Token | ! |
Token ID | 0 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
bike | +0.011 |
disl | +0.010 |
spe | +0.010 |
gol | +0.010 |
Mechan | +0.009 |
Neg logit contributions | |
eh | -0.006 |
una | -0.006 |
Mia | -0.006 |
sheet | -0.006 |
ches | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
una | +0.003 |
Mia | +0.003 |
eh | +0.003 |
Molly | +0.003 |
sheet | +0.003 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.004 |
spe | -0.004 |
Mechan | -0.003 |
gol | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
una | +0.010 |
eh | +0.010 |
sheet | +0.010 |
Mia | +0.009 |
inda | +0.009 |
Neg logit contributions | |
bike | -0.009 |
spe | -0.008 |
disl | -0.008 |
gol | -0.007 |
Mechan | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.002 |
inda | +0.002 |
sheet | +0.002 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
Mechan | -0.002 |
gol | -0.002 |
Token | town |
Token ID | 3240 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
disl | +0.058 |
bike | +0.054 |
spe | +0.051 |
Acc | +0.049 |
ishly | +0.046 |
Neg logit contributions | |
una | -0.042 |
eh | -0.039 |
page | -0.038 |
sheet | -0.037 |
Mia | -0.034 |
Token | spe |
Token ID | 4125 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
disl | +0.089 |
bike | +0.072 |
Acc | +0.070 |
Sorry | +0.063 |
lder | +0.061 |
Neg logit contributions | |
Mia | -0.076 |
eh | -0.072 |
una | -0.070 |
inda | -0.069 |
sheet | -0.068 |
Token | ople |
Token ID | 643 |
Feature activation | +4.77e-03 |
Pos logit contributions | |
disl | +0.157 |
bike | +0.133 |
Acc | +0.126 |
wishing | +0.119 |
miss | +0.118 |
Neg logit contributions | |
eh | -0.120 |
una | -0.109 |
Mia | -0.107 |
inda | -0.105 |
ily | -0.104 |
Token | thanked |
Token ID | 26280 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
disl | +0.010 |
bike | +0.010 |
Sorry | +0.008 |
gol | +0.008 |
Mechan | +0.008 |
Neg logit contributions | |
Mia | -0.007 |
una | -0.007 |
eh | -0.007 |
inda | -0.007 |
sheet | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
bike | +0.020 |
disl | +0.019 |
spe | +0.018 |
Mechan | +0.017 |
gol | +0.016 |
Neg logit contributions | |
Mia | -0.007 |
una | -0.006 |
Rachel | -0.006 |
Molly | -0.005 |
Lisa | -0.005 |
Token | hero |
Token ID | 4293 |
Feature activation | -1.44e-04 |
Pos logit contributions | |
disl | +0.046 |
bike | +0.041 |
spe | +0.041 |
Acc | +0.041 |
ishly | +0.038 |
Neg logit contributions | |
una | -0.029 |
page | -0.027 |
eh | -0.026 |
sheet | -0.025 |
corner | -0.024 |
Token | for |
Token ID | 329 |
Feature activation | +9.38e-03 |
Pos logit contributions | |
una | +0.000 |
Mia | +0.000 |
eh | +0.000 |
sheet | +0.000 |
inda | +0.000 |
Neg logit contributions | |
bike | -0.000 |
disl | -0.000 |
spe | -0.000 |
Mechan | -0.000 |
Sorry | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
bike | +0.063 |
disl | +0.057 |
spe | +0.053 |
Mechan | +0.051 |
gol | +0.049 |
Neg logit contributions | |
una | -0.038 |
Mia | -0.038 |
eh | -0.037 |
sheet | -0.033 |
inda | -0.032 |
Token | That |
Token ID | 1320 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
bike | +0.010 |
disl | +0.009 |
spe | +0.009 |
gol | +0.008 |
Mechan | +0.008 |
Neg logit contributions | |
una | -0.009 |
Mia | -0.009 |
eh | -0.008 |
Molly | -0.008 |
sheet | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
bike | +0.029 |
disl | +0.028 |
spe | +0.025 |
Acc | +0.024 |
gol | +0.024 |
Neg logit contributions | |
una | -0.017 |
sheet | -0.016 |
Mia | -0.016 |
eh | -0.016 |
Rachel | -0.015 |
Token | why |
Token ID | 1521 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
bike | +0.032 |
disl | +0.028 |
spe | +0.027 |
Mechan | +0.025 |
gol | +0.024 |
Neg logit contributions | |
una | -0.020 |
Mia | -0.020 |
eh | -0.019 |
inda | -0.017 |
sheet | -0.017 |
Token | our |
Token ID | 674 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
bike | +0.032 |
disl | +0.028 |
spe | +0.027 |
Mechan | +0.025 |
gol | +0.025 |
Neg logit contributions | |
Mia | -0.022 |
una | -0.022 |
sheet | -0.019 |
Molly | -0.019 |
eh | -0.019 |
Token | nation |
Token ID | 3277 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
bike | +0.094 |
Mechan | +0.077 |
qu | +0.070 |
disl | +0.068 |
spe | +0.067 |
Neg logit contributions | |
Mia | -0.066 |
eh | -0.058 |
una | -0.058 |
sheet | -0.058 |
ia | -0.057 |
Token | is |
Token ID | 318 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
bike | +0.192 |
disl | +0.172 |
gol | +0.161 |
spe | +0.158 |
Mechan | +0.158 |
Neg logit contributions | |
Mia | -0.087 |
eh | -0.087 |
una | -0.087 |
sheet | -0.082 |
spot | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
bike | +0.057 |
disl | +0.048 |
spe | +0.045 |
Mechan | +0.043 |
gol | +0.042 |
Neg logit contributions | |
eh | -0.038 |
una | -0.036 |
Mia | -0.036 |
sheet | -0.033 |
inda | -0.032 |
Token | greatest |
Token ID | 6000 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
bike | +0.030 |
disl | +0.026 |
Mechan | +0.023 |
spe | +0.023 |
Acc | +0.022 |
Neg logit contributions | |
eh | -0.022 |
una | -0.021 |
Mia | -0.020 |
sheet | -0.020 |
page | -0.019 |
Token | ." |
Token ID | 526 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
bike | +0.083 |
disl | +0.069 |
Mechan | +0.066 |
spe | +0.065 |
ishly | +0.060 |
Neg logit contributions | |
eh | -0.059 |
una | -0.059 |
Mia | -0.058 |
sheet | -0.055 |
Rachel | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +2.59e-03 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.005 |
disl | -0.004 |
spe | -0.004 |
Mechan | -0.003 |
gol | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.003 |
spe | +0.003 |
Mechan | +0.003 |
gol | +0.003 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
Molly | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
una | +0.012 |
eh | +0.011 |
sheet | +0.010 |
Mia | +0.010 |
inda | +0.010 |
Neg logit contributions | |
bike | -0.012 |
disl | -0.011 |
spe | -0.010 |
gol | -0.009 |
Mechan | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
una | +0.012 |
eh | +0.012 |
sheet | +0.012 |
inda | +0.011 |
Mia | +0.011 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.008 |
qu | -0.007 |
self | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
una | +0.006 |
eh | +0.006 |
Mia | +0.006 |
sheet | +0.006 |
inda | +0.005 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.006 |
spe | -0.006 |
gol | -0.005 |
self | -0.005 |
Token | town |
Token ID | 3240 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
bike | +0.035 |
disl | +0.031 |
spe | +0.030 |
Mechan | +0.026 |
self | +0.025 |
Neg logit contributions | |
una | -0.028 |
eh | -0.027 |
Mia | -0.025 |
sheet | -0.025 |
inda | -0.023 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
bike | +0.096 |
disl | +0.092 |
Mechan | +0.075 |
spe | +0.074 |
Acc | +0.073 |
Neg logit contributions | |
eh | -0.075 |
una | -0.074 |
Mia | -0.074 |
sheet | -0.068 |
inda | -0.066 |
Token | ople |
Token ID | 643 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
disl | +0.138 |
bike | +0.127 |
Acc | +0.107 |
wishing | +0.104 |
miss | +0.102 |
Neg logit contributions | |
eh | -0.137 |
una | -0.126 |
Mia | -0.122 |
inda | -0.120 |
enzie | -0.119 |
Token | were |
Token ID | 547 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
disl | +0.024 |
bike | +0.024 |
spe | +0.020 |
Mechan | +0.020 |
Sorry | +0.019 |
Neg logit contributions | |
Mia | -0.018 |
eh | -0.018 |
una | -0.017 |
inda | -0.017 |
sheet | -0.017 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
bike | +0.027 |
disl | +0.025 |
spe | +0.022 |
Mechan | +0.021 |
gol | +0.020 |
Neg logit contributions | |
eh | -0.023 |
Mia | -0.022 |
una | -0.022 |
Molly | -0.020 |
sheet | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
bike | +0.061 |
disl | +0.056 |
spe | +0.054 |
Mechan | +0.052 |
lder | +0.051 |
Neg logit contributions | |
Mia | -0.031 |
una | -0.028 |
Molly | -0.027 |
sheet | -0.025 |
Milo | -0.023 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
Mia | -0.002 |
eh | -0.002 |
una | -0.002 |
Molly | -0.002 |
sheet | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +6.99e-03 |
Pos logit contributions | |
bike | +0.035 |
disl | +0.033 |
Mechan | +0.029 |
spe | +0.028 |
affect | +0.027 |
Neg logit contributions | |
Mia | -0.025 |
una | -0.024 |
eh | -0.023 |
inda | -0.022 |
Molly | -0.022 |
Token | proud |
Token ID | 6613 |
Feature activation | -7.78e-04 |
Pos logit contributions | |
bike | +0.015 |
disl | +0.013 |
spe | +0.012 |
Mechan | +0.012 |
Sorry | +0.011 |
Neg logit contributions | |
Mia | -0.012 |
eh | -0.011 |
una | -0.011 |
Molly | -0.010 |
ily | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
una | +0.001 |
Mia | +0.001 |
eh | +0.000 |
sheet | +0.000 |
inda | +0.000 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
Mechan | -0.002 |
lder | -0.002 |
Token | John |
Token ID | 1757 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
bike | +0.028 |
disl | +0.025 |
spe | +0.024 |
gol | +0.024 |
Mechan | +0.024 |
Neg logit contributions | |
Mia | -0.018 |
una | -0.016 |
Amy | -0.015 |
Rachel | -0.015 |
Lisa | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
una | +0.013 |
Mia | +0.012 |
eh | +0.012 |
inda | +0.011 |
Molly | +0.011 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.020 |
spe | -0.019 |
Mechan | -0.018 |
Sorry | -0.018 |
Token | Kinder |
Token ID | 46832 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
bike | +0.015 |
disl | +0.013 |
Mechan | +0.013 |
qu | +0.013 |
spe | +0.012 |
Neg logit contributions | |
Mia | -0.010 |
Rachel | -0.008 |
Molly | -0.008 |
una | -0.008 |
Amy | -0.008 |
Token | g |
Token ID | 70 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
bike | +0.158 |
spe | +0.149 |
disl | +0.139 |
Mechan | +0.131 |
je | +0.129 |
Neg logit contributions | |
eh | -0.115 |
una | -0.112 |
ily | -0.103 |
ori | -0.099 |
book | -0.097 |
Token | arten |
Token ID | 23996 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
bike | +0.063 |
disl | +0.057 |
spe | +0.055 |
Mechan | +0.052 |
Sorry | +0.048 |
Neg logit contributions | |
una | -0.047 |
eh | -0.043 |
inda | -0.040 |
Mia | -0.038 |
enzie | -0.038 |
Token | ers |
Token ID | 364 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
bike | +0.084 |
disl | +0.082 |
Mechan | +0.072 |
spe | +0.069 |
gol | +0.068 |
Neg logit contributions | |
Mia | -0.044 |
una | -0.043 |
Molly | -0.039 |
Rachel | -0.038 |
eh | -0.037 |
Token | learned |
Token ID | 4499 |
Feature activation | -9.57e-04 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.008 |
Mechan | +0.007 |
spe | +0.007 |
Sorry | +0.007 |
Neg logit contributions | |
Mia | -0.004 |
una | -0.004 |
eh | -0.004 |
Molly | -0.004 |
inda | -0.004 |
Token | an |
Token ID | 281 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
una | +0.001 |
Mia | +0.001 |
eh | +0.001 |
sheet | +0.001 |
Molly | +0.001 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
Mechan | -0.002 |
lder | -0.002 |
Token | days |
Token ID | 1528 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
una | +0.015 |
eh | +0.014 |
Mia | +0.014 |
sheet | +0.012 |
inda | +0.011 |
Neg logit contributions | |
bike | -0.038 |
disl | -0.034 |
spe | -0.034 |
Sorry | -0.031 |
gol | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
eh | +0.007 |
Mia | +0.007 |
una | +0.007 |
sheet | +0.006 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.013 |
disl | -0.013 |
Sorry | -0.012 |
spe | -0.011 |
Acc | -0.011 |
Token | days |
Token ID | 1528 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
Sorry | +0.003 |
lder | +0.003 |
Neg logit contributions | |
Mia | -0.002 |
eh | -0.002 |
una | -0.002 |
inda | -0.002 |
sheet | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
disl | +0.034 |
bike | +0.034 |
Sorry | +0.030 |
spe | +0.029 |
Acc | +0.029 |
Neg logit contributions | |
Mia | -0.020 |
eh | -0.019 |
una | -0.017 |
Molly | -0.016 |
sheet | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.016 |
lder | +0.014 |
spe | +0.014 |
Sorry | +0.013 |
Neg logit contributions | |
Mia | -0.009 |
eh | -0.009 |
una | -0.009 |
inda | -0.008 |
sheet | -0.008 |
Token | towns |
Token ID | 11684 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
bike | +0.067 |
disl | +0.059 |
ishly | +0.055 |
qu | +0.055 |
spe | +0.054 |
Neg logit contributions | |
eh | -0.038 |
Mia | -0.037 |
page | -0.037 |
sheet | -0.036 |
corner | -0.034 |
Token | folk |
Token ID | 19956 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
disl | +0.152 |
Acc | +0.130 |
bike | +0.126 |
Mechan | +0.112 |
Sorry | +0.112 |
Neg logit contributions | |
Mia | -0.117 |
eh | -0.111 |
of | -0.111 |
corner | -0.108 |
Lisa | -0.105 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
disl | +0.103 |
bike | +0.097 |
Acc | +0.085 |
Sorry | +0.084 |
Mechan | +0.082 |
Neg logit contributions | |
eh | -0.060 |
Mia | -0.059 |
inda | -0.054 |
sheet | -0.053 |
una | -0.050 |
Token | on |
Token ID | 319 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
bike | +0.013 |
disl | +0.012 |
spe | +0.011 |
Mechan | +0.010 |
lder | +0.010 |
Neg logit contributions | |
eh | -0.006 |
Mia | -0.006 |
una | -0.006 |
sheet | -0.005 |
inda | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
Mia | +0.003 |
sheet | +0.002 |
spaghetti | +0.002 |
Molly | +0.002 |
una | +0.002 |
Neg logit contributions | |
bike | -0.006 |
disl | -0.006 |
Mechan | -0.005 |
Sorry | -0.005 |
spe | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
bike | +0.009 |
disl | +0.008 |
spe | +0.008 |
lder | +0.007 |
Mechan | +0.007 |
Neg logit contributions | |
Mia | -0.006 |
una | -0.006 |
eh | -0.006 |
Molly | -0.005 |
Rachel | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
Mia | -0.001 |
una | -0.001 |
Molly | -0.001 |
sheet | -0.001 |
Luna | -0.001 |
Token | why |
Token ID | 1521 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
una | +0.029 |
eh | +0.028 |
Mia | +0.027 |
sheet | +0.026 |
inda | +0.025 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.028 |
spe | -0.028 |
gol | -0.023 |
Mechan | -0.023 |
Token | don |
Token ID | 836 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
bike | +0.016 |
spe | +0.014 |
disl | +0.014 |
gol | +0.011 |
Mechan | +0.011 |
Neg logit contributions | |
una | -0.020 |
Mia | -0.019 |
eh | -0.018 |
sheet | -0.017 |
Molly | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
una | +0.025 |
eh | +0.024 |
Mia | +0.023 |
sheet | +0.022 |
inda | +0.022 |
Neg logit contributions | |
bike | -0.019 |
disl | -0.017 |
spe | -0.016 |
gol | -0.013 |
Mechan | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
Mia | +0.026 |
una | +0.026 |
sheet | +0.023 |
Molly | +0.023 |
eh | +0.022 |
Neg logit contributions | |
bike | -0.031 |
disl | -0.028 |
spe | -0.028 |
Mechan | -0.024 |
gol | -0.024 |
Token | un |
Token ID | 555 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
bike | +0.014 |
disl | +0.013 |
spe | +0.013 |
Mechan | +0.011 |
gol | +0.011 |
Neg logit contributions | |
una | -0.010 |
Mia | -0.009 |
eh | -0.009 |
sheet | -0.009 |
inda | -0.008 |
Token | pack |
Token ID | 8002 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
bike | +0.156 |
disl | +0.146 |
spe | +0.136 |
gol | +0.120 |
Mechan | +0.116 |
Neg logit contributions | |
una | -0.120 |
eh | -0.115 |
Mia | -0.111 |
sheet | -0.104 |
ori | -0.101 |
Token | your |
Token ID | 534 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
una | +0.014 |
eh | +0.014 |
Mia | +0.012 |
sheet | +0.012 |
inda | +0.011 |
Neg logit contributions | |
bike | -0.019 |
disl | -0.017 |
spe | -0.016 |
gol | -0.014 |
Mechan | -0.014 |
Token | things |
Token ID | 1243 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
Mechan | +0.005 |
gol | +0.005 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
Mia | -0.004 |
inda | -0.004 |
enzie | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
bike | +0.073 |
disl | +0.070 |
spe | +0.069 |
gol | +0.060 |
Mechan | +0.059 |
Neg logit contributions | |
una | -0.033 |
Mia | -0.031 |
sheet | -0.031 |
eh | -0.030 |
spaghetti | -0.027 |
Token | make |
Token ID | 787 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
bike | +0.011 |
spe | +0.010 |
disl | +0.009 |
gol | +0.009 |
Mechan | +0.009 |
Neg logit contributions | |
Mia | -0.008 |
una | -0.008 |
sheet | -0.008 |
eh | -0.008 |
spaghetti | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -6.30e-04 |
Pos logit contributions | |
una | +0.020 |
eh | +0.020 |
Mia | +0.019 |
sheet | +0.018 |
Molly | +0.016 |
Neg logit contributions | |
bike | -0.036 |
disl | -0.032 |
spe | -0.031 |
Mechan | -0.028 |
gol | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
una | +0.001 |
Mia | +0.001 |
eh | +0.001 |
Molly | +0.001 |
Luna | +0.001 |
Neg logit contributions | |
bike | -0.001 |
spe | -0.001 |
disl | -0.001 |
Mechan | -0.001 |
self | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
gol | +0.005 |
Mechan | +0.005 |
Neg logit contributions | |
una | -0.006 |
eh | -0.006 |
Mia | -0.006 |
sheet | -0.005 |
inda | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
bike | +0.013 |
disl | +0.012 |
spe | +0.012 |
Mechan | +0.010 |
Acc | +0.010 |
Neg logit contributions | |
una | -0.011 |
eh | -0.010 |
Mia | -0.009 |
ori | -0.009 |
inda | -0.008 |
Token | town |
Token ID | 3240 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
bike | +0.064 |
spe | +0.055 |
disl | +0.055 |
Mechan | +0.051 |
ishly | +0.050 |
Neg logit contributions | |
una | -0.036 |
eh | -0.035 |
Mia | -0.035 |
ily | -0.035 |
sheet | -0.032 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
disl | +0.078 |
bike | +0.074 |
Acc | +0.057 |
affect | +0.057 |
Mechan | +0.057 |
Neg logit contributions | |
Mia | -0.084 |
una | -0.079 |
eh | -0.079 |
inda | -0.077 |
ia | -0.076 |
Token | ople |
Token ID | 643 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
disl | +0.136 |
bike | +0.129 |
Acc | +0.106 |
spe | +0.105 |
wishing | +0.103 |
Neg logit contributions | |
eh | -0.127 |
una | -0.118 |
ily | -0.116 |
Mia | -0.115 |
inda | -0.113 |
Token | were |
Token ID | 547 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
disl | +0.024 |
bike | +0.023 |
gol | +0.019 |
spe | +0.019 |
Mechan | +0.019 |
Neg logit contributions | |
Mia | -0.017 |
una | -0.016 |
inda | -0.016 |
Molly | -0.016 |
eh | -0.015 |
Token | amazed |
Token ID | 24562 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
bike | +0.020 |
disl | +0.018 |
spe | +0.016 |
Mechan | +0.015 |
gol | +0.015 |
Neg logit contributions | |
eh | -0.014 |
Mia | -0.014 |
una | -0.014 |
Molly | -0.012 |
sheet | -0.012 |
Token | by |
Token ID | 416 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
bike | +0.070 |
disl | +0.065 |
Mechan | +0.065 |
spe | +0.061 |
Sorry | +0.058 |
Neg logit contributions | |
Mia | -0.029 |
una | -0.029 |
Molly | -0.026 |
Rachel | -0.025 |
inda | -0.023 |
Token | this |
Token ID | 428 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
bike | +0.021 |
disl | +0.020 |
spe | +0.020 |
lder | +0.018 |
qu | +0.018 |
Neg logit contributions | |
Mia | -0.010 |
una | -0.009 |
sheet | -0.008 |
Molly | -0.008 |
Luna | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
bike | +0.044 |
disl | +0.040 |
spe | +0.040 |
Mechan | +0.035 |
gol | +0.035 |
Neg logit contributions | |
Mia | -0.028 |
una | -0.028 |
eh | -0.026 |
sheet | -0.024 |
Molly | -0.024 |
Token | bowed |
Token ID | 35737 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
bike | +0.028 |
disl | +0.027 |
spe | +0.027 |
Mechan | +0.023 |
Sorry | +0.023 |
Neg logit contributions | |
una | -0.018 |
eh | -0.018 |
Mia | -0.017 |
ches | -0.017 |
sheet | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
bike | +0.080 |
disl | +0.075 |
spe | +0.073 |
gol | +0.066 |
Mechan | +0.065 |
Neg logit contributions | |
una | -0.051 |
Mia | -0.050 |
eh | -0.048 |
sheet | -0.045 |
Luna | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
bike | +0.026 |
disl | +0.024 |
spe | +0.023 |
Mechan | +0.021 |
gol | +0.021 |
Neg logit contributions | |
una | -0.014 |
eh | -0.014 |
Mia | -0.014 |
sheet | -0.012 |
inda | -0.012 |
Token | town |
Token ID | 3240 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
bike | +0.030 |
disl | +0.029 |
spe | +0.028 |
qu | +0.025 |
Mechan | +0.024 |
Neg logit contributions | |
una | -0.024 |
sheet | -0.024 |
eh | -0.022 |
page | -0.021 |
Mia | -0.021 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
disl | +0.112 |
bike | +0.105 |
Mechan | +0.094 |
gol | +0.091 |
Acc | +0.090 |
Neg logit contributions | |
Mia | -0.063 |
sheet | -0.058 |
una | -0.057 |
inda | -0.055 |
page | -0.055 |
Token | ople |
Token ID | 643 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
disl | +0.147 |
bike | +0.121 |
Acc | +0.114 |
wishing | +0.110 |
miss | +0.106 |
Neg logit contributions | |
eh | -0.111 |
inda | -0.098 |
oline | -0.095 |
adies | -0.094 |
ily | -0.094 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
bike | +0.049 |
disl | +0.049 |
Mechan | +0.043 |
spe | +0.041 |
gol | +0.041 |
Neg logit contributions | |
inda | -0.027 |
eh | -0.027 |
Mia | -0.027 |
ches | -0.026 |
una | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
bike | +0.072 |
disl | +0.069 |
spe | +0.066 |
lder | +0.065 |
Mechan | +0.062 |
Neg logit contributions | |
Mia | -0.030 |
upon | -0.027 |
eh | -0.025 |
Rachel | -0.025 |
una | -0.024 |
Token | admire |
Token ID | 21099 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
bike | +0.051 |
spe | +0.049 |
disl | +0.044 |
Mechan | +0.043 |
lder | +0.041 |
Neg logit contributions | |
Mia | -0.034 |
sheet | -0.031 |
una | -0.031 |
Rachel | -0.029 |
spot | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
bike | +0.063 |
disl | +0.056 |
spe | +0.055 |
Mechan | +0.054 |
gol | +0.051 |
Neg logit contributions | |
Mia | -0.021 |
una | -0.020 |
Molly | -0.018 |
sheet | -0.017 |
Rachel | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.004 |
Mechan | +0.004 |
Sorry | +0.004 |
gol | +0.004 |
Neg logit contributions | |
Mia | -0.002 |
eh | -0.002 |
una | -0.002 |
sheet | -0.002 |
Molly | -0.002 |
Token | leaving |
Token ID | 4305 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
Mia | +0.002 |
eh | +0.002 |
una | +0.002 |
sheet | +0.002 |
Molly | +0.002 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
lder | -0.003 |
Mechan | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
bike | +0.020 |
disl | +0.018 |
spe | +0.018 |
Mechan | +0.016 |
gol | +0.016 |
Neg logit contributions | |
una | -0.011 |
eh | -0.011 |
Mia | -0.010 |
sheet | -0.009 |
inda | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +7.33e-03 |
Pos logit contributions | |
bike | +0.023 |
disl | +0.021 |
spe | +0.020 |
gol | +0.019 |
Mechan | +0.019 |
Neg logit contributions | |
eh | -0.013 |
Mia | -0.012 |
una | -0.012 |
sheet | -0.011 |
inda | -0.010 |
Token | its |
Token ID | 663 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
bike | +0.017 |
spe | +0.015 |
disl | +0.014 |
Mechan | +0.013 |
gol | +0.012 |
Neg logit contributions | |
una | -0.011 |
eh | -0.011 |
Mia | -0.011 |
sheet | -0.010 |
inda | -0.009 |
Token | former |
Token ID | 1966 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
bike | +0.026 |
disl | +0.023 |
spe | +0.022 |
Mechan | +0.021 |
qu | +0.020 |
Neg logit contributions | |
una | -0.019 |
eh | -0.018 |
Mia | -0.017 |
sheet | -0.017 |
Molly | -0.015 |
Token | state |
Token ID | 1181 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
bike | +0.154 |
spe | +0.125 |
disl | +0.125 |
Mechan | +0.113 |
gol | +0.112 |
Neg logit contributions | |
una | -0.130 |
eh | -0.130 |
Mia | -0.119 |
sheet | -0.115 |
inda | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
bike | +0.067 |
disl | +0.061 |
spe | +0.057 |
Mechan | +0.053 |
Sorry | +0.053 |
Neg logit contributions | |
una | -0.042 |
eh | -0.041 |
Mia | -0.039 |
sheet | -0.037 |
inda | -0.035 |
Token | |
Token ID | 220 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.003 |
spe | -0.003 |
Mechan | -0.003 |
gol | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
bike | +0.030 |
disl | +0.027 |
spe | +0.027 |
gol | +0.023 |
Mechan | +0.023 |
Neg logit contributions | |
una | -0.024 |
eh | -0.023 |
Mia | -0.022 |
sheet | -0.020 |
inda | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.004 |
spe | -0.004 |
gol | -0.003 |
Mechan | -0.003 |
Token | bell |
Token ID | 8966 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
bike | +0.024 |
disl | +0.021 |
ishly | +0.019 |
spe | +0.019 |
qu | +0.019 |
Neg logit contributions | |
sheet | -0.014 |
page | -0.013 |
Mia | -0.012 |
corner | -0.012 |
spot | -0.011 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
disl | +0.066 |
bike | +0.063 |
gol | +0.058 |
Acc | +0.056 |
Polic | +0.055 |
Neg logit contributions | |
Mia | -0.039 |
sheet | -0.039 |
eh | -0.036 |
una | -0.036 |
ches | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
bike | +0.037 |
disl | +0.036 |
spe | +0.032 |
lder | +0.032 |
Sorry | +0.031 |
Neg logit contributions | |
Mia | -0.017 |
eh | -0.016 |
sheet | -0.015 |
una | -0.014 |
Rachel | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
una | +0.005 |
Mia | +0.005 |
eh | +0.005 |
sheet | +0.004 |
Molly | +0.004 |
Neg logit contributions | |
bike | -0.006 |
disl | -0.006 |
spe | -0.006 |
Mechan | -0.005 |
gol | -0.005 |
Token | town |
Token ID | 3240 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
bike | +0.043 |
disl | +0.040 |
qu | +0.036 |
spe | +0.036 |
amb | +0.035 |
Neg logit contributions | |
sheet | -0.026 |
page | -0.025 |
corner | -0.023 |
Mia | -0.023 |
spot | -0.021 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
disl | +0.108 |
bike | +0.098 |
Acc | +0.088 |
Sorry | +0.083 |
Mechan | +0.082 |
Neg logit contributions | |
Mia | -0.061 |
sheet | -0.055 |
inda | -0.055 |
una | -0.052 |
eh | -0.052 |
Token | ople |
Token ID | 643 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
disl | +0.142 |
bike | +0.127 |
Acc | +0.112 |
wishing | +0.110 |
affect | +0.104 |
Neg logit contributions | |
eh | -0.114 |
Mia | -0.106 |
inda | -0.106 |
una | -0.105 |
ily | -0.102 |
Token | cheered |
Token ID | 34767 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
disl | +0.027 |
bike | +0.026 |
Acc | +0.022 |
Mechan | +0.022 |
gol | +0.022 |
Neg logit contributions | |
Mia | -0.016 |
inda | -0.016 |
sheet | -0.015 |
Rachel | -0.014 |
Molly | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.81e-04 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.006 |
spe | +0.005 |
Mechan | +0.005 |
gol | +0.005 |
Neg logit contributions | |
una | -0.003 |
Mia | -0.003 |
Molly | -0.002 |
Rachel | -0.002 |
inda | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
Mechan | +0.002 |
spe | +0.002 |
lder | +0.002 |
Neg logit contributions | |
Mia | -0.002 |
Molly | -0.002 |
Rachel | -0.001 |
Lisa | -0.001 |
Emily | -0.001 |
Token | each |
Token ID | 1123 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
bike | +0.033 |
disl | +0.031 |
Mechan | +0.029 |
spe | +0.028 |
lder | +0.026 |
Neg logit contributions | |
Mia | -0.018 |
una | -0.016 |
Molly | -0.015 |
Rachel | -0.014 |
sheet | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
Mia | +0.025 |
sheet | +0.023 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.033 |
disl | -0.029 |
spe | -0.029 |
Mechan | -0.024 |
gol | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
bike | +0.005 |
disl | +0.005 |
spe | +0.005 |
gol | +0.004 |
Mechan | +0.004 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
inda | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
bike | +0.005 |
spe | +0.005 |
disl | +0.004 |
gol | +0.004 |
self | +0.004 |
Neg logit contributions | |
una | -0.007 |
eh | -0.007 |
sheet | -0.006 |
inda | -0.006 |
Mia | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
bike | +0.012 |
disl | +0.011 |
spe | +0.011 |
Mechan | +0.009 |
gol | +0.009 |
Neg logit contributions | |
una | -0.011 |
eh | -0.010 |
Mia | -0.010 |
sheet | -0.009 |
inda | -0.009 |
Token | town |
Token ID | 3240 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
bike | +0.066 |
spe | +0.058 |
disl | +0.058 |
Mechan | +0.052 |
qu | +0.049 |
Neg logit contributions | |
una | -0.040 |
eh | -0.038 |
Mia | -0.034 |
sheet | -0.034 |
inda | -0.032 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
bike | +0.081 |
disl | +0.079 |
Mechan | +0.062 |
spe | +0.061 |
Acc | +0.059 |
Neg logit contributions | |
eh | -0.080 |
una | -0.080 |
Mia | -0.079 |
inda | -0.073 |
sheet | -0.073 |
Token | ople |
Token ID | 643 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
disl | +0.124 |
bike | +0.119 |
spe | +0.097 |
Acc | +0.094 |
Mechan | +0.092 |
Neg logit contributions | |
eh | -0.138 |
una | -0.132 |
Mia | -0.126 |
inda | -0.124 |
ily | -0.123 |
Token | decided |
Token ID | 3066 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
disl | +0.016 |
bike | +0.016 |
spe | +0.013 |
Mechan | +0.013 |
gol | +0.013 |
Neg logit contributions | |
Mia | -0.009 |
eh | -0.009 |
inda | -0.009 |
una | -0.008 |
sheet | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
bike | +0.027 |
disl | +0.025 |
spe | +0.024 |
Mechan | +0.024 |
gol | +0.023 |
Neg logit contributions | |
Mia | -0.008 |
una | -0.007 |
Rachel | -0.006 |
Molly | -0.006 |
eh | -0.006 |
Token | ask |
Token ID | 1265 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
bike | +0.037 |
spe | +0.032 |
disl | +0.032 |
Mechan | +0.029 |
gol | +0.028 |
Neg logit contributions | |
Mia | -0.025 |
una | -0.024 |
sheet | -0.023 |
Molly | -0.022 |
Rachel | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
gol | +0.005 |
Mechan | +0.005 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
bike | +0.071 |
Mechan | +0.063 |
spe | +0.062 |
disl | +0.061 |
lder | +0.058 |
Neg logit contributions | |
Mia | -0.033 |
una | -0.032 |
Molly | -0.031 |
Rachel | -0.028 |
sheet | -0.026 |
Token | healthier |
Token ID | 22841 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
bike | +0.018 |
disl | +0.016 |
Mechan | +0.015 |
spe | +0.015 |
lder | +0.014 |
Neg logit contributions | |
Mia | -0.015 |
Molly | -0.013 |
una | -0.013 |
Rachel | -0.013 |
eh | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
bike | +0.089 |
disl | +0.081 |
Mechan | +0.080 |
spe | +0.078 |
Helic | +0.073 |
Neg logit contributions | |
una | -0.046 |
Mia | -0.045 |
Molly | -0.040 |
spaghetti | -0.036 |
sheet | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
bike | +0.006 |
lder | +0.005 |
disl | +0.005 |
Mechan | +0.005 |
spe | +0.005 |
Neg logit contributions | |
Mia | -0.003 |
Molly | -0.003 |
una | -0.003 |
spaghetti | -0.003 |
eh | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
bike | +0.042 |
disl | +0.040 |
Mechan | +0.037 |
lder | +0.036 |
spe | +0.034 |
Neg logit contributions | |
Mia | -0.028 |
Molly | -0.025 |
una | -0.024 |
Lisa | -0.023 |
Amy | -0.023 |
Token | community |
Token ID | 2055 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
bike | +0.065 |
disl | +0.054 |
spe | +0.054 |
Mechan | +0.053 |
qu | +0.050 |
Neg logit contributions | |
una | -0.052 |
Mia | -0.050 |
sheet | -0.047 |
Molly | -0.046 |
spaghetti | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
bike | +0.157 |
disl | +0.151 |
Mechan | +0.133 |
gol | +0.128 |
spe | +0.126 |
Neg logit contributions | |
Mia | -0.103 |
una | -0.101 |
sheet | -0.094 |
Molly | -0.093 |
eh | -0.093 |
Token | much |
Token ID | 881 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bike | +0.019 |
disl | +0.016 |
spe | +0.016 |
Mechan | +0.014 |
gol | +0.014 |
Neg logit contributions | |
eh | -0.015 |
una | -0.015 |
Mia | -0.015 |
sheet | -0.013 |
Molly | -0.013 |
Token | more |
Token ID | 517 |
Feature activation | +5.56e-03 |
Pos logit contributions | |
bike | +0.033 |
disl | +0.029 |
spe | +0.027 |
lder | +0.027 |
Mechan | +0.025 |
Neg logit contributions | |
Mia | -0.017 |
una | -0.016 |
eh | -0.016 |
Molly | -0.015 |
sheet | -0.015 |
Token | cheerful |
Token ID | 37999 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
bike | +0.012 |
Mechan | +0.010 |
spe | +0.010 |
Sorry | +0.009 |
Crane | +0.009 |
Neg logit contributions | |
eh | -0.009 |
una | -0.009 |
Mia | -0.009 |
Molly | -0.008 |
spaghetti | -0.008 |
Token | than |
Token ID | 621 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
bike | +0.057 |
disl | +0.052 |
Mechan | +0.050 |
spe | +0.049 |
lder | +0.046 |
Neg logit contributions | |
Mia | -0.027 |
una | -0.025 |
Molly | -0.024 |
sheet | -0.023 |
spaghetti | -0.022 |
Token | |
Token ID | 220 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.003 |
spe | +0.003 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
una | -0.006 |
eh | -0.006 |
Mia | -0.005 |
sheet | -0.005 |
inda | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
una | +0.036 |
eh | +0.035 |
sheet | +0.032 |
Mia | +0.032 |
inda | +0.030 |
Neg logit contributions | |
bike | -0.035 |
spe | -0.031 |
disl | -0.031 |
gol | -0.026 |
self | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
una | +0.043 |
eh | +0.041 |
sheet | +0.040 |
Mia | +0.037 |
ori | +0.036 |
Neg logit contributions | |
bike | -0.040 |
spe | -0.036 |
disl | -0.035 |
gol | -0.029 |
self | -0.028 |
Token | The |
Token ID | 464 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
una | +0.026 |
eh | +0.025 |
Mia | +0.023 |
sheet | +0.023 |
inda | +0.022 |
Neg logit contributions | |
bike | -0.029 |
spe | -0.026 |
disl | -0.026 |
gol | -0.022 |
Mechan | -0.021 |
Token | town |
Token ID | 3240 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
bike | +0.014 |
disl | +0.013 |
spe | +0.012 |
Mechan | +0.011 |
qu | +0.011 |
Neg logit contributions | |
eh | -0.012 |
una | -0.012 |
sheet | -0.011 |
Mia | -0.011 |
inda | -0.010 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
disl | +0.081 |
bike | +0.078 |
Mechan | +0.063 |
Acc | +0.062 |
affect | +0.062 |
Neg logit contributions | |
Mia | -0.072 |
eh | -0.066 |
inda | -0.064 |
una | -0.064 |
ia | -0.062 |
Token | ople |
Token ID | 643 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
disl | +0.131 |
bike | +0.115 |
wishing | +0.101 |
Acc | +0.101 |
miss | +0.101 |
Neg logit contributions | |
eh | -0.126 |
inda | -0.114 |
Mia | -0.108 |
ily | -0.108 |
enzie | -0.107 |
Token | had |
Token ID | 550 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
disl | +0.020 |
bike | +0.020 |
Acc | +0.017 |
Mechan | +0.017 |
Sorry | +0.016 |
Neg logit contributions | |
Mia | -0.013 |
inda | -0.013 |
eh | -0.012 |
Rachel | -0.011 |
enzie | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Mia | +0.003 |
eh | +0.003 |
una | +0.003 |
sheet | +0.003 |
Rachel | +0.003 |
Neg logit contributions | |
bike | -0.006 |
disl | -0.005 |
spe | -0.005 |
Acc | -0.005 |
Sorry | -0.005 |
Token | find |
Token ID | 1064 |
Feature activation | +2.81e-04 |
Pos logit contributions | |
bike | +0.041 |
disl | +0.036 |
spe | +0.036 |
Mechan | +0.033 |
Acc | +0.032 |
Neg logit contributions | |
Mia | -0.032 |
una | -0.028 |
sheet | -0.028 |
Rachel | -0.027 |
eh | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
bike | +0.001 |
disl | +0.001 |
spe | +0.001 |
Mechan | +0.001 |
gol | +0.001 |
Neg logit contributions | |
una | -0.000 |
Mia | -0.000 |
eh | -0.000 |
sheet | -0.000 |
inda | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
bike | +0.009 |
disl | +0.008 |
spe | +0.007 |
Mechan | +0.007 |
gol | +0.007 |
Neg logit contributions | |
Mia | -0.004 |
eh | -0.004 |
una | -0.004 |
sheet | -0.003 |
Rachel | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
una | +0.018 |
eh | +0.017 |
Mia | +0.017 |
sheet | +0.015 |
Molly | +0.015 |
Neg logit contributions | |
bike | -0.024 |
disl | -0.021 |
spe | -0.021 |
gol | -0.018 |
Mechan | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
una | +0.020 |
eh | +0.020 |
Mia | +0.018 |
sheet | +0.018 |
inda | +0.017 |
Neg logit contributions | |
bike | -0.020 |
disl | -0.018 |
spe | -0.018 |
Mechan | -0.015 |
gol | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.013 |
sheet | +0.013 |
inda | +0.013 |
Neg logit contributions | |
bike | -0.017 |
disl | -0.015 |
spe | -0.015 |
gol | -0.013 |
Mechan | -0.013 |
Token | town |
Token ID | 3240 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
bike | +0.058 |
disl | +0.056 |
spe | +0.051 |
Acc | +0.047 |
Sorry | +0.045 |
Neg logit contributions | |
eh | -0.037 |
una | -0.035 |
sheet | -0.034 |
Mia | -0.032 |
spot | -0.030 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
disl | +0.091 |
bike | +0.085 |
Acc | +0.071 |
Mechan | +0.070 |
Sorry | +0.070 |
Neg logit contributions | |
Mia | -0.063 |
eh | -0.063 |
una | -0.062 |
sheet | -0.057 |
ia | -0.056 |
Token | ople |
Token ID | 643 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
disl | +0.142 |
bike | +0.128 |
Acc | +0.112 |
wishing | +0.108 |
miss | +0.107 |
Neg logit contributions | |
eh | -0.117 |
una | -0.108 |
Mia | -0.106 |
ily | -0.104 |
inda | -0.102 |
Token | were |
Token ID | 547 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.007 |
spe | +0.005 |
Sorry | +0.005 |
Mechan | +0.005 |
Neg logit contributions | |
Mia | -0.005 |
una | -0.005 |
eh | -0.005 |
inda | -0.005 |
sheet | -0.005 |
Token | relieved |
Token ID | 22598 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
bike | +0.018 |
disl | +0.016 |
spe | +0.014 |
Mechan | +0.013 |
gol | +0.013 |
Neg logit contributions | |
eh | -0.014 |
Mia | -0.013 |
una | -0.013 |
Molly | -0.012 |
sheet | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-04 |
Pos logit contributions | |
bike | +0.023 |
disl | +0.022 |
spe | +0.021 |
Mechan | +0.020 |
gol | +0.019 |
Neg logit contributions | |
Mia | -0.011 |
una | -0.010 |
Molly | -0.010 |
Rachel | -0.009 |
sheet | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
Mia | +0.000 |
una | +0.000 |
Molly | +0.000 |
Rachel | +0.000 |
eh | +0.000 |
Neg logit contributions | |
bike | -0.001 |
disl | -0.001 |
spe | -0.001 |
Mechan | -0.000 |
gol | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
bike | +0.087 |
disl | +0.085 |
Mechan | +0.078 |
Acc | +0.078 |
Sy | +0.075 |
Neg logit contributions | |
Mia | -0.037 |
Lisa | -0.029 |
eh | -0.028 |
Rachel | -0.028 |
inda | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
bike | +0.016 |
disl | +0.014 |
spe | +0.014 |
Mechan | +0.012 |
self | +0.011 |
Neg logit contributions | |
Mia | -0.012 |
una | -0.012 |
eh | -0.012 |
Molly | -0.011 |
Rachel | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
bike | +0.014 |
spe | +0.012 |
disl | +0.011 |
gol | +0.010 |
qu | +0.009 |
Neg logit contributions | |
una | -0.018 |
eh | -0.018 |
sheet | -0.016 |
Mia | -0.016 |
inda | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
bike | +0.021 |
disl | +0.019 |
spe | +0.018 |
Mechan | +0.016 |
Acc | +0.016 |
Neg logit contributions | |
una | -0.017 |
eh | -0.016 |
Mia | -0.014 |
inda | -0.014 |
sheet | -0.013 |
Token | town |
Token ID | 3240 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
disl | +0.056 |
bike | +0.055 |
ishly | +0.049 |
affect | +0.047 |
qu | +0.046 |
Neg logit contributions | |
page | -0.035 |
corner | -0.035 |
Mia | -0.031 |
eh | -0.030 |
ily | -0.029 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
disl | +0.086 |
bike | +0.070 |
Acc | +0.068 |
affect | +0.065 |
Majesty | +0.058 |
Neg logit contributions | |
Mia | -0.069 |
eh | -0.062 |
ia | -0.061 |
ily | -0.061 |
una | -0.060 |
Token | ople |
Token ID | 643 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
disl | +0.145 |
bike | +0.125 |
Acc | +0.118 |
affect | +0.113 |
wishing | +0.111 |
Neg logit contributions | |
eh | -0.106 |
una | -0.096 |
ily | -0.096 |
Mia | -0.093 |
adies | -0.090 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
bike | +0.011 |
disl | +0.011 |
Acc | +0.009 |
Sorry | +0.009 |
Mechan | +0.008 |
Neg logit contributions | |
Mia | -0.007 |
inda | -0.006 |
eh | -0.006 |
una | -0.006 |
Rachel | -0.006 |
Token | together |
Token ID | 1978 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
bike | +0.035 |
disl | +0.032 |
spe | +0.030 |
Mechan | +0.027 |
Sorry | +0.027 |
Neg logit contributions | |
una | -0.028 |
eh | -0.028 |
Mia | -0.027 |
sheet | -0.025 |
inda | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
una | +0.018 |
eh | +0.017 |
Mia | +0.016 |
sheet | +0.015 |
inda | +0.015 |
Neg logit contributions | |
bike | -0.028 |
disl | -0.025 |
spe | -0.024 |
Mechan | -0.022 |
Sorry | -0.022 |
Token | help |
Token ID | 1037 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
bike | +0.007 |
spe | +0.007 |
disl | +0.006 |
ishly | +0.006 |
lder | +0.006 |
Neg logit contributions | |
Mia | -0.004 |
sheet | -0.004 |
eh | -0.004 |
inda | -0.004 |
Rachel | -0.004 |
Token | back |
Token ID | 736 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
una | +0.019 |
Mia | +0.017 |
eh | +0.017 |
sheet | +0.016 |
Molly | +0.016 |
Neg logit contributions | |
bike | -0.036 |
spe | -0.032 |
disl | -0.032 |
Mechan | -0.029 |
lder | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
una | +0.026 |
eh | +0.026 |
Mia | +0.024 |
sheet | +0.022 |
inda | +0.021 |
Neg logit contributions | |
bike | -0.051 |
disl | -0.046 |
spe | -0.045 |
Mechan | -0.041 |
gol | -0.040 |
Token | village |
Token ID | 7404 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
bike | +0.010 |
disl | +0.008 |
spe | +0.008 |
Sorry | +0.007 |
ishly | +0.007 |
Neg logit contributions | |
eh | -0.006 |
una | -0.006 |
sheet | -0.006 |
jam | -0.005 |
Mia | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
bike | +0.048 |
disl | +0.044 |
Mechan | +0.040 |
Sorry | +0.040 |
gol | +0.039 |
Neg logit contributions | |
eh | -0.027 |
Mia | -0.026 |
sheet | -0.024 |
una | -0.024 |
Molly | -0.023 |
Token | its |
Token ID | 663 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
bike | +0.022 |
spe | +0.020 |
disl | +0.019 |
Mechan | +0.017 |
gol | +0.017 |
Neg logit contributions | |
Mia | -0.009 |
una | -0.009 |
Molly | -0.008 |
Rachel | -0.008 |
sheet | -0.008 |
Token | former |
Token ID | 1966 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
bike | +0.034 |
disl | +0.030 |
spe | +0.028 |
Mechan | +0.026 |
gol | +0.025 |
Neg logit contributions | |
eh | -0.026 |
una | -0.026 |
Mia | -0.024 |
sheet | -0.023 |
Molly | -0.022 |
Token | state |
Token ID | 1181 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
bike | +0.145 |
disl | +0.119 |
spe | +0.118 |
Mechan | +0.104 |
gol | +0.104 |
Neg logit contributions | |
una | -0.137 |
eh | -0.135 |
Mia | -0.124 |
sheet | -0.121 |
inda | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
bike | +0.064 |
disl | +0.058 |
spe | +0.054 |
Mechan | +0.051 |
Sorry | +0.051 |
Neg logit contributions | |
una | -0.038 |
eh | -0.036 |
Mia | -0.035 |
sheet | -0.033 |
inda | -0.032 |
Token | With |
Token ID | 2080 |
Feature activation | -5.87e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.002 |
spe | +0.002 |
gol | +0.002 |
Mechan | +0.002 |
Neg logit contributions | |
una | -0.002 |
Mia | -0.002 |
eh | -0.002 |
Molly | -0.002 |
Rachel | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
una | +0.008 |
Mia | +0.007 |
eh | +0.007 |
sheet | +0.007 |
Molly | +0.006 |
Neg logit contributions | |
bike | -0.015 |
disl | -0.013 |
spe | -0.013 |
Mechan | -0.012 |
gol | -0.011 |
Token | help |
Token ID | 1037 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
bike | +0.020 |
spe | +0.017 |
disl | +0.017 |
Mechan | +0.015 |
Sorry | +0.015 |
Neg logit contributions | |
eh | -0.015 |
una | -0.015 |
sheet | -0.015 |
Mia | -0.014 |
inda | -0.014 |
Token | family |
Token ID | 1641 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
bike | +0.057 |
disl | +0.052 |
spe | +0.051 |
qu | +0.045 |
Mechan | +0.045 |
Neg logit contributions | |
una | -0.037 |
sheet | -0.035 |
Mia | -0.033 |
eh | -0.032 |
Molly | -0.031 |
Token | woke |
Token ID | 19092 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
disl | +0.096 |
bike | +0.089 |
spe | +0.077 |
Acc | +0.072 |
Mechan | +0.070 |
Neg logit contributions | |
eh | -0.057 |
Mia | -0.057 |
una | -0.057 |
sheet | -0.055 |
Molly | -0.052 |
Token | up |
Token ID | 510 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
bike | +0.120 |
spe | +0.113 |
disl | +0.111 |
Mechan | +0.103 |
gol | +0.100 |
Neg logit contributions | |
una | -0.042 |
Mia | -0.039 |
eh | -0.038 |
sheet | -0.035 |
Molly | -0.034 |
Token | feeling |
Token ID | 4203 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
bike | +0.076 |
disl | +0.071 |
spe | +0.064 |
Mechan | +0.062 |
lder | +0.059 |
Neg logit contributions | |
Mia | -0.031 |
eh | -0.030 |
una | -0.029 |
Molly | -0.028 |
sheet | -0.027 |
Token | very |
Token ID | 845 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
bike | +0.047 |
spe | +0.041 |
disl | +0.040 |
Mechan | +0.036 |
gol | +0.034 |
Neg logit contributions | |
eh | -0.040 |
una | -0.038 |
Mia | -0.037 |
Molly | -0.035 |
sheet | -0.034 |
Token | un |
Token ID | 555 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
bike | +0.015 |
Mechan | +0.012 |
spe | +0.012 |
disl | +0.011 |
Crane | +0.011 |
Neg logit contributions | |
eh | -0.011 |
Mia | -0.010 |
Molly | -0.010 |
ulp | -0.010 |
una | -0.010 |
Token | well |
Token ID | 4053 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
disl | +0.127 |
bike | +0.099 |
Sorry | +0.093 |
prope | +0.092 |
affect | +0.092 |
Neg logit contributions | |
eh | -0.138 |
ches | -0.120 |
inda | -0.116 |
inn | -0.115 |
aks | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
bike | +0.054 |
disl | +0.053 |
spe | +0.049 |
Mechan | +0.045 |
Sorry | +0.045 |
Neg logit contributions | |
una | -0.026 |
eh | -0.023 |
Mia | -0.021 |
sheet | -0.021 |
ily | -0.020 |
Token | The |
Token ID | 383 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
bike | +0.027 |
disl | +0.024 |
spe | +0.024 |
Mechan | +0.020 |
gol | +0.020 |
Neg logit contributions | |
una | -0.023 |
eh | -0.022 |
Mia | -0.021 |
sheet | -0.020 |
inda | -0.020 |
Token | blue |
Token ID | 4171 |
Feature activation | -7.55e-03 |
Pos logit contributions | |
bike | +0.032 |
disl | +0.029 |
spe | +0.028 |
Sorry | +0.025 |
Mechan | +0.025 |
Neg logit contributions | |
una | -0.023 |
eh | -0.023 |
sheet | -0.021 |
Mia | -0.021 |
spaghetti | -0.019 |
Token | o |
Token ID | 267 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
una | +0.013 |
eh | +0.013 |
Mia | +0.012 |
sheet | +0.011 |
inda | +0.011 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.014 |
spe | -0.014 |
gol | -0.012 |
Mechan | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
bike | +0.020 |
disl | +0.018 |
spe | +0.018 |
gol | +0.016 |
Mechan | +0.016 |
Neg logit contributions | |
una | -0.015 |
Mia | -0.015 |
eh | -0.014 |
Molly | -0.013 |
inda | -0.013 |
Token | really |
Token ID | 1107 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
bike | +0.026 |
disl | +0.022 |
spe | +0.021 |
Mechan | +0.019 |
gol | +0.019 |
Neg logit contributions | |
eh | -0.026 |
una | -0.026 |
Mia | -0.025 |
Molly | -0.023 |
inda | -0.023 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Mia | +0.003 |
eh | +0.003 |
una | +0.003 |
Molly | +0.003 |
Rachel | +0.002 |
Neg logit contributions | |
bike | -0.003 |
spe | -0.003 |
disl | -0.003 |
Mechan | -0.003 |
gol | -0.003 |
Token | about |
Token ID | 546 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
bike | +0.049 |
disl | +0.044 |
spe | +0.044 |
Mechan | +0.039 |
gol | +0.038 |
Neg logit contributions | |
una | -0.031 |
eh | -0.029 |
Mia | -0.028 |
sheet | -0.026 |
inda | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
bike | +0.079 |
spe | +0.071 |
disl | +0.069 |
Mechan | +0.064 |
lder | +0.062 |
Neg logit contributions | |
una | -0.044 |
Mia | -0.043 |
eh | -0.040 |
Molly | -0.037 |
sheet | -0.037 |
Token | upcoming |
Token ID | 7865 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
bike | +0.073 |
disl | +0.067 |
spe | +0.061 |
qu | +0.060 |
ishly | +0.059 |
Neg logit contributions | |
sheet | -0.043 |
una | -0.041 |
eh | -0.037 |
page | -0.036 |
Mia | -0.036 |
Token | adventure |
Token ID | 8855 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
disl | +0.149 |
bike | +0.145 |
spe | +0.134 |
ishly | +0.124 |
Acc | +0.119 |
Neg logit contributions | |
sheet | -0.109 |
una | -0.107 |
eh | -0.106 |
spaghetti | -0.096 |
page | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
bike | +0.065 |
disl | +0.062 |
spe | +0.058 |
Mechan | +0.053 |
gol | +0.052 |
Neg logit contributions | |
una | -0.046 |
eh | -0.044 |
Mia | -0.043 |
sheet | -0.040 |
inda | -0.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.004 |
spe | +0.004 |
gol | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
sheet | -0.005 |
inda | -0.004 |
ori | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
bike | +0.032 |
spe | +0.027 |
disl | +0.026 |
Mechan | +0.023 |
gol | +0.023 |
Neg logit contributions | |
una | -0.036 |
eh | -0.036 |
inda | -0.032 |
sheet | -0.032 |
Mia | -0.030 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.94e-03 |
Pos logit contributions | |
bike | +0.019 |
spe | +0.018 |
disl | +0.017 |
je | +0.015 |
gol | +0.015 |
Neg logit contributions | |
una | -0.011 |
eh | -0.011 |
sheet | -0.008 |
ori | -0.008 |
spaghetti | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
una | +0.025 |
Mia | +0.023 |
sheet | +0.021 |
eh | +0.021 |
inda | +0.020 |
Neg logit contributions | |
bike | -0.042 |
spe | -0.036 |
disl | -0.035 |
Mechan | -0.034 |
gol | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
bike | +0.016 |
disl | +0.014 |
spe | +0.014 |
Mechan | +0.012 |
gol | +0.012 |
Neg logit contributions | |
una | -0.012 |
Mia | -0.011 |
eh | -0.011 |
sheet | -0.010 |
Molly | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
bike | +0.017 |
spe | +0.015 |
disl | +0.015 |
gol | +0.013 |
Mechan | +0.013 |
Neg logit contributions | |
una | -0.017 |
eh | -0.017 |
Mia | -0.016 |
sheet | -0.015 |
inda | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
bike | +0.024 |
disl | +0.021 |
spe | +0.021 |
Mechan | +0.018 |
gol | +0.018 |
Neg logit contributions | |
una | -0.016 |
eh | -0.016 |
Mia | -0.014 |
sheet | -0.013 |
inda | -0.013 |
Token | town |
Token ID | 3240 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
bike | +0.053 |
disl | +0.048 |
Mechan | +0.042 |
ishly | +0.042 |
amb | +0.042 |
Neg logit contributions | |
corner | -0.027 |
eh | -0.026 |
page | -0.024 |
sheet | -0.023 |
spot | -0.023 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
disl | +0.089 |
bike | +0.078 |
Mechan | +0.068 |
Acc | +0.068 |
Sorry | +0.064 |
Neg logit contributions | |
Mia | -0.066 |
eh | -0.061 |
una | -0.060 |
inda | -0.060 |
of | -0.060 |
Token | ople |
Token ID | 643 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
disl | +0.140 |
bike | +0.125 |
Acc | +0.109 |
wishing | +0.107 |
miss | +0.103 |
Neg logit contributions | |
eh | -0.110 |
una | -0.104 |
Mia | -0.101 |
ily | -0.100 |
inda | -0.098 |
Token | were |
Token ID | 547 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.017 |
Mechan | +0.015 |
gol | +0.014 |
Sorry | +0.014 |
Neg logit contributions | |
una | -0.011 |
inda | -0.011 |
enzie | -0.011 |
Mia | -0.011 |
ches | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
bike | +0.019 |
disl | +0.018 |
spe | +0.016 |
Mechan | +0.015 |
gol | +0.015 |
Neg logit contributions | |
Mia | -0.014 |
eh | -0.014 |
una | -0.014 |
Molly | -0.012 |
Rachel | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Mia | +0.005 |
ulu | +0.004 |
hes | +0.004 |
Molly | +0.004 |
Rachel | +0.004 |
Neg logit contributions | |
bike | -0.010 |
disl | -0.008 |
Mechan | -0.008 |
ishly | -0.008 |
arrest | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -6.87e-04 |
Pos logit contributions | |
bike | +0.057 |
spe | +0.051 |
disl | +0.051 |
Mechan | +0.049 |
self | +0.047 |
Neg logit contributions | |
Mia | -0.030 |
una | -0.029 |
Molly | -0.026 |
Rachel | -0.025 |
sheet | -0.024 |
Token | |
Token ID | 220 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
bike | +0.018 |
disl | +0.016 |
spe | +0.015 |
Mechan | +0.013 |
gol | +0.013 |
Neg logit contributions | |
Mia | -0.013 |
una | -0.013 |
eh | -0.012 |
Molly | -0.011 |
Rachel | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
bike | +0.031 |
disl | +0.027 |
spe | +0.026 |
Mechan | +0.022 |
gol | +0.022 |
Neg logit contributions | |
una | -0.032 |
eh | -0.032 |
sheet | -0.029 |
Mia | -0.029 |
inda | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
bike | +0.025 |
disl | +0.022 |
spe | +0.022 |
gol | +0.018 |
Mechan | +0.018 |
Neg logit contributions | |
una | -0.023 |
eh | -0.023 |
Mia | -0.021 |
sheet | -0.020 |
inda | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
bike | +0.027 |
disl | +0.023 |
spe | +0.023 |
Mechan | +0.020 |
gol | +0.020 |
Neg logit contributions | |
una | -0.021 |
eh | -0.021 |
Mia | -0.019 |
inda | -0.018 |
sheet | -0.018 |
Token | town |
Token ID | 3240 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
bike | +0.053 |
disl | +0.049 |
spe | +0.047 |
gol | +0.042 |
ishly | +0.042 |
Neg logit contributions | |
eh | -0.031 |
sheet | -0.030 |
una | -0.030 |
Mia | -0.027 |
ily | -0.026 |
Token | spe |
Token ID | 4125 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
disl | +0.077 |
bike | +0.072 |
Acc | +0.057 |
Mechan | +0.056 |
affect | +0.054 |
Neg logit contributions | |
Mia | -0.070 |
eh | -0.068 |
una | -0.067 |
inda | -0.064 |
sheet | -0.063 |
Token | ople |
Token ID | 643 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
disl | +0.125 |
bike | +0.117 |
spe | +0.098 |
Acc | +0.092 |
wishing | +0.090 |
Neg logit contributions | |
eh | -0.133 |
una | -0.130 |
Mia | -0.122 |
ily | -0.120 |
inda | -0.119 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
disl | +0.018 |
bike | +0.017 |
Mechan | +0.015 |
spe | +0.015 |
Acc | +0.014 |
Neg logit contributions | |
Mia | -0.009 |
inda | -0.008 |
eh | -0.008 |
una | -0.008 |
ily | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +5.21e-04 |
Pos logit contributions | |
eh | +0.009 |
una | +0.009 |
Mia | +0.007 |
enzie | +0.007 |
ori | +0.007 |
Neg logit contributions | |
bike | -0.011 |
disl | -0.010 |
spe | -0.010 |
gol | -0.008 |
Mechan | -0.008 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
bike | +0.001 |
disl | +0.001 |
spe | +0.001 |
hy | +0.001 |
affect | +0.001 |
Neg logit contributions | |
Mia | -0.001 |
una | -0.001 |
Rachel | -0.001 |
inda | -0.001 |
Molly | -0.001 |
Token | until |
Token ID | 1566 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
gol | +0.005 |
Mechan | +0.005 |
Neg logit contributions | |
eh | -0.005 |
una | -0.005 |
Mia | -0.004 |
enzie | -0.004 |
ori | -0.004 |
Token | this |
Token ID | 428 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
bike | +0.021 |
disl | +0.020 |
wishing | +0.016 |
Sorry | +0.016 |
rh | +0.016 |
Neg logit contributions | |
una | -0.027 |
eh | -0.027 |
inda | -0.025 |
enzie | -0.025 |
ori | -0.024 |
Token | ? |
Token ID | 30 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.007 |
spe | +0.006 |
lder | +0.005 |
bell | +0.005 |
Neg logit contributions | |
eh | -0.006 |
una | -0.005 |
inda | -0.005 |
Mia | -0.005 |
ori | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
bike | +0.005 |
spe | +0.005 |
disl | +0.004 |
gol | +0.004 |
Mechan | +0.004 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
Molly | -0.004 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
una | +0.018 |
eh | +0.018 |
Mia | +0.016 |
sheet | +0.016 |
inda | +0.015 |
Neg logit contributions | |
bike | -0.020 |
disl | -0.017 |
spe | -0.017 |
gol | -0.015 |
Mechan | -0.015 |
Token | y |
Token ID | 331 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
una | +0.038 |
eh | +0.037 |
Mia | +0.034 |
sheet | +0.033 |
ori | +0.033 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.029 |
spe | -0.028 |
gol | -0.023 |
self | -0.023 |
Token | ucky |
Token ID | 5309 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
eh | +0.069 |
una | +0.068 |
Mia | +0.063 |
inda | +0.062 |
sheet | +0.062 |
Neg logit contributions | |
bike | -0.049 |
disl | -0.041 |
spe | -0.039 |
gol | -0.034 |
self | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
una | +0.173 |
eh | +0.169 |
Mia | +0.157 |
inda | +0.153 |
ori | +0.153 |
Neg logit contributions | |
bike | -0.172 |
disl | -0.149 |
spe | -0.144 |
gol | -0.122 |
Mechan | -0.120 |
Token | I |
Token ID | 314 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
una | +0.022 |
eh | +0.022 |
sheet | +0.020 |
Mia | +0.020 |
inda | +0.019 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.018 |
spe | -0.017 |
Mechan | -0.015 |
Sorry | -0.015 |
Token | don |
Token ID | 836 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
una | +0.084 |
eh | +0.083 |
Mia | +0.078 |
sheet | +0.073 |
inda | +0.071 |
Neg logit contributions | |
bike | -0.096 |
spe | -0.082 |
disl | -0.078 |
gol | -0.068 |
Mechan | -0.068 |
Token | 't |
Token ID | 470 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
una | +0.036 |
eh | +0.036 |
Mia | +0.034 |
inda | +0.033 |
sheet | +0.033 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.016 |
spe | -0.016 |
Mechan | -0.013 |
qu | -0.012 |
Token | want |
Token ID | 765 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
una | +0.035 |
eh | +0.034 |
Mia | +0.032 |
sheet | +0.031 |
inda | +0.030 |
Neg logit contributions | |
bike | -0.027 |
disl | -0.024 |
spe | -0.023 |
gol | -0.019 |
Mechan | -0.019 |
Token | not |
Token ID | 407 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.017 |
sheet | +0.016 |
Mia | +0.016 |
ori | +0.016 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.015 |
spe | -0.015 |
wishing | -0.012 |
gol | -0.012 |
Token | bigger |
Token ID | 5749 |
Feature activation | +9.71e-04 |
Pos logit contributions | |
una | +0.041 |
eh | +0.041 |
Mia | +0.038 |
sheet | +0.036 |
inda | +0.035 |
Neg logit contributions | |
bike | -0.048 |
disl | -0.041 |
spe | -0.041 |
Mechan | -0.035 |
gol | -0.035 |
Token | than |
Token ID | 621 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
Mechan | +0.002 |
lder | +0.002 |
Neg logit contributions | |
una | -0.002 |
Mia | -0.001 |
eh | -0.001 |
sheet | -0.001 |
Molly | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +6.47e-04 |
Pos logit contributions | |
una | +0.011 |
Mia | +0.011 |
eh | +0.010 |
sheet | +0.009 |
Molly | +0.009 |
Neg logit contributions | |
bike | -0.020 |
disl | -0.017 |
spe | -0.017 |
Mechan | -0.016 |
gol | -0.015 |
Token | fing |
Token ID | 8038 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
bike | +0.001 |
disl | +0.001 |
spe | +0.001 |
Mechan | +0.001 |
self | +0.001 |
Neg logit contributions | |
una | -0.001 |
eh | -0.001 |
Mia | -0.001 |
sheet | -0.001 |
Molly | -0.001 |
Token | ern |
Token ID | 1142 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.019 |
Mia | +0.018 |
sheet | +0.017 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.025 |
disl | -0.023 |
spe | -0.022 |
gol | -0.019 |
Mechan | -0.019 |
Token | ail |
Token ID | 603 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
una | +0.162 |
eh | +0.145 |
Mia | +0.139 |
Luna | +0.139 |
sheet | +0.138 |
Neg logit contributions | |
bike | -0.162 |
spe | -0.149 |
disl | -0.139 |
gol | -0.120 |
qu | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
una | +0.057 |
eh | +0.055 |
Mia | +0.053 |
sheet | +0.049 |
inda | +0.047 |
Neg logit contributions | |
bike | -0.092 |
disl | -0.082 |
spe | -0.081 |
Mechan | -0.076 |
Sorry | -0.074 |
Token | They |
Token ID | 1119 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
bike | +0.015 |
disl | +0.013 |
spe | +0.013 |
Mechan | +0.011 |
gol | +0.011 |
Neg logit contributions | |
una | -0.012 |
eh | -0.011 |
Mia | -0.011 |
sheet | -0.010 |
inda | -0.010 |
Token | also |
Token ID | 635 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
una | +0.025 |
Mia | +0.024 |
eh | +0.024 |
inda | +0.022 |
sheet | +0.022 |
Neg logit contributions | |
bike | -0.029 |
disl | -0.026 |
spe | -0.024 |
Mechan | -0.022 |
gol | -0.022 |
Token | found |
Token ID | 1043 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
bike | +0.009 |
disl | +0.008 |
spe | +0.008 |
Mechan | +0.007 |
gol | +0.007 |
Neg logit contributions | |
eh | -0.006 |
Mia | -0.005 |
una | -0.005 |
inda | -0.005 |
Rachel | -0.005 |
Token | This |
Token ID | 1212 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
bike | +0.075 |
spe | +0.065 |
disl | +0.064 |
Mechan | +0.053 |
gol | +0.053 |
Neg logit contributions | |
una | -0.082 |
eh | -0.080 |
Mia | -0.074 |
sheet | -0.070 |
inda | -0.069 |
Token | cel |
Token ID | 18725 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
bike | +0.005 |
disl | +0.005 |
spe | +0.005 |
Mechan | +0.004 |
gol | +0.004 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | ery |
Token ID | 1924 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
Mia | +0.026 |
sheet | +0.022 |
ori | +0.021 |
Neg logit contributions | |
bike | -0.066 |
disl | -0.061 |
spe | -0.059 |
qu | -0.054 |
self | -0.054 |
Token | tastes |
Token ID | 18221 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
una | +0.014 |
eh | +0.013 |
Mia | +0.013 |
sheet | +0.012 |
spaghetti | +0.011 |
Neg logit contributions | |
bike | -0.021 |
spe | -0.019 |
disl | -0.018 |
gol | -0.017 |
Mad | -0.016 |
Token | y |
Token ID | 331 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
una | +0.038 |
eh | +0.036 |
Mia | +0.034 |
sheet | +0.032 |
spaghetti | +0.031 |
Neg logit contributions | |
bike | -0.044 |
spe | -0.038 |
disl | -0.037 |
Mechan | -0.033 |
gol | -0.032 |
Token | ucky |
Token ID | 5309 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
una | +0.049 |
eh | +0.049 |
Mia | +0.044 |
sheet | +0.043 |
inda | +0.042 |
Neg logit contributions | |
bike | -0.061 |
disl | -0.054 |
spe | -0.053 |
gol | -0.046 |
Mechan | -0.045 |
Token | ," |
Token ID | 553 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
una | +0.151 |
eh | +0.145 |
Mia | +0.135 |
sheet | +0.127 |
inda | +0.120 |
Neg logit contributions | |
bike | -0.183 |
spe | -0.161 |
disl | -0.160 |
Mechan | -0.139 |
gol | -0.137 |
Token | he |
Token ID | 339 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
una | +0.021 |
eh | +0.020 |
Mia | +0.018 |
sheet | +0.017 |
inda | +0.017 |
Neg logit contributions | |
bike | -0.029 |
disl | -0.026 |
spe | -0.025 |
gol | -0.022 |
Mechan | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.007 |
spe | +0.007 |
gol | +0.006 |
Mechan | +0.006 |
Neg logit contributions | |
una | -0.010 |
eh | -0.010 |
Mia | -0.009 |
sheet | -0.009 |
inda | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
Mia | +0.017 |
eh | +0.016 |
una | +0.016 |
Molly | +0.014 |
ily | +0.013 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.029 |
spe | -0.028 |
Mechan | -0.026 |
gol | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
una | +0.022 |
eh | +0.021 |
Mia | +0.020 |
sheet | +0.018 |
inda | +0.018 |
Neg logit contributions | |
bike | -0.026 |
disl | -0.023 |
spe | -0.023 |
gol | -0.019 |
Mechan | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
una | +0.052 |
eh | +0.051 |
Mia | +0.047 |
sheet | +0.046 |
inda | +0.043 |
Neg logit contributions | |
bike | -0.063 |
disl | -0.057 |
spe | -0.055 |
Mechan | -0.047 |
gol | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
una | +0.023 |
eh | +0.022 |
Mia | +0.021 |
sheet | +0.020 |
inda | +0.019 |
Neg logit contributions | |
bike | -0.025 |
disl | -0.022 |
spe | -0.021 |
gol | -0.018 |
Mechan | -0.018 |
Token | just |
Token ID | 655 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
una | +0.039 |
eh | +0.039 |
Mia | +0.036 |
sheet | +0.035 |
inda | +0.033 |
Neg logit contributions | |
bike | -0.043 |
disl | -0.038 |
spe | -0.037 |
gol | -0.031 |
Mechan | -0.031 |
Token | as |
Token ID | 355 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
Mia | +0.048 |
eh | +0.047 |
una | +0.047 |
sheet | +0.042 |
inda | +0.041 |
Neg logit contributions | |
bike | -0.100 |
spe | -0.087 |
disl | -0.086 |
lder | -0.081 |
Mechan | -0.079 |
Token | boun |
Token ID | 31283 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
una | +0.089 |
eh | +0.085 |
Mia | +0.084 |
sheet | +0.079 |
inda | +0.074 |
Neg logit contributions | |
bike | -0.106 |
disl | -0.091 |
spe | -0.088 |
Mechan | -0.078 |
lder | -0.076 |
Token | cy |
Token ID | 948 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
una | +0.081 |
eh | +0.079 |
Mia | +0.072 |
sheet | +0.071 |
ori | +0.070 |
Neg logit contributions | |
bike | -0.056 |
spe | -0.045 |
disl | -0.042 |
gol | -0.042 |
self | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
una | +0.134 |
eh | +0.131 |
Mia | +0.121 |
sheet | +0.115 |
inda | +0.109 |
Neg logit contributions | |
bike | -0.188 |
disl | -0.167 |
spe | -0.166 |
Mechan | -0.145 |
gol | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +8.62e-04 |
Pos logit contributions | |
una | +0.086 |
eh | +0.083 |
Mia | +0.075 |
sheet | +0.072 |
inda | +0.069 |
Neg logit contributions | |
bike | -0.130 |
disl | -0.116 |
spe | -0.115 |
gol | -0.100 |
Mechan | -0.100 |
Token | red |
Token ID | 2266 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
gol | +0.001 |
Mechan | +0.001 |
Neg logit contributions | |
una | -0.002 |
eh | -0.001 |
Mia | -0.001 |
sheet | -0.001 |
inda | -0.001 |
Token | one |
Token ID | 530 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
una | +0.070 |
eh | +0.070 |
inda | +0.062 |
Mia | +0.061 |
ori | +0.060 |
Neg logit contributions | |
bike | -0.065 |
spe | -0.052 |
disl | -0.051 |
gol | -0.047 |
bell | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
una | +0.046 |
eh | +0.044 |
Mia | +0.040 |
sheet | +0.039 |
inda | +0.038 |
Neg logit contributions | |
bike | -0.051 |
spe | -0.044 |
disl | -0.044 |
gol | -0.038 |
self | -0.037 |
Token | squash |
Token ID | 34613 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
una | +0.001 |
Mia | +0.001 |
eh | +0.001 |
spaghetti | +0.001 |
sheet | +0.001 |
Neg logit contributions | |
bike | -0.001 |
spe | -0.001 |
disl | -0.001 |
Mechan | -0.001 |
gol | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
una | +0.021 |
eh | +0.020 |
Mia | +0.019 |
sheet | +0.018 |
spaghetti | +0.018 |
Neg logit contributions | |
bike | -0.025 |
spe | -0.023 |
disl | -0.023 |
Mechan | -0.020 |
gol | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
bike | +0.023 |
spe | +0.020 |
disl | +0.020 |
gol | +0.017 |
Mechan | +0.017 |
Neg logit contributions | |
una | -0.017 |
Mia | -0.017 |
eh | -0.016 |
sheet | -0.014 |
Luna | -0.014 |
Token | tastes |
Token ID | 18221 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
una | +0.006 |
eh | +0.005 |
Mia | +0.005 |
ches | +0.005 |
sheet | +0.005 |
Neg logit contributions | |
bike | -0.010 |
disl | -0.009 |
spe | -0.009 |
gol | -0.008 |
Mad | -0.008 |
Token | y |
Token ID | 331 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
una | +0.034 |
eh | +0.033 |
Mia | +0.031 |
sheet | +0.029 |
inda | +0.028 |
Neg logit contributions | |
bike | -0.036 |
spe | -0.031 |
disl | -0.030 |
Mechan | -0.026 |
gol | -0.026 |
Token | ucky |
Token ID | 5309 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
eh | +0.062 |
una | +0.060 |
Mia | +0.056 |
sheet | +0.056 |
inda | +0.056 |
Neg logit contributions | |
bike | -0.054 |
disl | -0.047 |
spe | -0.044 |
gol | -0.040 |
self | -0.040 |
Token | ." |
Token ID | 526 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
una | +0.154 |
eh | +0.150 |
Mia | +0.139 |
sheet | +0.133 |
inda | +0.129 |
Neg logit contributions | |
bike | -0.164 |
disl | -0.143 |
spe | -0.142 |
gol | -0.119 |
Mechan | -0.119 |
Token | |
Token ID | 220 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
sheet | +0.023 |
ori | +0.023 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.022 |
disl | -0.018 |
spe | -0.017 |
Mechan | -0.014 |
Acc | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
self | +0.002 |
Acc | +0.002 |
Neg logit contributions | |
eh | -0.004 |
una | -0.004 |
sheet | -0.004 |
enzie | -0.004 |
inda | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
una | +0.013 |
eh | +0.012 |
sheet | +0.012 |
inda | +0.011 |
ori | +0.011 |
Neg logit contributions | |
bike | -0.009 |
spe | -0.007 |
disl | -0.007 |
self | -0.006 |
Mechan | -0.005 |
Token | His |
Token ID | 6653 |
Feature activation | +6.36e-03 |
Pos logit contributions | |
una | +0.011 |
eh | +0.011 |
Mia | +0.010 |
sheet | +0.010 |
inda | +0.009 |
Neg logit contributions | |
bike | -0.013 |
disl | -0.011 |
spe | -0.011 |
gol | -0.009 |
Mechan | -0.009 |
Token | fairy |
Token ID | 25607 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.014 |
sheet | +0.013 |
inda | +0.012 |
Neg logit contributions | |
bike | -0.022 |
disl | -0.019 |
spe | -0.019 |
gol | -0.017 |
Mechan | -0.017 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
una | +0.032 |
eh | +0.031 |
Mia | +0.029 |
sheet | +0.027 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.040 |
disl | -0.036 |
spe | -0.035 |
gol | -0.030 |
Mechan | -0.030 |
Token | onto |
Token ID | 4291 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
una | +0.016 |
eh | +0.015 |
Mia | +0.014 |
sheet | +0.014 |
inda | +0.012 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.030 |
spe | -0.028 |
Mechan | -0.026 |
gol | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
una | +0.041 |
eh | +0.040 |
Mia | +0.036 |
sheet | +0.034 |
inda | +0.033 |
Neg logit contributions | |
bike | -0.067 |
disl | -0.060 |
spe | -0.060 |
gol | -0.052 |
Mechan | -0.052 |
Token | l |
Token ID | 300 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
una | +0.039 |
eh | +0.038 |
Mia | +0.035 |
sheet | +0.033 |
inda | +0.031 |
Neg logit contributions | |
bike | -0.052 |
spe | -0.046 |
disl | -0.046 |
Mechan | -0.040 |
gol | -0.039 |
Token | ily |
Token ID | 813 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
spaghetti | +0.052 |
sheet | +0.048 |
Amy | +0.045 |
Lisa | +0.045 |
Mia | +0.045 |
Neg logit contributions | |
qu | -0.099 |
bike | -0.099 |
gol | -0.097 |
hy | -0.096 |
disl | -0.095 |
Token | pad |
Token ID | 14841 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
una | +0.130 |
eh | +0.125 |
Mia | +0.115 |
sheet | +0.107 |
inda | +0.106 |
Neg logit contributions | |
bike | -0.175 |
spe | -0.154 |
disl | -0.153 |
gol | -0.131 |
self | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -6.96e-03 |
Pos logit contributions | |
una | +0.106 |
eh | +0.102 |
Mia | +0.096 |
sheet | +0.089 |
ori | +0.089 |
Neg logit contributions | |
bike | -0.107 |
spe | -0.093 |
disl | -0.090 |
self | -0.077 |
gol | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
una | +0.011 |
eh | +0.011 |
Mia | +0.011 |
sheet | +0.010 |
inda | +0.009 |
Neg logit contributions | |
bike | -0.015 |
disl | -0.013 |
spe | -0.013 |
Mechan | -0.012 |
gol | -0.011 |
Token | pond |
Token ID | 16723 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.004 |
sheet | +0.004 |
Molly | +0.003 |
Neg logit contributions | |
bike | -0.006 |
spe | -0.006 |
disl | -0.005 |
Mechan | -0.005 |
gol | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
una | +0.009 |
eh | +0.009 |
Mia | +0.008 |
sheet | +0.008 |
inda | +0.007 |
Neg logit contributions | |
bike | -0.013 |
disl | -0.011 |
spe | -0.011 |
Mechan | -0.010 |
gol | -0.010 |
Token | garden |
Token ID | 11376 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
bike | +0.010 |
spe | +0.009 |
disl | +0.009 |
qu | +0.008 |
Mechan | +0.008 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
Mia | -0.005 |
sheet | -0.005 |
Luna | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.016 |
spe | +0.015 |
Mechan | +0.014 |
gol | +0.014 |
Neg logit contributions | |
una | -0.012 |
eh | -0.012 |
Mia | -0.011 |
sheet | -0.011 |
inda | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
bike | +0.016 |
disl | +0.014 |
spe | +0.014 |
Mechan | +0.012 |
gol | +0.012 |
Neg logit contributions | |
una | -0.014 |
eh | -0.014 |
Mia | -0.013 |
sheet | -0.012 |
inda | -0.012 |
Token | smelled |
Token ID | 37609 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.003 |
sheet | +0.003 |
ori | +0.003 |
Neg logit contributions | |
bike | -0.003 |
spe | -0.003 |
disl | -0.003 |
Mechan | -0.002 |
self | -0.002 |
Token | y |
Token ID | 331 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
una | +0.041 |
eh | +0.041 |
Mia | +0.037 |
inda | +0.036 |
sheet | +0.036 |
Neg logit contributions | |
bike | -0.035 |
disl | -0.031 |
spe | -0.030 |
gol | -0.025 |
Mechan | -0.025 |
Token | ucky |
Token ID | 5309 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
una | +0.043 |
eh | +0.043 |
Mia | +0.039 |
sheet | +0.037 |
inda | +0.036 |
Neg logit contributions | |
bike | -0.051 |
disl | -0.045 |
spe | -0.044 |
gol | -0.038 |
Mechan | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
una | +0.136 |
eh | +0.130 |
Mia | +0.121 |
sheet | +0.117 |
inda | +0.108 |
Neg logit contributions | |
bike | -0.176 |
disl | -0.157 |
spe | -0.156 |
Mechan | -0.135 |
gol | -0.135 |
Token | they |
Token ID | 484 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
una | +0.025 |
eh | +0.025 |
Mia | +0.024 |
sheet | +0.022 |
inda | +0.021 |
Neg logit contributions | |
bike | -0.033 |
spe | -0.029 |
disl | -0.029 |
gol | -0.025 |
Mechan | -0.025 |
Token | did |
Token ID | 750 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.015 |
sheet | +0.014 |
inda | +0.014 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.015 |
spe | -0.014 |
gol | -0.013 |
Mechan | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
una | +0.025 |
eh | +0.024 |
Mia | +0.023 |
sheet | +0.021 |
ori | +0.020 |
Neg logit contributions | |
bike | -0.035 |
spe | -0.031 |
disl | -0.030 |
gol | -0.028 |
Mechan | -0.027 |
Token | know |
Token ID | 760 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
gol | +0.002 |
Mechan | +0.002 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
inda | -0.003 |
Token | medicine |
Token ID | 9007 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
una | +0.037 |
eh | +0.036 |
enzie | +0.031 |
inda | +0.031 |
Mia | +0.031 |
Neg logit contributions | |
bike | -0.047 |
disl | -0.043 |
spe | -0.041 |
self | -0.037 |
Acc | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.003 |
spe | -0.003 |
gol | -0.003 |
Mechan | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
gol | +0.002 |
Mechan | +0.002 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
Molly | -0.002 |
Token | tasted |
Token ID | 29187 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
una | +0.006 |
eh | +0.005 |
Mia | +0.005 |
sheet | +0.005 |
inda | +0.005 |
Neg logit contributions | |
bike | -0.005 |
disl | -0.005 |
spe | -0.005 |
Mechan | -0.004 |
gol | -0.004 |
Token | y |
Token ID | 331 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
una | +0.065 |
eh | +0.064 |
Mia | +0.059 |
sheet | +0.057 |
inda | +0.057 |
Neg logit contributions | |
bike | -0.053 |
disl | -0.047 |
spe | -0.045 |
self | -0.038 |
Mechan | -0.037 |
Token | ucky |
Token ID | 5309 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
eh | +0.056 |
una | +0.055 |
Mia | +0.051 |
sheet | +0.050 |
inda | +0.049 |
Neg logit contributions | |
bike | -0.054 |
disl | -0.049 |
spe | -0.046 |
self | -0.040 |
gol | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
una | +0.142 |
eh | +0.137 |
Mia | +0.127 |
sheet | +0.121 |
inda | +0.117 |
Neg logit contributions | |
bike | -0.167 |
disl | -0.147 |
spe | -0.146 |
gol | -0.125 |
Mechan | -0.125 |
Token | But |
Token ID | 887 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.004 |
sheet | +0.004 |
Molly | +0.004 |
Neg logit contributions | |
bike | -0.007 |
spe | -0.006 |
disl | -0.006 |
Mechan | -0.005 |
gol | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
una | +0.009 |
eh | +0.009 |
Mia | +0.008 |
sheet | +0.008 |
inda | +0.007 |
Neg logit contributions | |
bike | -0.014 |
disl | -0.013 |
spe | -0.013 |
gol | -0.011 |
Mechan | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
una | +0.013 |
eh | +0.013 |
Mia | +0.012 |
sheet | +0.012 |
inda | +0.012 |
Neg logit contributions | |
bike | -0.011 |
spe | -0.009 |
disl | -0.009 |
self | -0.007 |
Mechan | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
eh | +0.043 |
una | +0.042 |
enzie | +0.034 |
inda | +0.033 |
Mia | +0.033 |
Neg logit contributions | |
bike | -0.075 |
disl | -0.069 |
spe | -0.067 |
self | -0.060 |
Mechan | -0.060 |
Token | each |
Token ID | 1123 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.007 |
spe | +0.007 |
Mechan | +0.006 |
gol | +0.006 |
Neg logit contributions | |
una | -0.007 |
eh | -0.007 |
Mia | -0.007 |
sheet | -0.006 |
inda | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
una | +0.008 |
eh | +0.007 |
Luna | +0.007 |
sheet | +0.007 |
ori | +0.007 |
Neg logit contributions | |
bike | -0.009 |
spe | -0.008 |
gol | -0.007 |
disl | -0.007 |
judge | -0.007 |
Token | took |
Token ID | 1718 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
una | +0.010 |
eh | +0.009 |
Mia | +0.008 |
sheet | +0.008 |
ori | +0.008 |
Neg logit contributions | |
bike | -0.010 |
spe | -0.009 |
disl | -0.008 |
gol | -0.007 |
Mechan | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
una | +0.034 |
eh | +0.033 |
Mia | +0.029 |
sheet | +0.028 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.062 |
disl | -0.056 |
spe | -0.055 |
gol | -0.049 |
Mechan | -0.048 |
Token | l |
Token ID | 300 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
una | +0.037 |
eh | +0.035 |
Mia | +0.032 |
inda | +0.031 |
ori | +0.030 |
Neg logit contributions | |
bike | -0.043 |
spe | -0.038 |
disl | -0.037 |
gol | -0.033 |
Mechan | -0.033 |
Token | ily |
Token ID | 813 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
sheet | +0.069 |
spaghetti | +0.066 |
eh | +0.062 |
hay | +0.062 |
Luna | +0.061 |
Neg logit contributions | |
gol | -0.091 |
bike | -0.089 |
self | -0.086 |
winners | -0.086 |
aring | -0.085 |
Token | pad |
Token ID | 14841 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
una | +0.122 |
eh | +0.117 |
Mia | +0.108 |
sheet | +0.101 |
inda | +0.098 |
Neg logit contributions | |
bike | -0.183 |
spe | -0.162 |
disl | -0.161 |
gol | -0.140 |
Mechan | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
una | +0.106 |
eh | +0.102 |
Mia | +0.095 |
sheet | +0.090 |
inda | +0.088 |
Neg logit contributions | |
bike | -0.115 |
spe | -0.100 |
disl | -0.097 |
gol | -0.085 |
self | -0.083 |
Token | But |
Token ID | 887 |
Feature activation | -9.26e-03 |
Pos logit contributions | |
una | +0.008 |
eh | +0.007 |
Mia | +0.007 |
sheet | +0.007 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.007 |
spe | -0.007 |
gol | -0.006 |
Mechan | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
una | +0.014 |
eh | +0.014 |
Mia | +0.014 |
sheet | +0.012 |
Molly | +0.012 |
Neg logit contributions | |
bike | -0.020 |
disl | -0.018 |
spe | -0.018 |
Mechan | -0.016 |
gol | -0.015 |
Token | when |
Token ID | 618 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
una | +0.007 |
eh | +0.007 |
Mia | +0.007 |
sheet | +0.006 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.012 |
disl | -0.011 |
spe | -0.011 |
Mechan | -0.010 |
gol | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
Mia | +0.011 |
una | +0.010 |
Molly | +0.009 |
ily | +0.009 |
eh | +0.009 |
Neg logit contributions | |
bike | -0.018 |
spe | -0.016 |
disl | -0.015 |
Mechan | -0.014 |
benefit | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
Mia | +0.010 |
una | +0.009 |
Luna | +0.008 |
Molly | +0.008 |
eh | +0.008 |
Neg logit contributions | |
bike | -0.025 |
spe | -0.024 |
disl | -0.023 |
gol | -0.020 |
benefit | -0.020 |
Token | It |
Token ID | 1026 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
bike | +0.091 |
disl | +0.083 |
spe | +0.080 |
Mechan | +0.070 |
ishly | +0.068 |
Neg logit contributions | |
una | -0.086 |
eh | -0.081 |
Mia | -0.076 |
ori | -0.072 |
inda | -0.071 |
Token | looks |
Token ID | 3073 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
una | +0.016 |
Mia | +0.015 |
eh | +0.014 |
ches | +0.013 |
sheet | +0.013 |
Neg logit contributions | |
bike | -0.028 |
spe | -0.025 |
disl | -0.025 |
gol | -0.023 |
Mad | -0.022 |
Token | y |
Token ID | 331 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
bike | +0.011 |
spe | +0.009 |
disl | +0.009 |
Mechan | +0.008 |
gol | +0.008 |
Neg logit contributions | |
una | -0.010 |
eh | -0.010 |
Mia | -0.010 |
sheet | -0.009 |
inda | -0.009 |
Token | ucky |
Token ID | 5309 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
una | +0.027 |
eh | +0.027 |
Mia | +0.024 |
sheet | +0.023 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.030 |
disl | -0.026 |
spe | -0.026 |
gol | -0.023 |
self | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
una | +0.144 |
eh | +0.140 |
Mia | +0.130 |
sheet | +0.124 |
inda | +0.121 |
Neg logit contributions | |
bike | -0.160 |
disl | -0.141 |
spe | -0.139 |
gol | -0.118 |
Mechan | -0.117 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
bike | +0.004 |
spe | +0.004 |
disl | +0.004 |
gol | +0.003 |
Mechan | +0.003 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
inda | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
una | +0.040 |
eh | +0.039 |
Mia | +0.036 |
sheet | +0.034 |
inda | +0.033 |
Neg logit contributions | |
bike | -0.049 |
disl | -0.043 |
spe | -0.043 |
Mechan | -0.037 |
gol | -0.037 |
Token | find |
Token ID | 1064 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
bike | +0.021 |
spe | +0.019 |
disl | +0.019 |
Mechan | +0.017 |
gol | +0.016 |
Neg logit contributions | |
una | -0.017 |
eh | -0.017 |
Mia | -0.017 |
sheet | -0.015 |
Molly | -0.015 |
Token | another |
Token ID | 1194 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
eh | +0.031 |
una | +0.030 |
enzie | +0.027 |
ori | +0.027 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.035 |
disl | -0.033 |
spe | -0.028 |
rh | -0.026 |
self | -0.026 |
Token | that |
Token ID | 326 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
una | +0.032 |
eh | +0.030 |
Mia | +0.027 |
inda | +0.027 |
ori | +0.027 |
Neg logit contributions | |
bike | -0.038 |
spe | -0.033 |
disl | -0.031 |
gol | -0.029 |
bell | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
una | +0.032 |
eh | +0.032 |
Mia | +0.028 |
sheet | +0.027 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.031 |
spe | -0.027 |
disl | -0.027 |
Mechan | -0.022 |
gol | -0.022 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
una | +0.045 |
eh | +0.044 |
Mia | +0.038 |
inda | +0.038 |
enzie | +0.038 |
Neg logit contributions | |
bike | -0.041 |
spe | -0.036 |
disl | -0.035 |
wishing | -0.031 |
ringing | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
una | +0.031 |
eh | +0.030 |
Mia | +0.028 |
sheet | +0.027 |
inda | +0.025 |
Neg logit contributions | |
bike | -0.036 |
disl | -0.032 |
spe | -0.031 |
Mechan | -0.027 |
gol | -0.026 |
Token | boun |
Token ID | 31283 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
una | +0.061 |
eh | +0.059 |
Mia | +0.055 |
sheet | +0.052 |
inda | +0.051 |
Neg logit contributions | |
bike | -0.061 |
disl | -0.053 |
spe | -0.052 |
gol | -0.044 |
Mechan | -0.044 |
Token | cy |
Token ID | 948 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
una | +0.074 |
eh | +0.071 |
Mia | +0.065 |
Luna | +0.064 |
sheet | +0.063 |
Neg logit contributions | |
bike | -0.048 |
spe | -0.037 |
disl | -0.035 |
gol | -0.033 |
self | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
una | +0.136 |
eh | +0.132 |
Mia | +0.122 |
sheet | +0.117 |
inda | +0.112 |
Neg logit contributions | |
bike | -0.167 |
disl | -0.149 |
spe | -0.146 |
Mechan | -0.126 |
gol | -0.125 |
Token | They |
Token ID | 1119 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
una | +0.029 |
eh | +0.029 |
sheet | +0.025 |
inda | +0.024 |
ori | +0.024 |
Neg logit contributions | |
bike | -0.026 |
disl | -0.025 |
spe | -0.023 |
gol | -0.022 |
Sorry | -0.021 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
Mia | +0.042 |
una | +0.042 |
eh | +0.041 |
sheet | +0.039 |
inda | +0.038 |
Neg logit contributions | |
bike | -0.045 |
disl | -0.041 |
spe | -0.038 |
Mechan | -0.034 |
gol | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
una | +0.040 |
eh | +0.038 |
sheet | +0.033 |
inda | +0.033 |
Mia | +0.032 |
Neg logit contributions | |
bike | -0.044 |
spe | -0.038 |
disl | -0.037 |
gol | -0.033 |
self | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | -2.94e-04 |
Pos logit contributions | |
eh | +0.029 |
una | +0.029 |
inda | +0.024 |
enzie | +0.023 |
ori | +0.023 |
Neg logit contributions | |
bike | -0.026 |
disl | -0.023 |
spe | -0.021 |
worry | -0.019 |
miss | -0.019 |
Token | red |
Token ID | 2266 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
una | +0.020 |
eh | +0.020 |
inda | +0.018 |
enzie | +0.018 |
ori | +0.018 |
Neg logit contributions | |
bike | -0.014 |
spe | -0.011 |
disl | -0.011 |
wishing | -0.010 |
rh | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
una | +0.060 |
eh | +0.059 |
Mia | +0.054 |
inda | +0.052 |
sheet | +0.051 |
Neg logit contributions | |
bike | -0.061 |
spe | -0.051 |
disl | -0.051 |
gol | -0.043 |
Mechan | -0.043 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
una | +0.055 |
eh | +0.054 |
Mia | +0.049 |
sheet | +0.047 |
inda | +0.046 |
Neg logit contributions | |
bike | -0.061 |
disl | -0.054 |
spe | -0.053 |
gol | -0.045 |
Mechan | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
una | +0.023 |
eh | +0.021 |
Mia | +0.021 |
sheet | +0.020 |
spaghetti | +0.018 |
Neg logit contributions | |
bike | -0.035 |
disl | -0.033 |
spe | -0.032 |
Mechan | -0.028 |
gol | -0.028 |
Token | boun |
Token ID | 31283 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
una | +0.045 |
eh | +0.044 |
Mia | +0.041 |
sheet | +0.039 |
inda | +0.038 |
Neg logit contributions | |
bike | -0.050 |
disl | -0.044 |
spe | -0.043 |
gol | -0.037 |
Mechan | -0.037 |
Token | cy |
Token ID | 948 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
una | +0.059 |
eh | +0.058 |
Mia | +0.052 |
sheet | +0.051 |
inda | +0.051 |
Neg logit contributions | |
bike | -0.038 |
spe | -0.029 |
disl | -0.029 |
gol | -0.026 |
self | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
una | +0.142 |
eh | +0.138 |
Mia | +0.127 |
sheet | +0.122 |
inda | +0.119 |
Neg logit contributions | |
bike | -0.161 |
disl | -0.142 |
spe | -0.140 |
gol | -0.119 |
Mechan | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
una | +0.024 |
eh | +0.024 |
inda | +0.022 |
sheet | +0.022 |
enzie | +0.021 |
Neg logit contributions | |
bike | -0.017 |
disl | -0.015 |
spe | -0.014 |
gol | -0.013 |
Sorry | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
eh | +0.017 |
una | +0.017 |
inda | +0.016 |
sheet | +0.016 |
enzie | +0.016 |
Neg logit contributions | |
bike | -0.006 |
spe | -0.005 |
disl | -0.005 |
qu | -0.004 |
Mad | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
sheet | +0.003 |
Mia | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.003 |
spe | -0.003 |
disl | -0.003 |
gol | -0.002 |
self | -0.002 |
Token | Wow |
Token ID | 22017 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
bike | +0.032 |
spe | +0.027 |
disl | +0.026 |
gol | +0.022 |
Mechan | +0.022 |
Neg logit contributions | |
una | -0.040 |
eh | -0.039 |
Mia | -0.036 |
sheet | -0.035 |
inda | -0.035 |
Token | think |
Token ID | 892 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
una | +0.028 |
eh | +0.028 |
sheet | +0.025 |
Mia | +0.025 |
Luna | +0.025 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.015 |
spe | -0.013 |
miss | -0.011 |
gol | -0.011 |
Token | we |
Token ID | 356 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
una | +0.006 |
eh | +0.006 |
Mia | +0.005 |
sheet | +0.005 |
inda | +0.005 |
Neg logit contributions | |
bike | -0.008 |
disl | -0.007 |
spe | -0.007 |
gol | -0.006 |
Mechan | -0.006 |
Token | can |
Token ID | 460 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
una | +0.038 |
Mia | +0.036 |
eh | +0.036 |
sheet | +0.034 |
inda | +0.032 |
Neg logit contributions | |
bike | -0.052 |
spe | -0.047 |
disl | -0.045 |
gol | -0.039 |
Mechan | -0.039 |
Token | find |
Token ID | 1064 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
una | +0.020 |
eh | +0.019 |
Mia | +0.018 |
sheet | +0.018 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.023 |
spe | -0.022 |
disl | -0.021 |
gol | -0.018 |
Mechan | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
eh | +0.036 |
una | +0.036 |
Mia | +0.030 |
inda | +0.030 |
ori | +0.029 |
Neg logit contributions | |
bike | -0.049 |
disl | -0.045 |
spe | -0.042 |
gol | -0.038 |
bell | -0.038 |
Token | end |
Token ID | 886 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
sheet | +0.025 |
una | +0.024 |
Mia | +0.024 |
eh | +0.022 |
page | +0.021 |
Neg logit contributions | |
bike | -0.054 |
disl | -0.047 |
spe | -0.046 |
Mechan | -0.041 |
ishly | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
eh | +0.145 |
una | +0.143 |
ori | +0.133 |
inda | +0.127 |
Milo | +0.122 |
Neg logit contributions | |
bike | -0.127 |
spe | -0.122 |
work | -0.111 |
qu | -0.108 |
Helic | -0.107 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
una | +0.041 |
eh | +0.039 |
Mia | +0.036 |
sheet | +0.034 |
inda | +0.033 |
Neg logit contributions | |
bike | -0.062 |
disl | -0.055 |
spe | -0.055 |
gol | -0.048 |
Mechan | -0.048 |
Token | rainbow |
Token ID | 27223 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
sheet | +0.017 |
Mia | +0.017 |
una | +0.017 |
eh | +0.017 |
page | +0.015 |
Neg logit contributions | |
bike | -0.037 |
disl | -0.031 |
spe | -0.031 |
ishly | -0.029 |
Mechan | -0.029 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
una | +0.038 |
eh | +0.036 |
Mia | +0.033 |
sheet | +0.031 |
inda | +0.030 |
Neg logit contributions | |
bike | -0.054 |
disl | -0.048 |
spe | -0.047 |
gol | -0.041 |
Mechan | -0.041 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
sheet | +0.023 |
ori | +0.022 |
ches | +0.022 |
Neg logit contributions | |
bike | -0.038 |
disl | -0.037 |
spe | -0.034 |
gol | -0.033 |
Sorry | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
una | +0.021 |
eh | +0.021 |
Mia | +0.021 |
sheet | +0.018 |
spaghetti | +0.018 |
Neg logit contributions | |
bike | -0.040 |
disl | -0.036 |
spe | -0.036 |
Mechan | -0.033 |
gol | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
Mia | +0.004 |
sheet | +0.004 |
inda | +0.004 |
Neg logit contributions | |
bike | -0.005 |
disl | -0.004 |
spe | -0.004 |
gol | -0.004 |
Mechan | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
bike | +0.096 |
spe | +0.083 |
disl | +0.082 |
Mechan | +0.070 |
gol | +0.070 |
Neg logit contributions | |
una | -0.084 |
eh | -0.082 |
Mia | -0.076 |
sheet | -0.071 |
inda | -0.070 |
Token | smells |
Token ID | 25760 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.019 |
Mia | +0.018 |
sheet | +0.016 |
ches | +0.016 |
Neg logit contributions | |
bike | -0.030 |
spe | -0.027 |
disl | -0.026 |
gol | -0.025 |
Mechan | -0.023 |
Token | y |
Token ID | 331 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
una | +0.021 |
eh | +0.020 |
Mia | +0.019 |
sheet | +0.018 |
spaghetti | +0.018 |
Neg logit contributions | |
bike | -0.026 |
spe | -0.022 |
disl | -0.021 |
Mechan | -0.019 |
gol | -0.019 |
Token | ucky |
Token ID | 5309 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
una | +0.041 |
eh | +0.041 |
Mia | +0.037 |
sheet | +0.036 |
inda | +0.035 |
Neg logit contributions | |
bike | -0.041 |
disl | -0.036 |
spe | -0.035 |
gol | -0.030 |
self | -0.030 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
una | +0.130 |
eh | +0.124 |
Mia | +0.114 |
sheet | +0.108 |
inda | +0.101 |
Neg logit contributions | |
bike | -0.177 |
spe | -0.159 |
disl | -0.156 |
Mechan | -0.137 |
gol | -0.135 |
Token | she |
Token ID | 673 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
una | +0.030 |
eh | +0.029 |
ori | +0.025 |
sheet | +0.025 |
inda | +0.025 |
Neg logit contributions | |
bike | -0.028 |
disl | -0.025 |
spe | -0.023 |
gol | -0.020 |
Sorry | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.007 |
spe | +0.006 |
gol | +0.005 |
Mechan | +0.005 |
Neg logit contributions | |
una | -0.009 |
eh | -0.009 |
Mia | -0.008 |
sheet | -0.008 |
ori | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
Mia | +0.017 |
eh | +0.016 |
una | +0.016 |
Molly | +0.014 |
sheet | +0.014 |
Neg logit contributions | |
bike | -0.030 |
disl | -0.027 |
spe | -0.026 |
Mechan | -0.024 |
gol | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
una | +0.017 |
eh | +0.017 |
Mia | +0.016 |
sheet | +0.015 |
inda | +0.014 |
Neg logit contributions | |
bike | -0.020 |
disl | -0.018 |
spe | -0.018 |
Mechan | -0.015 |
gol | -0.015 |
Token | this |
Token ID | 428 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
una | +0.033 |
eh | +0.033 |
inda | +0.029 |
Mia | +0.029 |
ori | +0.029 |
Neg logit contributions | |
bike | -0.038 |
disl | -0.034 |
spe | -0.033 |
gol | -0.028 |
self | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
bike | +0.027 |
disl | +0.024 |
spe | +0.024 |
self | +0.019 |
Mechan | +0.019 |
Neg logit contributions | |
una | -0.022 |
eh | -0.021 |
Mia | -0.019 |
inda | -0.019 |
ori | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
bike | +0.015 |
spe | +0.013 |
disl | +0.013 |
gol | +0.012 |
Mechan | +0.011 |
Neg logit contributions | |
una | -0.012 |
Mia | -0.011 |
eh | -0.011 |
sheet | -0.010 |
Molly | -0.010 |
Token | looks |
Token ID | 3073 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
gol | +0.006 |
Mechan | +0.005 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
Mia | -0.005 |
sheet | -0.004 |
ches | -0.004 |
Token | y |
Token ID | 331 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.003 |
spe | +0.003 |
gol | +0.003 |
Mechan | +0.003 |
Neg logit contributions | |
una | -0.005 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
ori | -0.004 |
Token | ucky |
Token ID | 5309 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
eh | +0.032 |
una | +0.031 |
Mia | +0.029 |
inda | +0.029 |
sheet | +0.028 |
Neg logit contributions | |
bike | -0.024 |
disl | -0.020 |
spe | -0.020 |
self | -0.017 |
gol | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
una | +0.152 |
eh | +0.148 |
Mia | +0.137 |
sheet | +0.131 |
inda | +0.129 |
Neg logit contributions | |
bike | -0.149 |
disl | -0.129 |
spe | -0.128 |
gol | -0.106 |
Mechan | -0.106 |
Token | dry |
Token ID | 5894 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
una | +0.025 |
eh | +0.024 |
Mia | +0.023 |
sheet | +0.022 |
inda | +0.021 |
Neg logit contributions | |
bike | -0.029 |
spe | -0.025 |
disl | -0.025 |
gol | -0.022 |
Mechan | -0.022 |
Token | ," |
Token ID | 553 |
Feature activation | -4.84e-03 |
Pos logit contributions | |
una | +0.014 |
eh | +0.013 |
Mia | +0.012 |
sheet | +0.012 |
Molly | +0.011 |
Neg logit contributions | |
bike | -0.015 |
disl | -0.013 |
spe | -0.013 |
Mechan | -0.011 |
gol | -0.011 |
Token | Tommy |
Token ID | 19919 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
Mia | +0.006 |
una | +0.006 |
eh | +0.006 |
Molly | +0.005 |
ily | +0.005 |
Neg logit contributions | |
bike | -0.012 |
spe | -0.011 |
disl | -0.011 |
Mechan | -0.010 |
gol | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
bike | +0.013 |
disl | +0.011 |
spe | +0.011 |
gol | +0.009 |
Mechan | +0.009 |
Neg logit contributions | |
una | -0.014 |
eh | -0.014 |
Mia | -0.013 |
sheet | -0.013 |
inda | -0.012 |
Token | Emma |
Token ID | 18966 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
Mia | +0.003 |
una | +0.003 |
eh | +0.003 |
Molly | +0.003 |
sheet | +0.003 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.006 |
spe | -0.006 |
gol | -0.005 |
Mechan | -0.005 |
Token | could |
Token ID | 714 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
bike | +0.012 |
disl | +0.012 |
spe | +0.010 |
gol | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
eh | -0.007 |
una | -0.006 |
Mia | -0.006 |
sheet | -0.006 |
inda | -0.006 |
Token | hear |
Token ID | 3285 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
una | +0.018 |
eh | +0.018 |
Mia | +0.017 |
sheet | +0.016 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.022 |
disl | -0.019 |
spe | -0.019 |
gol | -0.016 |
Mechan | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
bike | +0.018 |
disl | +0.016 |
spe | +0.016 |
Mechan | +0.015 |
gol | +0.015 |
Neg logit contributions | |
una | -0.009 |
Mia | -0.008 |
eh | -0.008 |
sheet | -0.007 |
Molly | -0.007 |
Token | wh |
Token ID | 348 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
bike | +0.012 |
disl | +0.011 |
spe | +0.010 |
gol | +0.009 |
Mechan | +0.009 |
Neg logit contributions | |
sheet | -0.008 |
una | -0.008 |
Mia | -0.008 |
eh | -0.008 |
page | -0.008 |
Token | inn |
Token ID | 3732 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
bike | +0.023 |
spe | +0.020 |
disl | +0.020 |
gol | +0.017 |
Mechan | +0.017 |
Neg logit contributions | |
una | -0.020 |
eh | -0.019 |
Mia | -0.018 |
sheet | -0.017 |
Luna | -0.017 |
Token | ying |
Token ID | 1112 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
una | +0.127 |
eh | +0.126 |
Mia | +0.114 |
sheet | +0.107 |
Luna | +0.102 |
Neg logit contributions | |
bike | -0.172 |
spe | -0.154 |
disl | -0.149 |
Mechan | -0.127 |
self | -0.126 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
bike | +0.058 |
disl | +0.055 |
spe | +0.051 |
Mechan | +0.047 |
gol | +0.047 |
Neg logit contributions | |
una | -0.033 |
eh | -0.031 |
Mia | -0.031 |
sheet | -0.030 |
inda | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.003 |
spe | +0.003 |
Mechan | +0.003 |
gol | +0.003 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
inda | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
una | +0.006 |
eh | +0.005 |
Mia | +0.005 |
sheet | +0.005 |
inda | +0.005 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.006 |
spe | -0.006 |
gol | -0.005 |
Mechan | -0.005 |
Token | stepped |
Token ID | 10764 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
Mia | +0.006 |
una | +0.006 |
eh | +0.006 |
inda | +0.006 |
sheet | +0.005 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.007 |
gol | -0.007 |
Sorry | -0.007 |
Token | can |
Token ID | 460 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
una | +0.014 |
Mia | +0.013 |
eh | +0.013 |
sheet | +0.012 |
Molly | +0.012 |
Neg logit contributions | |
bike | -0.019 |
spe | -0.016 |
disl | -0.016 |
Mechan | -0.014 |
gol | -0.014 |
Token | I |
Token ID | 314 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
una | +0.037 |
eh | +0.035 |
Mia | +0.035 |
sheet | +0.032 |
Luna | +0.031 |
Neg logit contributions | |
bike | -0.041 |
spe | -0.037 |
disl | -0.037 |
gol | -0.031 |
Mechan | -0.031 |
Token | steal |
Token ID | 8711 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
una | +0.062 |
eh | +0.062 |
Mia | +0.060 |
sheet | +0.054 |
inda | +0.054 |
Neg logit contributions | |
bike | -0.077 |
spe | -0.069 |
disl | -0.067 |
Mechan | -0.059 |
gol | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.019 |
Mia | +0.016 |
sheet | +0.016 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.030 |
disl | -0.027 |
spe | -0.026 |
gol | -0.023 |
self | -0.023 |
Token | l |
Token ID | 300 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.025 |
sheet | +0.024 |
inda | +0.024 |
Neg logit contributions | |
bike | -0.030 |
disl | -0.026 |
spe | -0.026 |
gol | -0.022 |
Mechan | -0.022 |
Token | ily |
Token ID | 813 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
sheet | +0.053 |
spaghetti | +0.049 |
Rachel | +0.047 |
eh | +0.046 |
Mia | +0.045 |
Neg logit contributions | |
bike | -0.096 |
gol | -0.094 |
qu | -0.092 |
self | -0.089 |
hy | -0.089 |
Token | ? |
Token ID | 30 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
una | +0.139 |
eh | +0.133 |
sheet | +0.122 |
Mia | +0.122 |
inda | +0.120 |
Neg logit contributions | |
bike | -0.150 |
disl | -0.130 |
spe | -0.128 |
self | -0.110 |
gol | -0.108 |
Token | Please |
Token ID | 4222 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
una | +0.005 |
Mia | +0.005 |
eh | +0.005 |
Molly | +0.005 |
Luna | +0.005 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.006 |
spe | -0.006 |
Mechan | -0.005 |
gol | -0.005 |
Token | ? |
Token ID | 30 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
una | +0.012 |
Mia | +0.012 |
eh | +0.011 |
Molly | +0.011 |
sheet | +0.010 |
Neg logit contributions | |
bike | -0.016 |
spe | -0.015 |
disl | -0.014 |
Mechan | -0.012 |
gol | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.002 |
Luna | +0.002 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
Mechan | -0.002 |
gol | -0.002 |
Token | € |
Token ID | 26391 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
una | +0.006 |
eh | +0.006 |
Mia | +0.006 |
inda | +0.005 |
sheet | +0.005 |
Neg logit contributions | |
bike | -0.007 |
spe | -0.007 |
disl | -0.006 |
Mechan | -0.006 |
gol | -0.005 |
Token | together |
Token ID | 1978 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bike | +0.025 |
disl | +0.022 |
spe | +0.022 |
gol | +0.019 |
Mechan | +0.019 |
Neg logit contributions | |
una | -0.020 |
eh | -0.019 |
Mia | -0.018 |
sheet | -0.017 |
inda | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
una | +0.022 |
eh | +0.021 |
Mia | +0.020 |
sheet | +0.019 |
inda | +0.018 |
Neg logit contributions | |
bike | -0.029 |
disl | -0.026 |
spe | -0.025 |
Mechan | -0.022 |
gol | -0.022 |
Token | It |
Token ID | 632 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
bike | +0.004 |
disl | +0.003 |
spe | +0.003 |
gol | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
eh | -0.007 |
una | -0.007 |
inda | -0.006 |
sheet | -0.006 |
ches | -0.006 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.014 |
spe | +0.014 |
Mechan | +0.012 |
self | +0.012 |
Neg logit contributions | |
una | -0.018 |
eh | -0.017 |
Mia | -0.016 |
sheet | -0.015 |
inda | -0.015 |
Token | y |
Token ID | 331 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
una | +0.004 |
eh | +0.004 |
ori | +0.003 |
Mia | +0.003 |
enzie | +0.003 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
self | -0.002 |
wishing | -0.002 |
Token | ucky |
Token ID | 5309 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
eh | +0.027 |
una | +0.026 |
Mia | +0.024 |
sheet | +0.023 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.018 |
spe | -0.018 |
self | -0.015 |
qu | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
una | +0.134 |
eh | +0.130 |
Mia | +0.120 |
sheet | +0.115 |
inda | +0.111 |
Neg logit contributions | |
bike | -0.167 |
disl | -0.148 |
spe | -0.146 |
gol | -0.125 |
Mechan | -0.125 |
Token | smells |
Token ID | 25760 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
Mia | +0.025 |
sheet | +0.023 |
inda | +0.022 |
Neg logit contributions | |
bike | -0.031 |
spe | -0.027 |
disl | -0.027 |
gol | -0.023 |
Mechan | -0.023 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
Mechan | -0.002 |
gol | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
una | +0.010 |
eh | +0.010 |
Mia | +0.009 |
sheet | +0.009 |
inda | +0.008 |
Neg logit contributions | |
bike | -0.014 |
disl | -0.012 |
spe | -0.012 |
Mechan | -0.010 |
gol | -0.010 |
Token | But |
Token ID | 887 |
Feature activation | +9.91e-04 |
Pos logit contributions | |
eh | +0.010 |
una | +0.010 |
sheet | +0.009 |
inda | +0.009 |
ches | +0.009 |
Neg logit contributions | |
bike | -0.006 |
disl | -0.005 |
spe | -0.005 |
Sorry | -0.004 |
gol | -0.004 |
Token | red |
Token ID | 2266 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
una | +0.020 |
eh | +0.019 |
inda | +0.018 |
enzie | +0.018 |
ori | +0.017 |
Neg logit contributions | |
bike | -0.012 |
wishing | -0.010 |
rh | -0.009 |
je | -0.009 |
spe | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
eh | +0.062 |
una | +0.062 |
inda | +0.056 |
Mia | +0.056 |
ori | +0.054 |
Neg logit contributions | |
bike | -0.053 |
spe | -0.041 |
disl | -0.040 |
gol | -0.035 |
Mechan | -0.035 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
una | +0.057 |
eh | +0.055 |
Mia | +0.050 |
sheet | +0.048 |
inda | +0.048 |
Neg logit contributions | |
bike | -0.060 |
disl | -0.053 |
spe | -0.052 |
Mechan | -0.044 |
gol | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
una | +0.022 |
eh | +0.020 |
Mia | +0.020 |
sheet | +0.019 |
spaghetti | +0.017 |
Neg logit contributions | |
bike | -0.031 |
disl | -0.028 |
spe | -0.028 |
Mechan | -0.024 |
gol | -0.024 |
Token | boun |
Token ID | 31283 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
una | +0.046 |
eh | +0.045 |
Mia | +0.041 |
sheet | +0.040 |
inda | +0.039 |
Neg logit contributions | |
bike | -0.050 |
disl | -0.043 |
spe | -0.043 |
gol | -0.036 |
Mechan | -0.036 |
Token | cy |
Token ID | 948 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
una | +0.061 |
eh | +0.060 |
sheet | +0.053 |
Mia | +0.053 |
inda | +0.053 |
Neg logit contributions | |
bike | -0.037 |
disl | -0.027 |
spe | -0.027 |
gol | -0.025 |
self | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
una | +0.144 |
eh | +0.141 |
Mia | +0.128 |
sheet | +0.123 |
inda | +0.122 |
Neg logit contributions | |
bike | -0.156 |
disl | -0.136 |
spe | -0.135 |
gol | -0.114 |
Mechan | -0.112 |
Token | They |
Token ID | 1119 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
una | +0.023 |
eh | +0.022 |
Mia | +0.021 |
sheet | +0.020 |
inda | +0.019 |
Neg logit contributions | |
bike | -0.023 |
disl | -0.020 |
spe | -0.020 |
gol | -0.017 |
Mechan | -0.017 |
Token | want |
Token ID | 765 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Mia | +0.037 |
una | +0.036 |
eh | +0.034 |
sheet | +0.034 |
Molly | +0.032 |
Neg logit contributions | |
bike | -0.047 |
spe | -0.043 |
disl | -0.042 |
Mechan | -0.037 |
gol | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
eh | +0.061 |
una | +0.058 |
inda | +0.053 |
enzie | +0.051 |
ori | +0.050 |
Neg logit contributions | |
bike | -0.051 |
disl | -0.044 |
spe | -0.040 |
gol | -0.036 |
Mechan | -0.034 |
Token | play |
Token ID | 711 |
Feature activation | +6.23e-04 |
Pos logit contributions | |
bike | +0.003 |
spe | +0.002 |
disl | +0.002 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
una | -0.003 |
eh | -0.003 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
una | +0.000 |
eh | +0.000 |
Mia | +0.000 |
sheet | +0.000 |
ches | +0.000 |
Neg logit contributions | |
bike | -0.001 |
disl | -0.001 |
spe | -0.001 |
gol | -0.001 |
Mechan | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
una | +0.012 |
eh | +0.012 |
ori | +0.011 |
enzie | +0.011 |
inda | +0.011 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.007 |
rh | -0.007 |
wishing | -0.007 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
una | +0.027 |
eh | +0.027 |
sheet | +0.024 |
Mia | +0.024 |
inda | +0.024 |
Neg logit contributions | |
bike | -0.019 |
disl | -0.018 |
spe | -0.017 |
gol | -0.014 |
self | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
Mia | +0.024 |
sheet | +0.023 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.028 |
disl | -0.025 |
spe | -0.024 |
gol | -0.020 |
Mechan | -0.020 |
Token | boun |
Token ID | 31283 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
una | +0.021 |
Mia | +0.020 |
eh | +0.020 |
sheet | +0.019 |
Luna | +0.018 |
Neg logit contributions | |
bike | -0.025 |
spe | -0.021 |
disl | -0.020 |
Mechan | -0.018 |
gol | -0.018 |
Token | cy |
Token ID | 948 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
una | +0.050 |
eh | +0.050 |
Mia | +0.046 |
sheet | +0.044 |
Luna | +0.044 |
Neg logit contributions | |
bike | -0.036 |
spe | -0.028 |
disl | -0.028 |
gol | -0.026 |
self | -0.025 |
Token | ." |
Token ID | 526 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
una | +0.154 |
eh | +0.151 |
Mia | +0.138 |
inda | +0.133 |
sheet | +0.132 |
Neg logit contributions | |
bike | -0.143 |
disl | -0.123 |
spe | -0.123 |
gol | -0.101 |
self | -0.099 |
Token | The |
Token ID | 383 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
una | +0.020 |
eh | +0.020 |
Mia | +0.017 |
sheet | +0.017 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.038 |
disl | -0.035 |
spe | -0.034 |
gol | -0.030 |
Mechan | -0.030 |
Token | girl |
Token ID | 2576 |
Feature activation | -7.86e-03 |
Pos logit contributions | |
bike | +0.035 |
disl | +0.031 |
spe | +0.031 |
Mechan | +0.026 |
gol | +0.026 |
Neg logit contributions | |
una | -0.033 |
eh | -0.032 |
Mia | -0.030 |
sheet | -0.029 |
inda | -0.028 |
Token | said |
Token ID | 531 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
una | +0.014 |
eh | +0.014 |
Mia | +0.013 |
sheet | +0.012 |
inda | +0.012 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.014 |
spe | -0.014 |
Mechan | -0.012 |
gol | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.026 |
sheet | +0.023 |
Molly | +0.023 |
Neg logit contributions | |
bike | -0.041 |
disl | -0.037 |
spe | -0.036 |
Mechan | -0.032 |
gol | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
bike | +0.036 |
disl | +0.033 |
spe | +0.032 |
Mechan | +0.032 |
gol | +0.030 |
Neg logit contributions | |
Mia | -0.014 |
una | -0.014 |
Molly | -0.012 |
sheet | -0.011 |
Rachel | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -5.85e-05 |
Pos logit contributions | |
bike | +0.010 |
disl | +0.009 |
spe | +0.009 |
gol | +0.008 |
Mechan | +0.008 |
Neg logit contributions | |
una | -0.008 |
eh | -0.008 |
Mia | -0.008 |
sheet | -0.007 |
inda | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
una | +0.000 |
eh | +0.000 |
sheet | +0.000 |
Mia | +0.000 |
ori | +0.000 |
Neg logit contributions | |
bike | -0.000 |
spe | -0.000 |
disl | -0.000 |
wishing | -0.000 |
miss | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
una | +0.041 |
eh | +0.040 |
Mia | +0.036 |
sheet | +0.034 |
inda | +0.034 |
Neg logit contributions | |
bike | -0.049 |
spe | -0.043 |
disl | -0.043 |
Mechan | -0.036 |
gol | -0.036 |
Token | end |
Token ID | 886 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
bike | +0.034 |
spe | +0.031 |
disl | +0.031 |
Mechan | +0.027 |
gol | +0.026 |
Neg logit contributions | |
una | -0.027 |
Mia | -0.025 |
eh | -0.025 |
sheet | -0.024 |
Molly | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
una | +0.026 |
eh | +0.026 |
Mia | +0.023 |
sheet | +0.022 |
inda | +0.021 |
Neg logit contributions | |
bike | -0.037 |
disl | -0.033 |
spe | -0.032 |
gol | -0.028 |
Mechan | -0.028 |
Token | adventure |
Token ID | 8855 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
bike | +0.082 |
disl | +0.074 |
spe | +0.070 |
gol | +0.067 |
Mechan | +0.064 |
Neg logit contributions | |
una | -0.052 |
sheet | -0.051 |
eh | -0.050 |
Mia | -0.050 |
spaghetti | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
bike | +0.078 |
disl | +0.078 |
spe | +0.068 |
Mechan | +0.066 |
gol | +0.064 |
Neg logit contributions | |
una | -0.046 |
Mia | -0.044 |
eh | -0.043 |
sheet | -0.042 |
Molly | -0.039 |
Token | head |
Token ID | 1182 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
bike | +0.029 |
disl | +0.026 |
spe | +0.025 |
Mechan | +0.023 |
gol | +0.022 |
Neg logit contributions | |
Mia | -0.023 |
una | -0.023 |
eh | -0.022 |
sheet | -0.021 |
Molly | -0.021 |
Token | back |
Token ID | 736 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
bike | +0.026 |
disl | +0.025 |
spe | +0.022 |
gol | +0.022 |
Mechan | +0.022 |
Neg logit contributions | |
una | -0.014 |
Mia | -0.013 |
eh | -0.013 |
sheet | -0.012 |
Molly | -0.012 |
Token | home |
Token ID | 1363 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
Mia | +0.003 |
una | +0.003 |
eh | +0.003 |
Molly | +0.003 |
sheet | +0.003 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.007 |
spe | -0.006 |
Mechan | -0.006 |
gol | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
gol | +0.003 |
Mechan | +0.003 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
spaghetti | -0.002 |
Token | Her |
Token ID | 2332 |
Feature activation | +8.47e-04 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
Sorry | +0.002 |
Acc | +0.002 |
Neg logit contributions | |
una | -0.003 |
eh | -0.003 |
inda | -0.003 |
enzie | -0.003 |
sheet | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.001 |
spe | +0.001 |
gol | +0.001 |
Mechan | +0.001 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.001 |
inda | -0.001 |
enzie | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
bike | +0.046 |
disl | +0.042 |
spe | +0.040 |
gol | +0.035 |
Sorry | +0.034 |
Neg logit contributions | |
una | -0.033 |
eh | -0.032 |
Mia | -0.032 |
sheet | -0.029 |
inda | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e-03 |
Pos logit contributions | |
una | +0.023 |
Mia | +0.022 |
eh | +0.022 |
sheet | +0.021 |
Molly | +0.020 |
Neg logit contributions | |
bike | -0.025 |
spe | -0.021 |
disl | -0.021 |
gol | -0.018 |
Mechan | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
una | +0.006 |
Mia | +0.006 |
eh | +0.005 |
Luna | +0.005 |
sheet | +0.005 |
Neg logit contributions | |
bike | -0.013 |
spe | -0.012 |
disl | -0.012 |
gol | -0.011 |
self | -0.010 |
Token | Good |
Token ID | 10248 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
bike | +0.073 |
spe | +0.063 |
disl | +0.062 |
gol | +0.052 |
Mechan | +0.051 |
Neg logit contributions | |
una | -0.094 |
eh | -0.091 |
Mia | -0.086 |
sheet | -0.083 |
inda | -0.080 |
Token | job |
Token ID | 1693 |
Feature activation | -9.70e-04 |
Pos logit contributions | |
bike | +0.052 |
spe | +0.046 |
disl | +0.045 |
Mechan | +0.035 |
self | +0.035 |
Neg logit contributions | |
una | -0.061 |
eh | -0.059 |
Mia | -0.058 |
sheet | -0.055 |
inda | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
una | +0.002 |
Mia | +0.002 |
eh | +0.002 |
sheet | +0.002 |
Molly | +0.002 |
Neg logit contributions | |
bike | -0.002 |
spe | -0.002 |
disl | -0.002 |
gol | -0.001 |
Mechan | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
una | +0.013 |
eh | +0.012 |
Mia | +0.011 |
sheet | +0.010 |
inda | +0.009 |
Neg logit contributions | |
bike | -0.042 |
spe | -0.038 |
disl | -0.037 |
Mechan | -0.034 |
gol | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
una | +0.038 |
eh | +0.036 |
Mia | +0.035 |
sheet | +0.033 |
inda | +0.031 |
Neg logit contributions | |
bike | -0.054 |
spe | -0.048 |
disl | -0.048 |
gol | -0.041 |
Mechan | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
eh | +0.010 |
una | +0.009 |
sheet | +0.009 |
inda | +0.009 |
enzie | +0.008 |
Neg logit contributions | |
bike | -0.005 |
spe | -0.004 |
disl | -0.004 |
gol | -0.003 |
qu | -0.003 |
Token | Tim |
Token ID | 14967 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.002 |
spe | +0.002 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
inda | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | +9.47e-04 |
Pos logit contributions | |
una | +0.033 |
eh | +0.032 |
Mia | +0.030 |
sheet | +0.028 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.044 |
disl | -0.038 |
spe | -0.038 |
Mechan | -0.033 |
gol | -0.033 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
bike | +0.002 |
disl | +0.002 |
spe | +0.002 |
Mechan | +0.002 |
Sorry | +0.002 |
Neg logit contributions | |
eh | -0.001 |
una | -0.001 |
Mia | -0.001 |
sheet | -0.001 |
inda | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
gol | +0.004 |
Mechan | +0.004 |
Neg logit contributions | |
una | -0.006 |
eh | -0.006 |
Mia | -0.005 |
sheet | -0.005 |
inda | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
Mia | +0.005 |
una | +0.005 |
eh | +0.005 |
Molly | +0.005 |
Luna | +0.004 |
Neg logit contributions | |
bike | -0.010 |
spe | -0.010 |
disl | -0.009 |
self | -0.008 |
benefit | -0.008 |
Token | What |
Token ID | 2061 |
Feature activation | +3.77e-04 |
Pos logit contributions | |
bike | +0.097 |
disl | +0.083 |
spe | +0.082 |
gol | +0.069 |
Mechan | +0.069 |
Neg logit contributions | |
una | -0.105 |
eh | -0.102 |
Mia | -0.096 |
sheet | -0.091 |
inda | -0.089 |
Token | is |
Token ID | 318 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
bike | +0.001 |
disl | +0.001 |
spe | +0.001 |
gol | +0.001 |
Mechan | +0.001 |
Neg logit contributions | |
una | -0.001 |
eh | -0.001 |
Mia | -0.001 |
sheet | -0.001 |
inda | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
bike | +0.038 |
disl | +0.033 |
spe | +0.031 |
gol | +0.028 |
Mechan | +0.027 |
Neg logit contributions | |
una | -0.042 |
eh | -0.041 |
Mia | -0.038 |
sheet | -0.036 |
inda | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
una | +0.005 |
eh | +0.005 |
Mia | +0.005 |
sheet | +0.005 |
inda | +0.004 |
Neg logit contributions | |
bike | -0.008 |
spe | -0.007 |
disl | -0.007 |
Mechan | -0.006 |
gol | -0.006 |
Token | Billy |
Token ID | 15890 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
bike | +0.013 |
disl | +0.012 |
spe | +0.012 |
Mechan | +0.010 |
gol | +0.010 |
Neg logit contributions | |
una | -0.013 |
eh | -0.012 |
Mia | -0.012 |
sheet | -0.011 |
inda | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
una | +0.008 |
eh | +0.007 |
Mia | +0.007 |
sheet | +0.007 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.008 |
gol | -0.007 |
Mechan | -0.007 |
Token | quiet |
Token ID | 5897 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
una | +0.029 |
eh | +0.029 |
inda | +0.024 |
ori | +0.024 |
Mia | +0.024 |
Neg logit contributions | |
bike | -0.028 |
spe | -0.025 |
disl | -0.025 |
Mechan | -0.020 |
Sorry | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
bike | +0.033 |
disl | +0.030 |
spe | +0.029 |
gol | +0.026 |
Mechan | +0.026 |
Neg logit contributions | |
una | -0.022 |
Mia | -0.020 |
eh | -0.020 |
sheet | -0.019 |
Molly | -0.017 |
Token | Anna |
Token ID | 11735 |
Feature activation | -6.88e-04 |
Pos logit contributions | |
eh | +0.010 |
una | +0.009 |
inda | +0.009 |
enzie | +0.008 |
ori | +0.008 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.006 |
Sorry | -0.006 |
spe | -0.006 |
Helic | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
una | +0.001 |
eh | +0.001 |
Mia | +0.001 |
sheet | +0.001 |
inda | +0.001 |
Neg logit contributions | |
bike | -0.001 |
disl | -0.001 |
spe | -0.001 |
gol | -0.001 |
Mechan | -0.001 |
Token | Spot |
Token ID | 15899 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
bike | +0.005 |
disl | +0.004 |
spe | +0.004 |
gol | +0.003 |
Mechan | +0.003 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
bike | +0.089 |
spe | +0.085 |
disl | +0.081 |
gol | +0.074 |
Mechan | +0.073 |
Neg logit contributions | |
Mia | -0.057 |
una | -0.057 |
sheet | -0.053 |
Luna | -0.050 |
eh | -0.050 |
Token | not |
Token ID | 407 |
Feature activation | -4.03e-05 |
Pos logit contributions | |
bike | +0.022 |
disl | +0.019 |
spe | +0.018 |
wishing | +0.014 |
gol | +0.014 |
Neg logit contributions | |
una | -0.033 |
eh | -0.032 |
Mia | -0.029 |
inda | -0.029 |
sheet | -0.029 |
Token | afraid |
Token ID | 7787 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
una | +0.000 |
eh | +0.000 |
Mia | +0.000 |
sheet | +0.000 |
inda | +0.000 |
Neg logit contributions | |
bike | -0.000 |
disl | -0.000 |
spe | -0.000 |
Mechan | -0.000 |
gol | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.007 |
spe | +0.007 |
gol | +0.006 |
Mechan | +0.006 |
Neg logit contributions | |
una | -0.006 |
eh | -0.006 |
Mia | -0.005 |
sheet | -0.005 |
inda | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
Sorry | +0.002 |
Helic | +0.002 |
Neg logit contributions | |
eh | -0.005 |
una | -0.005 |
inda | -0.004 |
sheet | -0.004 |
enzie | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.007 |
spe | +0.006 |
Mechan | +0.006 |
gol | +0.006 |
Neg logit contributions | |
una | -0.004 |
Mia | -0.004 |
eh | -0.004 |
sheet | -0.004 |
Luna | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
una | +0.007 |
eh | +0.006 |
Mia | +0.006 |
sheet | +0.006 |
inda | +0.005 |
Neg logit contributions | |
bike | -0.008 |
disl | -0.007 |
spe | -0.007 |
Mechan | -0.006 |
gol | -0.006 |
Token | monster |
Token ID | 9234 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
bike | +0.044 |
disl | +0.039 |
spe | +0.039 |
qu | +0.032 |
Mechan | +0.032 |
Neg logit contributions | |
una | -0.038 |
eh | -0.036 |
Mia | -0.035 |
sheet | -0.034 |
inda | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
bike | +0.052 |
disl | +0.049 |
spe | +0.046 |
Mechan | +0.043 |
gol | +0.042 |
Neg logit contributions | |
una | -0.042 |
Mia | -0.041 |
eh | -0.040 |
sheet | -0.037 |
ia | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Mia | +0.015 |
una | +0.015 |
Molly | +0.013 |
eh | +0.013 |
ily | +0.013 |
Neg logit contributions | |
bike | -0.023 |
disl | -0.021 |
spe | -0.021 |
Mechan | -0.018 |
gol | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
Mia | +0.009 |
una | +0.009 |
eh | +0.007 |
Molly | +0.007 |
Luna | +0.007 |
Neg logit contributions | |
bike | -0.027 |
disl | -0.026 |
spe | -0.026 |
gol | -0.024 |
self | -0.023 |
Token | W |
Token ID | 54 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
bike | +0.088 |
disl | +0.081 |
spe | +0.080 |
Mechan | +0.068 |
wreck | +0.067 |
Neg logit contributions | |
una | -0.093 |
eh | -0.087 |
Mia | -0.082 |
enzie | -0.078 |
ori | -0.078 |
Token | ear |
Token ID | 451 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.013 |
sheet | +0.013 |
inda | +0.012 |
Neg logit contributions | |
bike | -0.022 |
spe | -0.019 |
disl | -0.019 |
Mechan | -0.016 |
gol | -0.016 |
Token | your |
Token ID | 534 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
bike | +0.038 |
spe | +0.035 |
disl | +0.035 |
Mechan | +0.030 |
gol | +0.030 |
Neg logit contributions | |
una | -0.031 |
Mia | -0.029 |
eh | -0.028 |
sheet | -0.025 |
Molly | -0.025 |
Token | pants |
Token ID | 12581 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
bike | +0.043 |
spe | +0.038 |
disl | +0.036 |
qu | +0.035 |
gol | +0.033 |
Neg logit contributions | |
sheet | -0.028 |
una | -0.028 |
eh | -0.027 |
Mia | -0.027 |
spaghetti | -0.024 |
Token | proudly |
Token ID | 23017 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
bike | +0.028 |
disl | +0.027 |
spe | +0.027 |
gol | +0.024 |
Mechan | +0.023 |
Neg logit contributions | |
una | -0.016 |
Mia | -0.016 |
sheet | -0.014 |
eh | -0.014 |
ily | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
bike | +0.037 |
disl | +0.032 |
spe | +0.032 |
gol | +0.027 |
Mechan | +0.027 |
Neg logit contributions | |
una | -0.041 |
eh | -0.040 |
Mia | -0.039 |
sheet | -0.036 |
inda | -0.035 |
Token | Mia |
Token ID | 32189 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
worry | +0.006 |
spe | +0.006 |
Sorry | +0.006 |
bike | +0.006 |
don | +0.005 |
Neg logit contributions | |
eh | -0.008 |
una | -0.007 |
ches | -0.007 |
ool | -0.007 |
aks | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
una | +0.020 |
eh | +0.020 |
Mia | +0.018 |
sheet | +0.017 |
inda | +0.017 |
Neg logit contributions | |
bike | -0.028 |
disl | -0.025 |
spe | -0.024 |
gol | -0.021 |
Mechan | -0.021 |
Token | so |
Token ID | 523 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
bike | +0.019 |
spe | +0.015 |
disl | +0.015 |
wishing | +0.012 |
Mechan | +0.012 |
Neg logit contributions | |
una | -0.027 |
eh | -0.025 |
sheet | -0.024 |
inda | -0.023 |
Mia | -0.023 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
Mechan | +0.005 |
gol | +0.005 |
Neg logit contributions | |
eh | -0.006 |
Mia | -0.006 |
una | -0.006 |
ulu | -0.005 |
Molly | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
bike | +0.032 |
disl | +0.026 |
spe | +0.025 |
wishing | +0.021 |
qu | +0.020 |
Neg logit contributions | |
una | -0.042 |
eh | -0.042 |
sheet | -0.038 |
inda | -0.037 |
ori | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
bike | +0.021 |
disl | +0.019 |
spe | +0.018 |
Acc | +0.015 |
lder | +0.015 |
Neg logit contributions | |
una | -0.028 |
eh | -0.028 |
sheet | -0.024 |
inda | -0.024 |
enzie | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
una | +0.010 |
eh | +0.010 |
Mia | +0.009 |
sheet | +0.008 |
inda | +0.008 |
Neg logit contributions | |
bike | -0.010 |
disl | -0.009 |
spe | -0.009 |
Mechan | -0.008 |
gol | -0.007 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.007 |
spe | +0.007 |
gol | +0.006 |
Mechan | +0.006 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
Mia | -0.004 |
sheet | -0.004 |
inda | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
una | +0.022 |
eh | +0.022 |
Mia | +0.018 |
sheet | +0.018 |
inda | +0.017 |
Neg logit contributions | |
bike | -0.047 |
disl | -0.044 |
spe | -0.043 |
gol | -0.039 |
qu | -0.038 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.004 |
spe | -0.004 |
disl | -0.004 |
Mechan | -0.003 |
self | -0.003 |
Token | feels |
Token ID | 5300 |
Feature activation | -7.32e-04 |
Pos logit contributions | |
una | +0.007 |
Mia | +0.006 |
eh | +0.006 |
sheet | +0.006 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.008 |
disl | -0.007 |
spe | -0.006 |
gol | -0.006 |
Mechan | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -9.16e-03 |
Pos logit contributions | |
una | +0.001 |
eh | +0.001 |
Mia | +0.001 |
sheet | +0.001 |
inda | +0.001 |
Neg logit contributions | |
bike | -0.001 |
spe | -0.001 |
disl | -0.001 |
Mechan | -0.001 |
gol | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
eh | +0.017 |
Mia | +0.017 |
una | +0.016 |
Molly | +0.015 |
Rachel | +0.015 |
Neg logit contributions | |
bike | -0.019 |
spe | -0.015 |
Mechan | -0.015 |
disl | -0.013 |
gol | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -6.81e-04 |
Pos logit contributions | |
bike | +0.029 |
spe | +0.026 |
disl | +0.025 |
Mechan | +0.023 |
gol | +0.022 |
Neg logit contributions | |
una | -0.022 |
Mia | -0.021 |
eh | -0.020 |
sheet | -0.019 |
Molly | -0.018 |
Token | proud |
Token ID | 6613 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
Mia | +0.001 |
una | +0.001 |
eh | +0.001 |
Molly | +0.001 |
Rachel | +0.001 |
Neg logit contributions | |
bike | -0.001 |
spe | -0.001 |
disl | -0.001 |
Mechan | -0.001 |
gol | -0.001 |
Token | ! |
Token ID | 0 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
bike | +0.018 |
disl | +0.016 |
spe | +0.016 |
Mechan | +0.014 |
gol | +0.014 |
Neg logit contributions | |
una | -0.009 |
eh | -0.009 |
Mia | -0.008 |
sheet | -0.008 |
inda | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
una | +0.012 |
eh | +0.012 |
Mia | +0.011 |
sheet | +0.010 |
inda | +0.010 |
Neg logit contributions | |
bike | -0.012 |
disl | -0.011 |
spe | -0.011 |
Mechan | -0.009 |
gol | -0.009 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
gol | +0.004 |
Mechan | +0.004 |
Neg logit contributions | |
una | -0.006 |
eh | -0.005 |
Mia | -0.005 |
sheet | -0.005 |
inda | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Mia | +0.034 |
una | +0.032 |
Molly | +0.030 |
eh | +0.029 |
sheet | +0.029 |
Neg logit contributions | |
bike | -0.047 |
disl | -0.043 |
spe | -0.040 |
Mechan | -0.038 |
gol | -0.038 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
bike | +0.019 |
disl | +0.016 |
spe | +0.016 |
Mechan | +0.013 |
gol | +0.013 |
Neg logit contributions | |
una | -0.020 |
eh | -0.020 |
Mia | -0.019 |
sheet | -0.018 |
inda | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
bike | +0.033 |
disl | +0.029 |
spe | +0.029 |
Mechan | +0.026 |
gol | +0.026 |
Neg logit contributions | |
una | -0.020 |
Mia | -0.019 |
eh | -0.018 |
sheet | -0.017 |
Molly | -0.016 |
Token | You |
Token ID | 1639 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
bike | +0.102 |
disl | +0.093 |
spe | +0.088 |
Mechan | +0.074 |
gol | +0.074 |
Neg logit contributions | |
una | -0.100 |
eh | -0.098 |
Mia | -0.090 |
sheet | -0.085 |
inda | -0.085 |
Token | are |
Token ID | 389 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
sheet | +0.014 |
una | +0.014 |
Mia | +0.013 |
inda | +0.013 |
eh | +0.013 |
Neg logit contributions | |
bike | -0.025 |
disl | -0.022 |
spe | -0.022 |
gol | -0.019 |
qu | -0.019 |
Token | only |
Token ID | 691 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
bike | +0.066 |
disl | +0.059 |
spe | +0.058 |
gol | +0.048 |
Mechan | +0.048 |
Neg logit contributions | |
una | -0.054 |
eh | -0.054 |
Mia | -0.050 |
sheet | -0.047 |
inda | -0.046 |
Token | weak |
Token ID | 4939 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
bike | +0.042 |
spe | +0.038 |
disl | +0.038 |
qu | +0.033 |
Sorry | +0.032 |
Neg logit contributions | |
una | -0.026 |
eh | -0.026 |
Mia | -0.026 |
sheet | -0.023 |
Molly | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
bike | +0.032 |
disl | +0.030 |
spe | +0.029 |
Sorry | +0.026 |
self | +0.025 |
Neg logit contributions | |
una | -0.019 |
sheet | -0.017 |
Mia | -0.017 |
eh | -0.017 |
spaghetti | -0.017 |
Token | my |
Token ID | 616 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
una | +0.007 |
Mia | +0.006 |
eh | +0.006 |
sheet | +0.006 |
Molly | +0.005 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.008 |
Mechan | -0.007 |
qu | -0.007 |
Token | son |
Token ID | 3367 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
bike | +0.057 |
spe | +0.052 |
disl | +0.051 |
qu | +0.046 |
Sorry | +0.045 |
Neg logit contributions | |
una | -0.046 |
sheet | -0.042 |
eh | -0.042 |
Mia | -0.039 |
inda | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
bike | +0.048 |
disl | +0.043 |
spe | +0.043 |
gol | +0.039 |
Mechan | +0.037 |
Neg logit contributions | |
Mia | -0.030 |
una | -0.030 |
eh | -0.028 |
Molly | -0.026 |
sheet | -0.025 |
Token | Why |
Token ID | 4162 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
bike | +0.030 |
spe | +0.027 |
disl | +0.026 |
gol | +0.022 |
qu | +0.022 |
Neg logit contributions | |
una | -0.027 |
Mia | -0.025 |
eh | -0.025 |
Molly | -0.022 |
sheet | -0.022 |
Token | don |
Token ID | 836 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bike | +0.003 |
spe | +0.003 |
disl | +0.003 |
gol | +0.002 |
self | +0.002 |
Neg logit contributions | |
una | -0.004 |
Mia | -0.003 |
eh | -0.003 |
sheet | -0.003 |
Molly | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.018 |
Mia | +0.017 |
sheet | +0.017 |
Luna | +0.016 |
Neg logit contributions | |
bike | -0.019 |
disl | -0.018 |
spe | -0.018 |
gol | -0.015 |
Acc | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
una | +0.005 |
eh | +0.004 |
Mia | +0.004 |
sheet | +0.004 |
inda | +0.004 |
Neg logit contributions | |
bike | -0.005 |
disl | -0.004 |
spe | -0.004 |
gol | -0.004 |
Mechan | -0.004 |
Token | jump |
Token ID | 4391 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
una | +0.013 |
eh | +0.013 |
Mia | +0.013 |
sheet | +0.012 |
Luna | +0.011 |
Neg logit contributions | |
bike | -0.015 |
spe | -0.013 |
disl | -0.013 |
Mechan | -0.011 |
gol | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -7.46e-03 |
Pos logit contributions | |
una | +0.038 |
eh | +0.037 |
Mia | +0.034 |
inda | +0.033 |
sheet | +0.033 |
Neg logit contributions | |
bike | -0.035 |
spe | -0.030 |
disl | -0.030 |
gol | -0.025 |
Mechan | -0.025 |
Token | slide |
Token ID | 10649 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
una | +0.013 |
eh | +0.013 |
Mia | +0.013 |
sheet | +0.012 |
Luna | +0.011 |
Neg logit contributions | |
bike | -0.014 |
spe | -0.013 |
disl | -0.013 |
Mechan | -0.011 |
gol | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
bike | +0.014 |
disl | +0.013 |
spe | +0.013 |
gol | +0.011 |
Mechan | +0.011 |
Neg logit contributions | |
una | -0.010 |
Mia | -0.010 |
eh | -0.009 |
sheet | -0.009 |
Luna | -0.008 |
Token | swing |
Token ID | 9628 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
bike | +0.024 |
spe | +0.022 |
disl | +0.022 |
Mechan | +0.020 |
lder | +0.019 |
Neg logit contributions | |
Mia | -0.019 |
eh | -0.017 |
una | -0.017 |
sheet | -0.017 |
Molly | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
bike | +0.009 |
disl | +0.008 |
spe | +0.008 |
Mechan | +0.007 |
gol | +0.007 |
Neg logit contributions | |
una | -0.007 |
eh | -0.006 |
Mia | -0.006 |
sheet | -0.006 |
Luna | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
disl | +0.006 |
bike | +0.005 |
spe | +0.005 |
Acc | +0.004 |
Sorry | +0.004 |
Neg logit contributions | |
eh | -0.007 |
una | -0.007 |
sheet | -0.006 |
inda | -0.006 |
enzie | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Mia | +0.007 |
una | +0.007 |
eh | +0.007 |
sheet | +0.006 |
inda | +0.006 |
Neg logit contributions | |
bike | -0.010 |
disl | -0.009 |
spe | -0.009 |
Mechan | -0.008 |
gol | -0.007 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
una | +0.056 |
eh | +0.054 |
inda | +0.048 |
sheet | +0.047 |
Mia | +0.047 |
Neg logit contributions | |
bike | -0.043 |
disl | -0.038 |
spe | -0.038 |
gol | -0.030 |
Mechan | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.026 |
sheet | +0.024 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.041 |
disl | -0.037 |
spe | -0.036 |
Mechan | -0.032 |
gol | -0.031 |
Token | ice |
Token ID | 4771 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.015 |
sheet | +0.013 |
spaghetti | +0.013 |
Neg logit contributions | |
bike | -0.026 |
spe | -0.023 |
disl | -0.022 |
gol | -0.020 |
Mechan | -0.020 |
Token | cream |
Token ID | 8566 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
una | +0.044 |
eh | +0.044 |
Mia | +0.040 |
sheet | +0.036 |
spaghetti | +0.034 |
Neg logit contributions | |
bike | -0.067 |
disl | -0.062 |
spe | -0.058 |
gol | -0.054 |
Mechan | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
una | +0.005 |
Mia | +0.005 |
eh | +0.005 |
sheet | +0.004 |
spaghetti | +0.004 |
Neg logit contributions | |
disl | -0.009 |
bike | -0.009 |
spe | -0.008 |
Mechan | -0.008 |
gol | -0.007 |
Token | Sus |
Token ID | 8932 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
affect | +0.006 |
lder | +0.005 |
Neg logit contributions | |
Mia | -0.005 |
Molly | -0.004 |
eh | -0.004 |
una | -0.004 |
ily | -0.003 |
Token | ie |
Token ID | 494 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
una | +0.016 |
eh | +0.016 |
Mia | +0.014 |
sheet | +0.013 |
Luna | +0.012 |
Neg logit contributions | |
bike | -0.033 |
spe | -0.030 |
disl | -0.029 |
Mechan | -0.026 |
self | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
una | +0.021 |
eh | +0.021 |
Mia | +0.020 |
sheet | +0.018 |
Molly | +0.018 |
Neg logit contributions | |
bike | -0.026 |
disl | -0.024 |
spe | -0.022 |
gol | -0.021 |
Mechan | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | +3.71e-04 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.015 |
spe | +0.014 |
gol | +0.012 |
Mechan | +0.012 |
Neg logit contributions | |
eh | -0.014 |
una | -0.014 |
Mia | -0.013 |
Molly | -0.012 |
sheet | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
bike | +0.001 |
disl | +0.001 |
spe | +0.001 |
Mechan | +0.001 |
Crane | +0.001 |
Neg logit contributions | |
Mia | -0.001 |
eh | -0.001 |
una | -0.001 |
Molly | -0.001 |
ily | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
bike | +0.047 |
spe | +0.042 |
disl | +0.042 |
Mechan | +0.038 |
gol | +0.036 |
Neg logit contributions | |
una | -0.033 |
Mia | -0.033 |
eh | -0.030 |
Molly | -0.029 |
sheet | -0.028 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
Mia | +0.006 |
eh | +0.006 |
una | +0.006 |
Molly | +0.005 |
sheet | +0.005 |
Neg logit contributions | |
bike | -0.005 |
spe | -0.005 |
disl | -0.005 |
Mechan | -0.004 |
gol | -0.004 |
Token | every |
Token ID | 790 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
bike | +0.004 |
spe | +0.004 |
disl | +0.004 |
Mechan | +0.003 |
gol | +0.003 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
Molly | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
bike | +0.015 |
spe | +0.013 |
disl | +0.012 |
Mechan | +0.012 |
Sorry | +0.011 |
Neg logit contributions | |
una | -0.010 |
Mia | -0.010 |
eh | -0.008 |
spaghetti | -0.008 |
Molly | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Mia | +0.007 |
una | +0.007 |
eh | +0.007 |
Luna | +0.006 |
Rachel | +0.006 |
Neg logit contributions | |
bike | -0.012 |
spe | -0.011 |
disl | -0.010 |
gol | -0.010 |
Mechan | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
bike | +0.026 |
spe | +0.023 |
disl | +0.022 |
gol | +0.020 |
Mechan | +0.020 |
Neg logit contributions | |
una | -0.026 |
Mia | -0.024 |
eh | -0.024 |
sheet | -0.022 |
inda | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
bike | +0.013 |
spe | +0.012 |
disl | +0.012 |
gol | +0.010 |
Mechan | +0.010 |
Neg logit contributions | |
una | -0.008 |
eh | -0.007 |
Mia | -0.007 |
sheet | -0.007 |
Molly | -0.006 |
Token | mixer |
Token ID | 33938 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.014 |
spe | +0.014 |
gol | +0.013 |
qu | +0.013 |
Neg logit contributions | |
sheet | -0.011 |
eh | -0.010 |
una | -0.010 |
Mia | -0.010 |
spaghetti | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
bike | +0.031 |
disl | +0.029 |
spe | +0.027 |
gol | +0.027 |
Mechan | +0.025 |
Neg logit contributions | |
Mia | -0.017 |
una | -0.016 |
sheet | -0.016 |
eh | -0.015 |
inda | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
una | +0.053 |
eh | +0.052 |
Mia | +0.049 |
sheet | +0.048 |
inda | +0.044 |
Neg logit contributions | |
bike | -0.068 |
spe | -0.058 |
disl | -0.058 |
gol | -0.051 |
Sorry | -0.050 |
Token | special |
Token ID | 2041 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
eh | +0.002 |
sheet | +0.002 |
una | +0.002 |
Mia | +0.002 |
spaghetti | +0.001 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.002 |
spe | -0.002 |
qu | -0.002 |
gol | -0.002 |
Token | switch |
Token ID | 5078 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
bike | +0.014 |
disl | +0.012 |
spe | +0.012 |
gol | +0.010 |
Mechan | +0.010 |
Neg logit contributions | |
eh | -0.011 |
una | -0.011 |
sheet | -0.010 |
Mia | -0.010 |
inda | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
sheet | +0.005 |
Mia | +0.004 |
eh | +0.004 |
una | +0.004 |
inda | +0.004 |
Neg logit contributions | |
bike | -0.008 |
disl | -0.008 |
spe | -0.007 |
gol | -0.007 |
lder | -0.007 |
Token | When |
Token ID | 1649 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
Mia | +0.009 |
eh | +0.007 |
una | +0.007 |
Molly | +0.007 |
Amy | +0.007 |
Neg logit contributions | |
bike | -0.015 |
spe | -0.014 |
disl | -0.013 |
affect | -0.012 |
fer | -0.012 |
Token | wearing |
Token ID | 5762 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
una | -0.003 |
eh | -0.003 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
bike | +0.024 |
disl | +0.022 |
spe | +0.022 |
gol | +0.019 |
Mechan | +0.019 |
Neg logit contributions | |
una | -0.012 |
eh | -0.012 |
Mia | -0.010 |
sheet | -0.010 |
inda | -0.009 |
Token | pink |
Token ID | 11398 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
una | +0.033 |
eh | +0.031 |
Mia | +0.029 |
sheet | +0.028 |
inda | +0.027 |
Neg logit contributions | |
bike | -0.034 |
disl | -0.030 |
spe | -0.029 |
gol | -0.025 |
Mechan | -0.025 |
Token | dress |
Token ID | 6576 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
una | +0.063 |
eh | +0.061 |
Mia | +0.056 |
ori | +0.053 |
inda | +0.053 |
Neg logit contributions | |
bike | -0.062 |
disl | -0.053 |
spe | -0.050 |
bell | -0.044 |
gol | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
una | +0.018 |
eh | +0.017 |
sheet | +0.016 |
Mia | +0.016 |
inda | +0.014 |
Neg logit contributions | |
bike | -0.027 |
disl | -0.027 |
spe | -0.025 |
Mechan | -0.022 |
Acc | -0.022 |
Token | pink |
Token ID | 11398 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.025 |
sheet | +0.023 |
inda | +0.022 |
Neg logit contributions | |
bike | -0.048 |
disl | -0.043 |
spe | -0.043 |
gol | -0.037 |
Mechan | -0.037 |
Token | shoes |
Token ID | 10012 |
Feature activation | -4.12e-04 |
Pos logit contributions | |
una | +0.060 |
eh | +0.059 |
Mia | +0.053 |
inda | +0.050 |
ori | +0.050 |
Neg logit contributions | |
bike | -0.060 |
disl | -0.052 |
spe | -0.050 |
gol | -0.043 |
bell | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
una | +0.000 |
eh | +0.000 |
sheet | +0.000 |
Mia | +0.000 |
ily | +0.000 |
Neg logit contributions | |
disl | -0.001 |
bike | -0.001 |
spe | -0.001 |
Mechan | -0.001 |
Sorry | -0.001 |
Token | just |
Token ID | 655 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
una | +0.031 |
eh | +0.030 |
Mia | +0.029 |
sheet | +0.027 |
Luna | +0.025 |
Neg logit contributions | |
bike | -0.045 |
spe | -0.041 |
disl | -0.040 |
Mechan | -0.035 |
gol | -0.035 |
Token | like |
Token ID | 588 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
una | +0.028 |
Mia | +0.028 |
eh | +0.026 |
sheet | +0.024 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.044 |
spe | -0.040 |
disl | -0.038 |
Mechan | -0.035 |
gol | -0.035 |
Token | Sara |
Token ID | 24799 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
una | +0.015 |
Mia | +0.015 |
eh | +0.013 |
Molly | +0.012 |
sheet | +0.012 |
Neg logit contributions | |
bike | -0.037 |
disl | -0.033 |
spe | -0.033 |
Mechan | -0.030 |
gol | -0.029 |
Token | Today |
Token ID | 8888 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
una | +0.003 |
sheet | +0.003 |
eh | +0.003 |
Milo | +0.003 |
inda | +0.003 |
Neg logit contributions | |
bike | -0.003 |
spe | -0.003 |
disl | -0.003 |
self | -0.002 |
lder | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
bike | +0.013 |
spe | +0.012 |
disl | +0.011 |
Sorry | +0.009 |
gol | +0.008 |
Neg logit contributions | |
una | -0.026 |
eh | -0.026 |
inda | -0.023 |
ches | -0.023 |
ori | -0.022 |
Token | Jane |
Token ID | 12091 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
una | +0.011 |
eh | +0.011 |
ches | +0.010 |
inda | +0.009 |
sheet | +0.009 |
Neg logit contributions | |
bike | -0.012 |
spe | -0.012 |
disl | -0.012 |
Sorry | -0.010 |
worry | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +1.02e-04 |
Pos logit contributions | |
una | +0.056 |
eh | +0.054 |
Mia | +0.051 |
sheet | +0.048 |
inda | +0.047 |
Neg logit contributions | |
bike | -0.057 |
disl | -0.049 |
spe | -0.049 |
Mechan | -0.041 |
gol | -0.041 |
Token | putting |
Token ID | 5137 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
bike | +0.000 |
disl | +0.000 |
spe | +0.000 |
gol | +0.000 |
Mechan | +0.000 |
Neg logit contributions | |
una | -0.000 |
eh | -0.000 |
Mia | -0.000 |
sheet | -0.000 |
inda | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
gol | +0.004 |
self | +0.004 |
Neg logit contributions | |
una | -0.004 |
eh | -0.004 |
Mia | -0.003 |
sheet | -0.003 |
inda | -0.003 |
Token | lots |
Token ID | 6041 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
una | +0.022 |
eh | +0.021 |
Mia | +0.018 |
sheet | +0.017 |
inda | +0.017 |
Neg logit contributions | |
bike | -0.046 |
disl | -0.042 |
spe | -0.042 |
Mechan | -0.037 |
gol | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
una | +0.038 |
eh | +0.035 |
Mia | +0.031 |
sheet | +0.029 |
inda | +0.028 |
Neg logit contributions | |
bike | -0.080 |
disl | -0.072 |
spe | -0.072 |
gol | -0.065 |
self | -0.063 |
Token | makeup |
Token ID | 16029 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
una | +0.059 |
eh | +0.054 |
enzie | +0.050 |
Mia | +0.050 |
ori | +0.049 |
Neg logit contributions | |
bike | -0.044 |
disl | -0.042 |
spe | -0.034 |
gol | -0.032 |
bell | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.018 |
sheet | +0.017 |
Mia | +0.017 |
spaghetti | +0.015 |
Neg logit contributions | |
bike | -0.029 |
disl | -0.028 |
spe | -0.027 |
gol | -0.023 |
Acc | -0.023 |
Token | felt |
Token ID | 2936 |
Feature activation | -6.97e-03 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.026 |
sheet | +0.024 |
inda | +0.023 |
Neg logit contributions | |
bike | -0.042 |
disl | -0.038 |
spe | -0.037 |
Mechan | -0.033 |
gol | -0.033 |
Token | swimming |
Token ID | 14899 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
una | +0.016 |
eh | +0.016 |
Mia | +0.015 |
sheet | +0.014 |
inda | +0.013 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.019 |
spe | -0.018 |
Mechan | -0.016 |
gol | -0.016 |
Token | around |
Token ID | 1088 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
bike | +0.004 |
spe | +0.003 |
disl | +0.003 |
gol | +0.003 |
self | +0.003 |
Neg logit contributions | |
una | -0.003 |
eh | -0.003 |
Mia | -0.003 |
sheet | -0.003 |
ori | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.015 |
spe | +0.015 |
gol | +0.013 |
self | +0.012 |
Neg logit contributions | |
una | -0.016 |
eh | -0.016 |
Mia | -0.014 |
sheet | -0.013 |
inda | -0.013 |
Token | There |
Token ID | 1318 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
gol | +0.004 |
Mechan | +0.004 |
Neg logit contributions | |
una | -0.006 |
eh | -0.006 |
sheet | -0.005 |
Mia | -0.005 |
inda | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | -9.49e-04 |
Pos logit contributions | |
una | +0.003 |
Mia | +0.003 |
eh | +0.003 |
sheet | +0.002 |
inda | +0.002 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
gol | -0.002 |
Mechan | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
una | +0.001 |
eh | +0.001 |
Mia | +0.001 |
sheet | +0.001 |
inda | +0.001 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
Mechan | -0.002 |
gol | -0.002 |
Token | many |
Token ID | 867 |
Feature activation | +2.90e-03 |
Pos logit contributions | |
una | +0.027 |
eh | +0.026 |
Mia | +0.026 |
sheet | +0.021 |
inda | +0.021 |
Neg logit contributions | |
bike | -0.049 |
disl | -0.043 |
spe | -0.041 |
Mechan | -0.038 |
gol | -0.037 |
Token | swimming |
Token ID | 14899 |
Feature activation | -5.76e-04 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.006 |
spe | +0.006 |
Mechan | +0.005 |
gol | +0.005 |
Neg logit contributions | |
una | -0.005 |
eh | -0.004 |
Mia | -0.004 |
sheet | -0.004 |
inda | -0.004 |
Token | near |
Token ID | 1474 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
una | +0.001 |
eh | +0.001 |
Mia | +0.001 |
sheet | +0.001 |
inda | +0.001 |
Neg logit contributions | |
bike | -0.001 |
disl | -0.001 |
spe | -0.001 |
gol | -0.001 |
Mechan | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
una | +0.023 |
eh | +0.023 |
sheet | +0.019 |
ori | +0.019 |
enzie | +0.019 |
Neg logit contributions | |
bike | -0.029 |
disl | -0.026 |
spe | -0.026 |
gol | -0.022 |
self | -0.022 |
Token | reef |
Token ID | 25088 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.003 |
spe | +0.003 |
Mechan | +0.002 |
gol | +0.002 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.001 |
Molly | -0.001 |
Token | do |
Token ID | 466 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
bike | +0.006 |
spe | +0.005 |
disl | +0.005 |
Mechan | +0.005 |
gol | +0.004 |
Neg logit contributions | |
una | -0.005 |
eh | -0.004 |
Mia | -0.004 |
Luna | -0.004 |
sheet | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
una | +0.034 |
eh | +0.031 |
Mia | +0.030 |
sheet | +0.027 |
Luna | +0.026 |
Neg logit contributions | |
bike | -0.062 |
spe | -0.057 |
disl | -0.053 |
gol | -0.051 |
Mechan | -0.050 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.002 |
spe | +0.002 |
gol | +0.002 |
Mechan | +0.002 |
Neg logit contributions | |
una | -0.002 |
eh | -0.002 |
Mia | -0.002 |
sheet | -0.002 |
inda | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
una | +0.037 |
eh | +0.036 |
sheet | +0.032 |
inda | +0.032 |
Mia | +0.031 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.027 |
spe | -0.027 |
gol | -0.023 |
Mechan | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-04 |
Pos logit contributions | |
eh | +0.005 |
una | +0.005 |
sheet | +0.005 |
inda | +0.005 |
enzie | +0.005 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
gol | -0.002 |
qu | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
una | +0.001 |
eh | +0.001 |
Mia | +0.001 |
sheet | +0.000 |
inda | +0.000 |
Neg logit contributions | |
bike | -0.001 |
disl | -0.001 |
spe | -0.001 |
Mechan | -0.001 |
gol | -0.001 |
Token | ily |
Token ID | 813 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
sheet | +0.030 |
Milo | +0.028 |
eh | +0.025 |
Rita | +0.024 |
Luna | +0.024 |
Neg logit contributions | |
disl | -0.056 |
bike | -0.055 |
gol | -0.053 |
qu | -0.049 |
/ | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
una | +0.029 |
eh | +0.028 |
Mia | +0.028 |
sheet | +0.026 |
inda | +0.025 |
Neg logit contributions | |
bike | -0.035 |
disl | -0.032 |
spe | -0.031 |
Mechan | -0.027 |
Sorry | -0.027 |
Token | not |
Token ID | 407 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
bike | +0.005 |
disl | +0.004 |
spe | +0.004 |
gol | +0.003 |
self | +0.003 |
Neg logit contributions | |
una | -0.008 |
eh | -0.007 |
sheet | -0.007 |
Mia | -0.007 |
inda | -0.007 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
una | +0.008 |
eh | +0.008 |
Mia | +0.007 |
sheet | +0.007 |
inda | +0.007 |
Neg logit contributions | |
bike | -0.008 |
disl | -0.007 |
spe | -0.007 |
Mechan | -0.006 |
gol | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
una | +0.003 |
eh | +0.003 |
Mia | +0.003 |
sheet | +0.002 |
inda | +0.002 |
Neg logit contributions | |
bike | -0.003 |
disl | -0.003 |
spe | -0.003 |
Mechan | -0.003 |
gol | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
bike | +0.017 |
disl | +0.015 |
spe | +0.015 |
gol | +0.013 |
Mechan | +0.013 |
Neg logit contributions | |
una | -0.014 |
eh | -0.013 |
Mia | -0.013 |
sheet | -0.012 |
Molly | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
una | +0.005 |
eh | +0.005 |
Mia | +0.005 |
sheet | +0.004 |
inda | +0.004 |
Neg logit contributions | |
bike | -0.007 |
disl | -0.007 |
spe | -0.006 |
gol | -0.006 |
Mechan | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
una | +0.024 |
eh | +0.024 |
Mia | +0.021 |
sheet | +0.020 |
inda | +0.020 |
Neg logit contributions | |
bike | -0.032 |
disl | -0.029 |
spe | -0.029 |
gol | -0.025 |
Mechan | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
bike | +0.003 |
disl | +0.002 |
spe | +0.002 |
qu | +0.002 |
ishly | +0.002 |
Neg logit contributions | |
sheet | -0.002 |
eh | -0.002 |
una | -0.002 |
Mia | -0.002 |
page | -0.002 |
Token | boun |
Token ID | 31283 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
bike | +0.006 |
disl | +0.005 |
spe | +0.005 |
qu | +0.005 |
affect | +0.004 |
Neg logit contributions | |
sheet | -0.004 |
Mia | -0.004 |
una | -0.004 |
eh | -0.004 |
spaghetti | -0.004 |
Token | cy |
Token ID | 948 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
una | +0.061 |
eh | +0.059 |
Mia | +0.055 |
inda | +0.052 |
ori | +0.052 |
Neg logit contributions | |
bike | -0.049 |
spe | -0.040 |
disl | -0.038 |
gol | -0.035 |
self | -0.033 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
una | +0.108 |
eh | +0.107 |
Mia | +0.098 |
sheet | +0.096 |
inda | +0.088 |
Neg logit contributions | |
bike | -0.147 |
disl | -0.132 |
spe | -0.129 |
Mechan | -0.111 |
gol | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
una | +0.066 |
eh | +0.064 |
Mia | +0.059 |
sheet | +0.057 |
inda | +0.055 |
Neg logit contributions | |
bike | -0.076 |
disl | -0.068 |
spe | -0.066 |
Mechan | -0.057 |
gol | -0.056 |
Token | The |
Token ID | 383 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bike | +0.007 |
disl | +0.007 |
spe | +0.006 |
gol | +0.006 |
Mechan | +0.005 |
Neg logit contributions | |
una | -0.006 |
Mia | -0.006 |
eh | -0.005 |
Molly | -0.005 |
sheet | -0.005 |
Token | 3 |
Token ID | 513 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
bike | +0.036 |
disl | +0.033 |
spe | +0.031 |
qu | +0.026 |
ishly | +0.026 |
Neg logit contributions | |
una | -0.031 |
eh | -0.030 |
Mia | -0.029 |
sheet | -0.028 |
ori | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
una | +0.015 |
eh | +0.015 |
Mia | +0.014 |
sheet | +0.012 |
ia | +0.012 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.019 |
spe | -0.017 |
Mechan | -0.016 |
gol | -0.016 |
Token | special |
Token ID | 2041 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
Mia | +0.010 |
una | +0.010 |
sheet | +0.010 |
eh | +0.010 |
Luna | +0.009 |
Neg logit contributions | |
bike | -0.014 |
spe | -0.013 |
disl | -0.012 |
gol | -0.012 |
Mechan | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -8.83e-03 |
Pos logit contributions | |
bike | +0.020 |
disl | +0.018 |
spe | +0.018 |
Mechan | +0.016 |
gol | +0.016 |
Neg logit contributions | |
una | -0.013 |
Mia | -0.012 |
eh | -0.012 |
sheet | -0.012 |
Molly | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | -9.83e-04 |
Pos logit contributions | |
eh | +0.018 |
una | +0.017 |
sheet | +0.015 |
Mia | +0.015 |
inda | +0.015 |
Neg logit contributions | |
bike | -0.016 |
disl | -0.014 |
spe | -0.013 |
Sorry | -0.011 |
Mechan | -0.011 |
Token | needs |
Token ID | 2476 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
una | +0.001 |
Mia | +0.001 |
eh | +0.001 |
ches | +0.001 |
sheet | +0.001 |
Neg logit contributions | |
bike | -0.002 |
disl | -0.002 |
spe | -0.002 |
gol | -0.002 |
Mechan | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
una | +0.052 |
eh | +0.049 |
Mia | +0.046 |
sheet | +0.044 |
inda | +0.041 |
Neg logit contributions | |
bike | -0.079 |
spe | -0.071 |
disl | -0.070 |
gol | -0.061 |
Mechan | -0.061 |
Token | lot |
Token ID | 1256 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
sheet | +0.003 |
una | +0.003 |
eh | +0.003 |
Mia | +0.002 |
page | +0.002 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.004 |
spe | -0.004 |
qu | -0.003 |
ishly | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
una | +0.069 |
eh | +0.068 |
Mia | +0.058 |
sheet | +0.055 |
inda | +0.053 |
Neg logit contributions | |
bike | -0.154 |
disl | -0.143 |
spe | -0.140 |
gol | -0.126 |
self | -0.123 |
Token | care |
Token ID | 1337 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
una | +0.039 |
eh | +0.037 |
Mia | +0.036 |
sheet | +0.036 |
inda | +0.032 |
Neg logit contributions | |
bike | -0.043 |
spe | -0.038 |
disl | -0.035 |
Mechan | -0.031 |
gol | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -8.98e-03 |
Pos logit contributions | |
una | +0.026 |
eh | +0.024 |
Mia | +0.022 |
sheet | +0.021 |
inda | +0.020 |
Neg logit contributions | |
bike | -0.049 |
disl | -0.043 |
spe | -0.043 |
gol | -0.039 |
Mechan | -0.039 |
Token | love |
Token ID | 1842 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
una | +0.016 |
Mia | +0.015 |
sheet | +0.015 |
eh | +0.014 |
spaghetti | +0.014 |
Neg logit contributions | |
bike | -0.018 |
spe | -0.016 |
disl | -0.014 |
Mechan | -0.013 |
gol | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
una | +0.003 |
Mia | +0.003 |
eh | +0.003 |
sheet | +0.003 |
spaghetti | +0.002 |
Neg logit contributions | |
bike | -0.004 |
disl | -0.004 |
spe | -0.004 |
gol | -0.003 |
Mechan | -0.003 |
Token | L |
Token ID | 43 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
bike | +0.005 |
disl | +0.004 |
spe | +0.004 |
Mechan | +0.004 |
gol | +0.004 |
Neg logit contributions | |
una | -0.005 |
eh | -0.005 |
inda | -0.004 |
sheet | -0.004 |
Mia | -0.004 |
Token | ily |
Token ID | 813 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
eh | +0.046 |
Rita | +0.037 |
pollen | +0.035 |
potion | +0.035 |
una | +0.034 |
Neg logit contributions | |
bike | -0.061 |
je | -0.054 |
disl | -0.052 |
arrest | -0.052 |
wreck | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -7.09e-03 |
Pos logit contributions | |
una | +0.049 |
eh | +0.047 |
Mia | +0.046 |
sheet | +0.042 |
Molly | +0.040 |
Neg logit contributions | |
bike | -0.078 |
spe | -0.073 |
disl | -0.069 |
Mechan | -0.063 |
Sorry | -0.062 |
Token | Tom |
Token ID | 4186 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
Mia | +0.010 |
una | +0.010 |
eh | +0.009 |
Rachel | +0.008 |
sheet | +0.008 |
Neg logit contributions | |
bike | -0.016 |
spe | -0.015 |
disl | -0.015 |
Mechan | -0.013 |
qu | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
bike | +0.022 |
spe | +0.021 |
disl | +0.019 |
gol | +0.018 |
Mechan | +0.017 |
Neg logit contributions | |
Mia | -0.013 |
una | -0.013 |
eh | -0.012 |
ily | -0.012 |
sheet | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
una | +0.009 |
eh | +0.009 |
Mia | +0.008 |
sheet | +0.008 |
inda | +0.008 |
Neg logit contributions | |
bike | -0.009 |
disl | -0.008 |
spe | -0.008 |
Mechan | -0.006 |
gol | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
una | +0.089 |
eh | +0.086 |
Mia | +0.082 |
sheet | +0.075 |
inda | +0.072 |
Neg logit contributions | |
bike | -0.121 |
disl | -0.110 |
spe | -0.107 |
Mechan | -0.095 |
gol | -0.093 |
Token | They |
Token ID | 1119 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
bike | +0.008 |
disl | +0.008 |
spe | +0.007 |
gol | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
una | -0.009 |
eh | -0.009 |
sheet | -0.008 |
inda | -0.008 |
ori | -0.008 |
Token | like |
Token ID | 588 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
una | +0.025 |
Mia | +0.025 |
ily | +0.023 |
eh | +0.023 |
inda | +0.022 |
Neg logit contributions | |
bike | -0.049 |
spe | -0.044 |
Mechan | -0.041 |
disl | -0.041 |
ths | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
una | +0.009 |
Mia | +0.009 |
eh | +0.008 |
sheet | +0.008 |
spaghetti | +0.007 |
Neg logit contributions | |
bike | -0.018 |
spe | -0.016 |
disl | -0.016 |
Mechan | -0.014 |
self | -0.014 |
Token | play |
Token ID | 711 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
bike | +0.021 |
spe | +0.019 |
disl | +0.018 |
Mechan | +0.016 |
gol | +0.016 |
Neg logit contributions | |
una | -0.022 |
Mia | -0.021 |
eh | -0.021 |
sheet | -0.020 |
inda | -0.019 |
Token | have |
Token ID | 423 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
una | +0.003 |
Mia | +0.003 |
eh | +0.003 |
sheet | +0.003 |
ches | +0.003 |
Neg logit contributions | |
bike | -0.005 |
disl | -0.004 |
spe | -0.004 |
Acc | -0.004 |
Mechan | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
una | +0.031 |
eh | +0.030 |
Mia | +0.028 |
sheet | +0.026 |
Luna | +0.024 |
Neg logit contributions | |
bike | -0.051 |
spe | -0.046 |
disl | -0.046 |
gol | -0.040 |
Mechan | -0.040 |
Token | give |
Token ID | 1577 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
bike | +0.022 |
spe | +0.021 |
disl | +0.018 |
Mechan | +0.018 |
gol | +0.016 |
Neg logit contributions | |
una | -0.018 |
Mia | -0.017 |
eh | -0.016 |
sheet | -0.015 |
ia | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
eh | +0.022 |
una | +0.022 |
sheet | +0.019 |
inda | +0.019 |
Mia | +0.019 |
Neg logit contributions | |
bike | -0.028 |
disl | -0.026 |
spe | -0.024 |
self | -0.022 |
gol | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
una | +0.028 |
eh | +0.027 |
Mia | +0.025 |
inda | +0.024 |
ori | +0.024 |
Neg logit contributions | |
bike | -0.027 |
disl | -0.024 |
spe | -0.023 |
self | -0.020 |
gol | -0.019 |
Token | name |
Token ID | 1438 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
una | +0.019 |
eh | +0.018 |
Mia | +0.017 |
sheet | +0.017 |
inda | +0.016 |
Neg logit contributions | |
bike | -0.023 |
disl | -0.020 |
spe | -0.020 |
Mechan | -0.017 |
gol | -0.017 |
Token | ." |
Token ID | 526 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
eh | +0.099 |
una | +0.099 |
Mia | +0.088 |
sheet | +0.086 |
inda | +0.085 |
Neg logit contributions | |
bike | -0.113 |
spe | -0.097 |
disl | -0.097 |
self | -0.082 |
gol | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
una | +0.054 |
eh | +0.054 |
sheet | +0.048 |
inda | +0.047 |
ori | +0.046 |
Neg logit contributions | |
bike | -0.046 |
disl | -0.040 |
spe | -0.038 |
gol | -0.033 |
Mechan | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
eh | +0.049 |
una | +0.048 |
sheet | +0.044 |
inda | +0.043 |
enzie | +0.043 |
Neg logit contributions | |
bike | -0.035 |
disl | -0.031 |
spe | -0.029 |
gol | -0.025 |
self | -0.024 |
Token | L |
Token ID | 43 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
una | +0.024 |
eh | +0.023 |
Mia | +0.021 |
sheet | +0.020 |
inda | +0.019 |
Neg logit contributions | |
bike | -0.038 |
disl | -0.034 |
spe | -0.034 |
gol | -0.029 |
Mechan | -0.029 |
Token | ily |
Token ID | 813 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
sheet | +0.033 |
eh | +0.033 |
Milo | +0.032 |
Rita | +0.029 |
enzie | +0.029 |
Neg logit contributions | |
bike | -0.076 |
disl | -0.075 |
gol | -0.071 |
/ | -0.069 |
based | -0.067 |
Token | She |
Token ID | 1375 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
Mia | +0.010 |
eh | +0.010 |
una | +0.009 |
Molly | +0.008 |
spaghetti | +0.008 |
Neg logit contributions | |
bike | -0.016 |
spe | -0.014 |
disl | -0.014 |
gol | -0.013 |
benefit | -0.012 |
Token | needed |
Token ID | 2622 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
una | +0.013 |
eh | +0.012 |
Mia | +0.012 |
sheet | +0.011 |
inda | +0.011 |
Neg logit contributions | |
bike | -0.010 |
spe | -0.009 |
disl | -0.009 |
Mechan | -0.007 |
gol | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +6.37e-03 |
Pos logit contributions | |
una | +0.043 |
eh | +0.042 |
Mia | +0.038 |
sheet | +0.036 |
inda | +0.035 |
Neg logit contributions | |
bike | -0.060 |
disl | -0.053 |
spe | -0.053 |
Mechan | -0.046 |
gol | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
bike | +0.015 |
spe | +0.014 |
disl | +0.014 |
gol | +0.012 |
Mechan | +0.012 |
Neg logit contributions | |
una | -0.009 |
eh | -0.008 |
Mia | -0.008 |
sheet | -0.008 |
inda | -0.007 |
Token | add |
Token ID | 751 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
bike | +0.014 |
spe | +0.013 |
disl | +0.012 |
gol | +0.011 |
Mechan | +0.011 |
Neg logit contributions | |
Mia | -0.011 |
una | -0.011 |
eh | -0.010 |
sheet | -0.010 |
Molly | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
una | +0.026 |
eh | +0.025 |
Mia | +0.024 |
sheet | +0.023 |
spaghetti | +0.021 |
Neg logit contributions | |
bike | -0.051 |
disl | -0.046 |
spe | -0.045 |
Mechan | -0.040 |
gol | -0.040 |
Token | sugar |
Token ID | 7543 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
una | +0.075 |
eh | +0.074 |
Mia | +0.067 |
sheet | +0.066 |
spaghetti | +0.060 |
Neg logit contributions | |
bike | -0.142 |
disl | -0.128 |
spe | -0.125 |
Mechan | -0.110 |
gol | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
una | +0.053 |
eh | +0.050 |
Mia | +0.049 |
sheet | +0.045 |
inda | +0.042 |
Neg logit contributions | |
bike | -0.080 |
disl | -0.073 |
spe | -0.070 |
Mechan | -0.062 |
gol | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
Mia | +0.034 |
una | +0.033 |
eh | +0.032 |
sheet | +0.029 |
Molly | +0.028 |
Neg logit contributions | |
bike | -0.056 |
spe | -0.050 |
disl | -0.049 |
gol | -0.044 |
Mechan | -0.044 |
Token | cookie |
Token ID | 19751 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
eh | +0.011 |
sheet | +0.010 |
una | +0.010 |
spaghetti | +0.010 |
Mia | +0.010 |
Neg logit contributions | |
bike | -0.021 |
disl | -0.019 |
spe | -0.019 |
gol | -0.017 |
Sorry | -0.016 |
Token | dough |
Token ID | 15756 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
una | +0.058 |
eh | +0.056 |
Mia | +0.052 |
sheet | +0.049 |
inda | +0.048 |
Neg logit contributions | |
bike | -0.070 |
disl | -0.062 |
spe | -0.061 |
gol | -0.052 |
Mechan | -0.052 |