 |
Neg logit contributions | |
since | -0.007 |
Mill | -0.006 |
unlike | -0.006 |
fulfilled | -0.006 |
cel | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
since | +0.033 |
unlike | +0.032 |
fulfilled | +0.031 |
stru | +0.030 |
cel | +0.029 |
Neg logit contributions | |
moms | -0.044 |
dads | -0.037 |
eps | -0.035 |
slide | -0.035 |
towels | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
moms | +0.027 |
dads | +0.025 |
eps | +0.025 |
sled | +0.024 |
microwave | +0.023 |
Neg logit contributions | |
since | -0.011 |
Mill | -0.009 |
such | -0.009 |
unlike | -0.008 |
Grace | -0.008 |
Token | building |
Token ID | 2615 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.013 |
stru | +0.013 |
cel | +0.013 |
Neg logit contributions | |
moms | -0.014 |
dads | -0.012 |
eps | -0.012 |
slide | -0.011 |
towels | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
moms | +0.025 |
dads | +0.022 |
eps | +0.021 |
snowball | +0.020 |
towels | +0.020 |
Neg logit contributions | |
since | -0.017 |
unlike | -0.016 |
fulfilled | -0.015 |
stru | -0.015 |
solving | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
moms | +0.024 |
dads | +0.020 |
sled | +0.020 |
snowball | +0.019 |
towels | +0.019 |
Neg logit contributions | |
since | -0.031 |
Mill | -0.028 |
unlike | -0.027 |
fulfilled | -0.027 |
exploring | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
moms | +0.029 |
dads | +0.024 |
slide | +0.023 |
dad | +0.022 |
truck | +0.022 |
Neg logit contributions | |
since | -0.027 |
fulfilled | -0.026 |
unlike | -0.025 |
stru | -0.025 |
cel | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
since | +0.012 |
fulfilled | +0.012 |
unlike | +0.011 |
stru | +0.011 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
slide | -0.014 |
truck | -0.013 |
dad | -0.013 |
Token | That |
Token ID | 2504 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
since | +0.040 |
unlike | +0.038 |
fulfilled | +0.035 |
stru | +0.034 |
Nice | +0.034 |
Neg logit contributions | |
moms | -0.043 |
dads | -0.038 |
eps | -0.035 |
towels | -0.034 |
truck | -0.034 |
Token | is |
Token ID | 318 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
moms | +0.082 |
dads | +0.067 |
eps | +0.065 |
slide | +0.064 |
truck | +0.062 |
Neg logit contributions | |
since | -0.090 |
unlike | -0.087 |
fulfilled | -0.087 |
stru | -0.083 |
cel | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
moms | +0.041 |
dads | +0.032 |
slide | +0.031 |
eps | +0.030 |
truck | +0.030 |
Neg logit contributions | |
stru | -0.051 |
since | -0.050 |
fulfilled | -0.050 |
cel | -0.050 |
zing | -0.049 |
Token | ling |
Token ID | 1359 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
since | +0.027 |
unlike | +0.026 |
fulfilled | +0.026 |
cel | +0.025 |
stru | +0.025 |
Neg logit contributions | |
moms | -0.029 |
dads | -0.025 |
eps | -0.025 |
slide | -0.023 |
towels | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
since | +0.068 |
unlike | +0.066 |
fulfilled | +0.066 |
stru | +0.064 |
cel | +0.064 |
Neg logit contributions | |
moms | -0.077 |
dads | -0.065 |
eps | -0.062 |
slide | -0.062 |
truck | -0.061 |
Token | having |
Token ID | 1719 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
since | +0.010 |
unlike | +0.010 |
fulfilled | +0.009 |
stru | +0.009 |
cel | +0.009 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.014 |
eps | -0.014 |
slide | -0.013 |
towels | -0.013 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
since | +0.017 |
unlike | +0.016 |
fulfilled | +0.016 |
stru | +0.015 |
cel | +0.015 |
Neg logit contributions | |
moms | -0.015 |
dads | -0.013 |
eps | -0.012 |
slide | -0.012 |
towels | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
moms | +0.053 |
dads | +0.045 |
eps | +0.043 |
slide | +0.043 |
truck | +0.041 |
Neg logit contributions | |
since | -0.044 |
unlike | -0.043 |
fulfilled | -0.042 |
stru | -0.041 |
cel | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
since | +0.002 |
unlike | +0.002 |
fulfilled | +0.002 |
stru | +0.002 |
cel | +0.002 |
Neg logit contributions | |
moms | -0.003 |
dads | -0.003 |
truck | -0.002 |
slide | -0.002 |
Tom | -0.002 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
moms | +0.024 |
dads | +0.020 |
eps | +0.019 |
towels | +0.019 |
slide | +0.018 |
Neg logit contributions | |
since | -0.023 |
fulfilled | -0.022 |
unlike | -0.022 |
stru | -0.021 |
cel | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
moms | +0.065 |
dads | +0.058 |
eps | +0.056 |
slide | +0.055 |
truck | +0.054 |
Neg logit contributions | |
since | -0.021 |
unlike | -0.020 |
fulfilled | -0.019 |
stru | -0.018 |
cel | -0.018 |
Token | join |
Token ID | 4654 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
since | +0.042 |
unlike | +0.040 |
fulfilled | +0.040 |
stru | +0.038 |
cel | +0.036 |
Neg logit contributions | |
moms | -0.045 |
eps | -0.039 |
dads | -0.038 |
microwave | -0.036 |
towels | -0.035 |
Token | them |
Token ID | 606 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
since | +0.024 |
unlike | +0.023 |
fulfilled | +0.022 |
stru | +0.022 |
cel | +0.021 |
Neg logit contributions | |
moms | -0.024 |
dads | -0.020 |
eps | -0.020 |
slide | -0.019 |
truck | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
moms | +0.023 |
dads | +0.020 |
slide | +0.019 |
eps | +0.019 |
sled | +0.018 |
Neg logit contributions | |
unlike | -0.017 |
since | -0.017 |
fulfilled | -0.017 |
cel | -0.016 |
stru | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
moms | +0.008 |
dads | +0.007 |
microwave | +0.007 |
snowball | +0.007 |
sled | +0.007 |
Neg logit contributions | |
since | -0.008 |
fulfilled | -0.008 |
cel | -0.007 |
unlike | -0.007 |
stru | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
moms | +0.069 |
eps | +0.063 |
dads | +0.062 |
slide | +0.060 |
sled | +0.059 |
Neg logit contributions | |
since | -0.022 |
unlike | -0.020 |
fulfilled | -0.020 |
knowing | -0.017 |
stru | -0.017 |
Token | see |
Token ID | 766 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
since | +0.042 |
fulfilled | +0.041 |
unlike | +0.039 |
Mill | +0.037 |
grant | +0.037 |
Neg logit contributions | |
moms | -0.049 |
eps | -0.046 |
dads | -0.044 |
microwave | -0.043 |
snowball | -0.041 |
Token | what |
Token ID | 644 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
since | +0.014 |
such | +0.013 |
knowing | +0.012 |
unlike | +0.012 |
fulfilled | +0.011 |
Neg logit contributions | |
moms | -0.019 |
oyd | -0.017 |
eps | -0.017 |
microwave | -0.016 |
dads | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
moms | +0.084 |
dads | +0.078 |
eps | +0.076 |
sled | +0.071 |
towels | +0.070 |
Neg logit contributions | |
unlike | -0.072 |
since | -0.072 |
fulfilled | -0.070 |
stru | -0.065 |
Nice | -0.064 |
Token | other |
Token ID | 584 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
moms | +0.014 |
dads | +0.012 |
eps | +0.012 |
sled | +0.011 |
towels | +0.011 |
Neg logit contributions | |
since | -0.012 |
unlike | -0.012 |
fulfilled | -0.011 |
cel | -0.011 |
solving | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
moms | +0.128 |
dads | +0.111 |
eps | +0.106 |
sled | +0.102 |
snowball | +0.100 |
Neg logit contributions | |
since | -0.142 |
unlike | -0.135 |
fulfilled | -0.131 |
cel | -0.125 |
stru | -0.124 |
Token | written |
Token ID | 3194 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
unlike | +0.023 |
since | +0.023 |
fulfilled | +0.022 |
cel | +0.022 |
stru | +0.022 |
Neg logit contributions | |
moms | -0.028 |
dads | -0.024 |
eps | -0.023 |
slide | -0.022 |
says | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
since | +0.019 |
unlike | +0.018 |
fulfilled | +0.018 |
stru | +0.016 |
cel | +0.016 |
Neg logit contributions | |
moms | -0.029 |
dads | -0.025 |
eps | -0.023 |
slide | -0.023 |
towels | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
since | +0.019 |
Nice | +0.018 |
unlike | +0.018 |
This | +0.018 |
fulfilled | +0.017 |
Neg logit contributions | |
moms | -0.029 |
eps | -0.028 |
dads | -0.027 |
cream | -0.026 |
slide | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
since | +0.010 |
fulfilled | +0.010 |
knowing | +0.009 |
unlike | +0.009 |
stru | +0.009 |
Neg logit contributions | |
moms | -0.017 |
dads | -0.016 |
sandbox | -0.015 |
microwave | -0.015 |
cream | -0.015 |
Token | Jen |
Token ID | 13364 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
moms | +0.022 |
eps | +0.021 |
dads | +0.019 |
says | +0.018 |
microwave | +0.018 |
Neg logit contributions | |
since | -0.031 |
fulfilled | -0.027 |
unlike | -0.027 |
solving | -0.026 |
exploring | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
since | +0.033 |
fulfilled | +0.030 |
unlike | +0.029 |
stru | +0.028 |
cel | +0.028 |
Neg logit contributions | |
moms | -0.052 |
dads | -0.046 |
eps | -0.043 |
towels | -0.042 |
microwave | -0.041 |
Token | He |
Token ID | 679 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.011 |
fulfilled | +0.011 |
Nice | +0.010 |
stru | +0.010 |
Neg logit contributions | |
moms | -0.020 |
eps | -0.018 |
dads | -0.018 |
towels | -0.016 |
slide | -0.016 |
Token | reaches |
Token ID | 12229 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
moms | +0.027 |
dads | +0.024 |
eps | +0.023 |
towels | +0.022 |
dad | +0.021 |
Neg logit contributions | |
since | -0.032 |
fulfilled | -0.031 |
unlike | -0.031 |
stru | -0.030 |
cel | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
since | +0.022 |
unlike | +0.021 |
fulfilled | +0.021 |
stru | +0.020 |
cel | +0.019 |
Neg logit contributions | |
moms | -0.029 |
dads | -0.025 |
eps | -0.024 |
slide | -0.022 |
towels | -0.022 |
Token | bottom |
Token ID | 4220 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
eps | +0.016 |
moms | +0.016 |
dads | +0.016 |
agree | +0.015 |
ep | +0.014 |
Neg logit contributions | |
since | -0.017 |
fulfilled | -0.016 |
unlike | -0.016 |
Nice | -0.016 |
among | -0.015 |
Token | first |
Token ID | 717 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
moms | +0.176 |
dads | +0.164 |
eps | +0.161 |
towels | +0.150 |
microwave | +0.146 |
Neg logit contributions | |
since | -0.077 |
unlike | -0.067 |
fulfilled | -0.058 |
Nice | -0.056 |
stru | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
moms | +0.073 |
eps | +0.064 |
dads | +0.064 |
towels | +0.058 |
truck | +0.057 |
Neg logit contributions | |
since | -0.048 |
unlike | -0.045 |
fulfilled | -0.043 |
stru | -0.040 |
Nice | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
since | +0.001 |
unlike | +0.001 |
fulfilled | +0.001 |
Nice | +0.001 |
This | +0.001 |
Neg logit contributions | |
moms | -0.003 |
eps | -0.003 |
dads | -0.003 |
towels | -0.003 |
slide | -0.003 |
Token | jumps |
Token ID | 18045 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
moms | +0.036 |
dads | +0.032 |
eps | +0.031 |
towels | +0.029 |
Dad | +0.027 |
Neg logit contributions | |
since | -0.042 |
unlike | -0.040 |
fulfilled | -0.040 |
stru | -0.039 |
cel | -0.038 |
Token | up |
Token ID | 510 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
since | +0.012 |
unlike | +0.012 |
fulfilled | +0.012 |
cel | +0.012 |
stru | +0.012 |
Neg logit contributions | |
moms | -0.014 |
slide | -0.012 |
dads | -0.012 |
eps | -0.011 |
truck | -0.011 |
Token | surprise |
Token ID | 5975 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
moms | +0.012 |
eps | +0.011 |
dads | +0.010 |
microwave | +0.010 |
towels | +0.010 |
Neg logit contributions | |
since | -0.014 |
fulfilled | -0.013 |
unlike | -0.013 |
stru | -0.013 |
knowing | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
moms | +0.014 |
dads | +0.012 |
eps | +0.012 |
slide | +0.012 |
truck | +0.011 |
Neg logit contributions | |
since | -0.010 |
unlike | -0.010 |
fulfilled | -0.010 |
stru | -0.009 |
cel | -0.009 |
Token | one |
Token ID | 530 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
moms | +0.011 |
dad | +0.009 |
dads | +0.009 |
Tom | +0.009 |
slide | +0.008 |
Neg logit contributions | |
stru | -0.013 |
unlike | -0.013 |
cel | -0.013 |
ulent | -0.012 |
since | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
moms | +0.090 |
dads | +0.080 |
eps | +0.078 |
slide | +0.075 |
towels | +0.074 |
Neg logit contributions | |
since | -0.046 |
unlike | -0.044 |
fulfilled | -0.043 |
stru | -0.041 |
cel | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
moms | +0.030 |
dads | +0.026 |
eps | +0.026 |
slide | +0.025 |
sled | +0.024 |
Neg logit contributions | |
since | -0.022 |
unlike | -0.020 |
fulfilled | -0.020 |
stru | -0.019 |
cel | -0.019 |
Token | pengu |
Token ID | 38373 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
moms | +0.001 |
dads | +0.001 |
eps | +0.001 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.002 |
fulfilled | -0.002 |
unlike | -0.002 |
stru | -0.002 |
cel | -0.002 |
Token | ins |
Token ID | 1040 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
moms | +0.123 |
dads | +0.102 |
towels | +0.099 |
sled | +0.098 |
slide | +0.097 |
Neg logit contributions | |
stru | -0.128 |
fulfilled | -0.125 |
since | -0.123 |
unlike | -0.121 |
among | -0.115 |
Token | came |
Token ID | 1625 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
moms | +0.055 |
dads | +0.045 |
eps | +0.043 |
snowball | +0.043 |
microwave | +0.042 |
Neg logit contributions | |
since | -0.045 |
fulfilled | -0.043 |
unlike | -0.042 |
stru | -0.039 |
knowing | -0.038 |
Token | over |
Token ID | 625 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
since | +0.058 |
unlike | +0.057 |
cel | +0.056 |
fulfilled | +0.056 |
stru | +0.054 |
Neg logit contributions | |
moms | -0.070 |
dads | -0.060 |
eps | -0.059 |
slide | -0.057 |
truck | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.033 |
dad | +0.032 |
slide | +0.032 |
towels | +0.031 |
Neg logit contributions | |
unlike | -0.040 |
cel | -0.039 |
fulfilled | -0.039 |
stru | -0.039 |
since | -0.039 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
moms | +0.029 |
dads | +0.024 |
eps | +0.024 |
sled | +0.023 |
towels | +0.022 |
Neg logit contributions | |
since | -0.028 |
fulfilled | -0.026 |
unlike | -0.026 |
stru | -0.025 |
cel | -0.024 |
Token | kept |
Token ID | 4030 |
Feature activation | -7.35e-04 |
Pos logit contributions | |
moms | +0.019 |
dads | +0.016 |
towels | +0.015 |
eps | +0.015 |
sled | +0.014 |
Neg logit contributions | |
since | -0.020 |
unlike | -0.019 |
fulfilled | -0.018 |
stru | -0.018 |
zing | -0.017 |
Token | z |
Token ID | 1976 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
moms | +0.001 |
dads | +0.001 |
eps | +0.001 |
slide | +0.001 |
towels | +0.001 |
Neg logit contributions | |
since | -0.001 |
unlike | -0.001 |
fulfilled | -0.001 |
stru | -0.001 |
cel | -0.001 |
Token | ooming |
Token ID | 30602 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
moms | +0.040 |
dads | +0.034 |
eps | +0.033 |
slide | +0.032 |
truck | +0.031 |
Neg logit contributions | |
since | -0.032 |
unlike | -0.031 |
fulfilled | -0.030 |
stru | -0.029 |
cel | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
since | +0.011 |
unlike | +0.011 |
fulfilled | +0.011 |
stru | +0.010 |
cel | +0.010 |
Neg logit contributions | |
moms | -0.015 |
dads | -0.013 |
eps | -0.013 |
slide | -0.012 |
truck | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
moms | +0.004 |
dads | +0.003 |
eps | +0.003 |
slide | +0.003 |
truck | +0.003 |
Neg logit contributions | |
since | -0.003 |
unlike | -0.003 |
fulfilled | -0.003 |
stru | -0.003 |
cel | -0.003 |
Token | bar |
Token ID | 2318 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
moms | +0.010 |
dads | +0.008 |
eps | +0.008 |
towels | +0.008 |
slide | +0.007 |
Neg logit contributions | |
since | -0.018 |
fulfilled | -0.017 |
unlike | -0.017 |
stru | -0.017 |
cel | -0.016 |
Token | ber |
Token ID | 527 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
moms | +0.145 |
towels | +0.145 |
dads | +0.130 |
eps | +0.128 |
sunscreen | +0.127 |
Neg logit contributions | |
stru | -0.200 |
unlike | -0.196 |
since | -0.195 |
knowing | -0.181 |
fulfilled | -0.180 |
Token | said |
Token ID | 531 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
moms | +0.084 |
dads | +0.074 |
towels | +0.071 |
eps | +0.066 |
microwave | +0.066 |
Neg logit contributions | |
since | -0.082 |
fulfilled | -0.076 |
unlike | -0.076 |
stru | -0.076 |
cel | -0.071 |
Token | again |
Token ID | 757 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
moms | +0.016 |
dads | +0.014 |
slide | +0.013 |
truck | +0.013 |
eps | +0.013 |
Neg logit contributions | |
since | -0.013 |
fulfilled | -0.012 |
unlike | -0.012 |
stru | -0.012 |
cel | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
moms | +0.037 |
dads | +0.032 |
eps | +0.032 |
slide | +0.030 |
towels | +0.029 |
Neg logit contributions | |
since | -0.023 |
unlike | -0.021 |
fulfilled | -0.020 |
stru | -0.019 |
knowing | -0.018 |
Token | but |
Token ID | 475 |
Feature activation | +8.33e-03 |
Pos logit contributions | |
since | +0.008 |
unlike | +0.007 |
fulfilled | +0.007 |
stru | +0.007 |
cel | +0.007 |
Neg logit contributions | |
moms | -0.013 |
dads | -0.011 |
eps | -0.010 |
slide | -0.010 |
truck | -0.010 |
Token | crane |
Token ID | 41175 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
moms | +0.011 |
eps | +0.010 |
dads | +0.009 |
towels | +0.009 |
says | +0.009 |
Neg logit contributions | |
unlike | -0.014 |
fulfilled | -0.014 |
since | -0.014 |
stru | -0.014 |
exploring | -0.014 |
Token | got |
Token ID | 1392 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
moms | +0.045 |
dads | +0.039 |
eps | +0.037 |
towels | +0.036 |
snowball | +0.034 |
Neg logit contributions | |
since | -0.038 |
fulfilled | -0.035 |
stru | -0.034 |
unlike | -0.033 |
cel | -0.031 |
Token | back |
Token ID | 736 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
since | +0.014 |
unlike | +0.014 |
fulfilled | +0.013 |
cel | +0.013 |
stru | +0.013 |
Neg logit contributions | |
moms | -0.021 |
dads | -0.018 |
eps | -0.017 |
slide | -0.017 |
truck | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
moms | +0.022 |
dads | +0.019 |
slide | +0.018 |
eps | +0.018 |
truck | +0.018 |
Neg logit contributions | |
unlike | -0.015 |
since | -0.015 |
cel | -0.014 |
fulfilled | -0.014 |
stru | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
since | +0.015 |
unlike | +0.015 |
fulfilled | +0.015 |
stru | +0.014 |
cel | +0.014 |
Neg logit contributions | |
moms | -0.016 |
dads | -0.014 |
eps | -0.013 |
slide | -0.013 |
truck | -0.012 |
Token | other |
Token ID | 584 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
since | +0.004 |
fulfilled | +0.004 |
exploring | +0.004 |
unlike | +0.004 |
stru | +0.004 |
Neg logit contributions | |
moms | -0.004 |
eps | -0.003 |
dads | -0.003 |
says | -0.003 |
towels | -0.003 |
Token | side |
Token ID | 1735 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
moms | +0.104 |
dads | +0.084 |
eps | +0.080 |
slide | +0.078 |
truck | +0.074 |
Neg logit contributions | |
since | -0.134 |
unlike | -0.132 |
fulfilled | -0.130 |
stru | -0.126 |
cel | -0.124 |
Token | of |
Token ID | 286 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
moms | +0.098 |
dads | +0.085 |
slide | +0.081 |
eps | +0.081 |
truck | +0.079 |
Neg logit contributions | |
since | -0.061 |
unlike | -0.060 |
fulfilled | -0.058 |
cel | -0.056 |
stru | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
moms | +0.022 |
eps | +0.020 |
dads | +0.019 |
says | +0.018 |
microwave | +0.017 |
Neg logit contributions | |
since | -0.011 |
unlike | -0.010 |
fulfilled | -0.010 |
exploring | -0.010 |
solving | -0.010 |
Token | road |
Token ID | 2975 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
moms | +0.005 |
dads | +0.004 |
eps | +0.004 |
towels | +0.003 |
says | +0.003 |
Neg logit contributions | |
since | -0.007 |
fulfilled | -0.006 |
unlike | -0.006 |
stru | -0.006 |
exploring | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
moms | +0.144 |
dads | +0.123 |
slide | +0.118 |
eps | +0.118 |
truck | +0.116 |
Neg logit contributions | |
since | -0.098 |
unlike | -0.097 |
fulfilled | -0.094 |
stru | -0.091 |
cel | -0.091 |