TOP ACTIVATIONS
MAX = 0.415

clown s juggling and ac rob ats doing flips . But
of fun watching the ac rob ats and clown s .
thought they looked like ac rob ats . She enjoyed the
clown s and the ac rob ats and the lions and
elephants , lions and ac rob ats . They are amazed
the animals , the ac rob ats and the clown s
saw clown s and ac rob ats and lions and elephants
finally , the z ig zag had an idea . It
ement as the z ig zag soared in the sky .
hill in a z ig zag pattern . When
fly like the z ig zag if he just opened his
. One day , Zig zag 's owner wanted to take
had their own z ig zag . The two
can make the z ig zag another day . I 'm
hanging from the z ig zag . M omm a repeated
side of the z ig zag , to the other side
the rain drops z ig zag down the window . She
hill and the z ig zag path in the rear view
he saw a z ig zag branch and decided to try
slide with a z ig zag shape . Lily wanted to

MIN ACTIVATIONS
MIN = -0.263

a big smile on his face and was carrying his own
felt a breeze on his face . He wondered what it
with a smile on his face . <|endoftext|> One day ,
. She sees mom 's face . She is scared .
a big smile on his face . The farmer
pe aches and made a face . They did not want
a big smile on her face .
. He saw Tom 's face and knew what had happened
feels the wind in his face and the pedals under his
Her Mom saw her face and said " Let me
It hits Tom in the face . He drops the shovel
She had shampoo on her face . She was crying .
. She had a red face and a hot head .
a big smile on his face . He waved and waved
feel the wind on his face . One day
a big smile on his face . He remembered his dream
at Lily with a proud face . He kissed her on
let the sunshine warm his face . It felt really good
a big smile on his face . What a great day
with a smile on her face . She had

INTERVAL 0.246 - 0.415
CONTAINS 0.024%

car to zoom around even faster . His mom smiled again
snap , the whip moved faster and faster . Now it
across the pool , swimming faster and faster .
The little squirrel ran faster , but the fox was
<|endoftext|> Sam was picking wild fl owers in the me adow

INTERVAL 0.076 - 0.246
CONTAINS 8.024%

comfortable and relaxed as he always did outside . He also
stop smiling . <|endoftext|> He idi had a big problem ,
car went too fast and hit a wall . The toy
with his toys , but one day his favorite toy broke
, she improved the world one little bit at a time

INTERVAL -0.094 - 0.076
CONTAINS 87.918%

was his reward ! Jack was so happy . He learned
things with blocks , like houses , cars , and towers
took his treasure and went running back home with a big
, the rabbit was right there with her - even when
there was an empty circle . Nothing was inside the circle

INTERVAL -0.263 - -0.094
CONTAINS 4.034%

Slow ly , the mom my got back to work .
scared when he saw a big bird nearby .
park . They saw a big tree with many branches .
After a while , Tim my saw the dog hiding behind
hungry . She wanted to eat a snack , but she
Token clown
Token ID25573
Feature activation+1.01e-01

Pos logit contributions
 makeup+0.079
vel+0.078
 face+0.078
 spit+0.076
 blush+0.070
Neg logit contributions
rob-0.176
zag-0.166
 Hipp-0.164
 Hero-0.157
girls-0.156
Tokens
Token ID82
Feature activation+3.02e-02

Pos logit contributions
rob+0.160
 Hipp+0.142
zag+0.142
 steep+0.135
 Hero+0.133
Neg logit contributions
vel-0.181
 face-0.180
 makeup-0.179
 spit-0.176
 blush-0.169
Token juggling
Token ID48097
Feature activation+1.89e-01

Pos logit contributions
rob+0.070
zag+0.065
 Hipp+0.065
 Hero+0.062
girls+0.062
Neg logit contributions
 face-0.032
 makeup-0.032
vel-0.032
 spit-0.031
 blush-0.029
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
rob+0.410
zag+0.384
 Hipp+0.381
 Hero+0.363
girls+0.359
Neg logit contributions
vel-0.227
 makeup-0.227
 face-0.225
 spit-0.220
 blush-0.206
Token ac
Token ID936
Feature activation+3.59e-02

Pos logit contributions
rob+0.026
zag+0.024
 steep+0.023
 Hipp+0.022
girls+0.022
Neg logit contributions
 face-0.015
 makeup-0.015
 blush-0.014
 her-0.014
 spit-0.014
Tokenrob
Token ID22609
Feature activation+4.15e-01

Pos logit contributions
 Hipp+0.010
zag+0.007
rob+0.005
 steep+0.005
 Hero+0.004
Neg logit contributions
vel-0.106
 makeup-0.105
She-0.102
 face-0.101
 spit-0.101
Tokenats
Token ID1381
Feature activation+6.75e-02

Pos logit contributions
rob+0.676
zag+0.611
 Hipp+0.581
girls+0.556
 Hero+0.552
Neg logit contributions
 makeup-0.726
 face-0.725
vel-0.720
 spit-0.716
 blush-0.682
Token doing
Token ID1804
Feature activation+5.84e-03

Pos logit contributions
rob+0.160
zag+0.150
 Hipp+0.149
 Hero+0.143
 steep+0.142
Neg logit contributions
vel-0.067
 makeup-0.067
 face-0.066
 spit-0.064
 blush-0.060
Token flips
Token ID45971
Feature activation+1.27e-01

Pos logit contributions
rob+0.012
zag+0.011
 Hipp+0.011
girls+0.011
 Hero+0.011
Neg logit contributions
vel-0.008
 makeup-0.007
 face-0.007
 spit-0.007
 her-0.007
Token.
Token ID13
Feature activation-8.51e-03

Pos logit contributions
rob+0.306
zag+0.283
 Hipp+0.281
girls+0.269
 Hero+0.267
Neg logit contributions
 makeup-0.126
vel-0.125
 face-0.123
 spit-0.116
 her-0.111
Token But
Token ID887
Feature activation+3.28e-02

Pos logit contributions
 makeup+0.009
 her+0.009
 face+0.009
She+0.008
Her+0.008
Neg logit contributions
rob-0.021
zag-0.020
 steep-0.019
girls-0.019
 Hipp-0.018
Token of
Token ID286
Feature activation-8.57e-02

Pos logit contributions
 makeup+0.041
vel+0.038
 face+0.037
 spit+0.034
 blush+0.027
Neg logit contributions
rob-0.338
zag-0.322
 Hipp-0.321
 Hero-0.309
girls-0.309
Token fun
Token ID1257
Feature activation+5.14e-02

Pos logit contributions
 makeup+0.116
 face+0.112
 spit+0.107
vel+0.102
prise+0.100
Neg logit contributions
zag-0.182
rob-0.173
 Hipp-0.170
field-0.159
 Hero-0.159
Token watching
Token ID4964
Feature activation+5.00e-02

Pos logit contributions
rob+0.128
 Hipp+0.122
zag+0.122
 Hero+0.118
 steep+0.117
Neg logit contributions
vel-0.045
 makeup-0.045
 face-0.044
 spit-0.042
 blush-0.037
Token the
Token ID262
Feature activation+2.98e-02

Pos logit contributions
rob+0.104
zag+0.097
 Hipp+0.095
 steep+0.090
 Hero+0.089
Neg logit contributions
 makeup-0.066
 face-0.066
vel-0.065
 spit-0.063
 blush-0.060
Token ac
Token ID936
Feature activation+2.82e-02

Pos logit contributions
rob+0.043
zag+0.042
 Hipp+0.040
 steep+0.038
 Zig+0.037
Neg logit contributions
 makeup-0.055
 face-0.055
vel-0.054
 spit-0.053
prise-0.051
Tokenrob
Token ID22609
Feature activation+4.06e-01

Pos logit contributions
 Hipp+0.008
 steep+0.006
zag+0.005
 Hero+0.004
girls+0.004
Neg logit contributions
vel-0.082
 makeup-0.081
She-0.079
 face-0.079
on-0.079
Tokenats
Token ID1381
Feature activation+6.06e-02

Pos logit contributions
rob+0.695
 Hipp+0.661
zag+0.642
 Hero+0.619
 steep+0.616
Neg logit contributions
vel-0.666
 makeup-0.654
 face-0.649
 spit-0.640
prise-0.608
Token and
Token ID290
Feature activation+3.14e-03

Pos logit contributions
rob+0.140
zag+0.132
 Hipp+0.132
 Hero+0.126
girls+0.125
Neg logit contributions
vel-0.063
 makeup-0.062
 face-0.061
 spit-0.060
 blush-0.055
Token clown
Token ID25573
Feature activation+9.10e-02

Pos logit contributions
rob+0.006
zag+0.006
 Hipp+0.006
 steep+0.006
 Hero+0.005
Neg logit contributions
 face-0.004
 makeup-0.004
 spit-0.004
 her-0.004
 blush-0.004
Tokens
Token ID82
Feature activation+2.03e-02

Pos logit contributions
rob+0.154
 Hipp+0.137
zag+0.135
 steep+0.132
 Hero+0.128
Neg logit contributions
vel-0.153
 face-0.153
 makeup-0.150
 spit-0.148
 blush-0.142
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
rob+0.051
 Hipp+0.047
zag+0.047
 Hero+0.045
 steep+0.044
Neg logit contributions
 face-0.019
 makeup-0.018
vel-0.018
 spit-0.018
 blush-0.016
Token thought
Token ID1807
Feature activation-4.87e-02

Pos logit contributions
 face+0.051
vel+0.050
 spit+0.050
 makeup+0.049
 blush+0.045
Neg logit contributions
rob-0.112
 Hipp-0.105
zag-0.101
 Hero-0.099
girls-0.099
Token they
Token ID484
Feature activation+7.63e-02

Pos logit contributions
vel+0.064
 makeup+0.064
 face+0.063
 spit+0.062
 blush+0.058
Neg logit contributions
rob-0.100
zag-0.093
 Hipp-0.092
 Hero-0.088
 steep-0.087
Token looked
Token ID3114
Feature activation-1.70e-02

Pos logit contributions
rob+0.125
zag+0.121
 Hipp+0.118
 steep+0.115
 Hero+0.111
Neg logit contributions
vel-0.125
 makeup-0.121
 face-0.118
prise-0.117
 spit-0.115
Token like
Token ID588
Feature activation-1.94e-02

Pos logit contributions
vel+0.018
 makeup+0.017
 face+0.017
 spit+0.017
 blush+0.016
Neg logit contributions
rob-0.040
zag-0.037
 Hipp-0.037
 Hero-0.036
girls-0.035
Token ac
Token ID936
Feature activation+2.54e-02

Pos logit contributions
 makeup+0.021
 face+0.021
vel+0.020
 spit+0.020
 blush+0.019
Neg logit contributions
rob-0.045
zag-0.043
 Hipp-0.042
 steep-0.040
 Hero-0.040
Tokenrob
Token ID22609
Feature activation+4.02e-01

Pos logit contributions
rob+0.013
 Hipp+0.013
zag+0.012
 Hero+0.010
 steep+0.009
Neg logit contributions
vel-0.070
 makeup-0.070
 face-0.068
 spit-0.067
 blush-0.067
Tokenats
Token ID1381
Feature activation+5.87e-02

Pos logit contributions
rob+0.670
zag+0.596
 Hipp+0.544
girls+0.542
 Hero+0.524
Neg logit contributions
 face-0.700
 spit-0.687
 makeup-0.685
vel-0.676
She-0.648
Token.
Token ID13
Feature activation-2.25e-02

Pos logit contributions
rob+0.143
zag+0.134
 Hipp+0.133
 steep+0.127
 Hero+0.127
Neg logit contributions
 makeup-0.056
 face-0.054
vel-0.053
 spit-0.050
 blush-0.049
Token She
Token ID1375
Feature activation-4.73e-02

Pos logit contributions
 makeup+0.022
 face+0.021
 spit+0.019
vel+0.019
 blush+0.019
Neg logit contributions
rob-0.059
zag-0.053
 Hipp-0.052
girls-0.050
 Hero-0.050
Token enjoyed
Token ID8359
Feature activation+1.72e-02

Pos logit contributions
 spit+0.049
 face+0.047
 makeup+0.044
vel+0.043
 cut+0.042
Neg logit contributions
rob-0.119
 Hipp-0.109
zag-0.107
girls-0.107
 Hero-0.104
Token the
Token ID262
Feature activation+2.62e-02

Pos logit contributions
rob+0.042
zag+0.040
 Hipp+0.039
 steep+0.039
 Hero+0.038
Neg logit contributions
 makeup-0.017
vel-0.016
 her-0.015
 face-0.015
 spit-0.015
Token clown
Token ID25573
Feature activation+9.25e-02

Pos logit contributions
rob+0.064
zag+0.059
 Hipp+0.059
 Hero+0.056
 steep+0.055
Neg logit contributions
vel-0.056
 makeup-0.055
 face-0.054
 spit-0.054
 blush-0.052
Tokens
Token ID82
Feature activation+2.00e-02

Pos logit contributions
rob+0.194
zag+0.187
 Hipp+0.184
 Hero+0.177
girls+0.175
Neg logit contributions
vel-0.114
 makeup-0.113
 spit-0.108
 face-0.108
 blush-0.102
Token and
Token ID290
Feature activation+6.16e-03

Pos logit contributions
rob+0.043
zag+0.042
 Hipp+0.041
 steep+0.040
 Hero+0.040
Neg logit contributions
vel-0.023
 makeup-0.022
 spit-0.021
prise-0.021
 face-0.021
Token the
Token ID262
Feature activation+3.45e-02

Pos logit contributions
rob+0.014
zag+0.013
 Hipp+0.013
 steep+0.012
girls+0.012
Neg logit contributions
 face-0.007
 spit-0.007
 makeup-0.007
 her-0.007
 blush-0.007
Token ac
Token ID936
Feature activation+2.89e-02

Pos logit contributions
rob+0.065
zag+0.060
 Hipp+0.060
 Hero+0.057
 steep+0.056
Neg logit contributions
vel-0.051
 makeup-0.050
 face-0.050
 spit-0.049
 blush-0.047
Tokenrob
Token ID22609
Feature activation+4.02e-01

Pos logit contributions
rob+0.010
 Hipp+0.007
zag+0.006
 Hero+0.004
 steep+0.003
Neg logit contributions
vel-0.087
 makeup-0.087
 face-0.086
 spit-0.085
 blush-0.083
Tokenats
Token ID1381
Feature activation+5.73e-02

Pos logit contributions
rob+0.652
zag+0.596
 Hipp+0.587
 Hero+0.552
girls+0.546
Neg logit contributions
vel-0.703
 makeup-0.702
 face-0.695
 spit-0.688
 blush-0.657
Token and
Token ID290
Feature activation+4.92e-03

Pos logit contributions
rob+0.124
zag+0.120
 Hipp+0.119
 Hero+0.115
 Zig+0.113
Neg logit contributions
vel-0.066
 makeup-0.065
prise-0.061
 spit-0.061
 face-0.060
Token the
Token ID262
Feature activation+3.32e-02

Pos logit contributions
rob+0.012
zag+0.011
 Hipp+0.011
 steep+0.010
girls+0.010
Neg logit contributions
 face-0.005
 spit-0.005
 makeup-0.005
 her-0.005
 blush-0.005
Token lions
Token ID31420
Feature activation+2.01e-01

Pos logit contributions
rob+0.063
 Hipp+0.058
zag+0.058
 Hero+0.055
 steep+0.054
Neg logit contributions
vel-0.050
 makeup-0.048
 spit-0.047
 face-0.047
 blush-0.045
Token and
Token ID290
Feature activation+4.62e-03

Pos logit contributions
rob+0.449
zag+0.426
 Hipp+0.425
girls+0.410
 Hero+0.409
Neg logit contributions
vel-0.221
 makeup-0.220
 spit-0.205
 face-0.205
prise-0.200
Token elephants
Token ID25368
Feature activation+2.19e-01

Pos logit contributions
 makeup+0.041
 face+0.041
vel+0.040
 spit+0.040
 blush+0.038
Neg logit contributions
rob-0.065
zag-0.061
 Hipp-0.060
 Hero-0.057
 steep-0.057
Token,
Token ID11
Feature activation-3.18e-02

Pos logit contributions
rob+0.479
 Hipp+0.455
zag+0.452
girls+0.435
 Hero+0.435
Neg logit contributions
vel-0.261
 makeup-0.253
 spit-0.248
 face-0.248
prise-0.231
Token lions
Token ID31420
Feature activation+2.01e-01

Pos logit contributions
vel+0.038
 makeup+0.037
 face+0.036
 spit+0.036
 blush+0.033
Neg logit contributions
rob-0.070
zag-0.065
 Hipp-0.065
 Hero-0.063
girls-0.062
Token and
Token ID290
Feature activation+5.91e-03

Pos logit contributions
rob+0.447
 Hipp+0.424
zag+0.423
 Hero+0.407
girls+0.405
Neg logit contributions
vel-0.230
 makeup-0.226
 spit-0.221
 face-0.220
 blush-0.205
Token ac
Token ID936
Feature activation+2.77e-02

Pos logit contributions
rob+0.010
zag+0.010
 Hipp+0.009
 Hero+0.009
 steep+0.009
Neg logit contributions
 makeup-0.009
 face-0.009
 spit-0.009
vel-0.009
 blush-0.009
Tokenrob
Token ID22609
Feature activation+4.02e-01

Pos logit contributions
zag+0.006
 Hipp+0.006
rob+0.005
 steep+0.004
 Hero+0.003
Neg logit contributions
 makeup-0.082
vel-0.081
 face-0.079
 spit-0.078
She-0.078
Tokenats
Token ID1381
Feature activation+5.61e-02

Pos logit contributions
rob+0.635
zag+0.576
 Hipp+0.561
 Hero+0.528
girls+0.528
Neg logit contributions
 makeup-0.719
vel-0.717
 face-0.714
 spit-0.706
 blush-0.675
Token.
Token ID13
Feature activation-1.65e-02

Pos logit contributions
rob+0.139
zag+0.131
 Hipp+0.129
 steep+0.125
 Hero+0.125
Neg logit contributions
vel-0.049
 makeup-0.049
 face-0.049
 spit-0.047
 blush-0.043
Token They
Token ID1119
Feature activation+1.29e-02

Pos logit contributions
 face+0.023
 makeup+0.021
 spit+0.021
 her+0.020
L+0.020
Neg logit contributions
rob-0.039
zag-0.037
field-0.033
 aboard-0.030
xy-0.030
Token are
Token ID389
Feature activation-1.12e-01

Pos logit contributions
rob+0.033
zag+0.031
 Hipp+0.031
 Hero+0.030
 steep+0.029
Neg logit contributions
 makeup-0.010
vel-0.010
 face-0.010
 spit-0.010
 blush-0.009
Token amazed
Token ID24562
Feature activation+1.13e-01

Pos logit contributions
 face+0.115
 spit+0.109
 makeup+0.107
vel+0.103
 her+0.099
Neg logit contributions
rob-0.281
zag-0.255
 Hipp-0.245
 Hero-0.238
 steep-0.233
Token the
Token ID262
Feature activation+2.78e-02

Pos logit contributions
 face+0.097
 makeup+0.096
vel+0.091
 spit+0.090
 her+0.089
Neg logit contributions
zag-0.185
rob-0.183
 Hipp-0.171
girls-0.166
 steep-0.164
Token animals
Token ID4695
Feature activation+3.67e-02

Pos logit contributions
zag+0.053
rob+0.052
 Hipp+0.048
 Zig+0.047
girls+0.046
Neg logit contributions
 face-0.039
 makeup-0.038
vel-0.036
 spit-0.036
 goodness-0.034
Token,
Token ID11
Feature activation-3.91e-02

Pos logit contributions
rob+0.090
zag+0.084
 Hipp+0.083
 Hero+0.080
 steep+0.080
Neg logit contributions
vel-0.034
 face-0.034
 makeup-0.033
 spit-0.032
 blush-0.029
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
 face+0.036
 makeup+0.034
 spit+0.033
 her+0.031
 blush+0.029
Neg logit contributions
rob-0.103
zag-0.098
 Hipp-0.090
girls-0.087
 aboard-0.087
Token ac
Token ID936
Feature activation+2.40e-02

Pos logit contributions
rob+0.054
zag+0.053
 Hipp+0.048
 Zig+0.047
 Hero+0.046
Neg logit contributions
 face-0.042
 makeup-0.041
 spit-0.039
vel-0.038
 mirror-0.037
Tokenrob
Token ID22609
Feature activation+3.99e-01

Pos logit contributions
 Hipp+0.007
 steep+0.005
zag+0.005
 Hero+0.004
 Zig+0.004
Neg logit contributions
 makeup-0.068
vel-0.068
on-0.067
She-0.066
 face-0.066
Tokenats
Token ID1381
Feature activation+5.46e-02

Pos logit contributions
rob+0.668
 Hipp+0.629
zag+0.617
 Hero+0.593
 steep+0.587
Neg logit contributions
vel-0.667
 makeup-0.660
 face-0.652
 spit-0.646
prise-0.611
Token and
Token ID290
Feature activation-3.05e-04

Pos logit contributions
rob+0.131
zag+0.123
 Hipp+0.121
 steep+0.117
 Hero+0.117
Neg logit contributions
 face-0.052
 makeup-0.051
vel-0.051
 spit-0.050
 blush-0.046
Token the
Token ID262
Feature activation+2.72e-02

Pos logit contributions
 face+0.000
 makeup+0.000
 spit+0.000
 her+0.000
 blush+0.000
Neg logit contributions
rob-0.001
zag-0.001
 Hipp-0.001
 steep-0.001
 Hero-0.001
Token clown
Token ID25573
Feature activation+8.63e-02

Pos logit contributions
rob+0.051
zag+0.048
 Hipp+0.047
 Hero+0.044
 Zig+0.044
Neg logit contributions
 makeup-0.040
 face-0.040
vel-0.040
 spit-0.039
 blush-0.037
Tokens
Token ID82
Feature activation+1.40e-02

Pos logit contributions
rob+0.152
 steep+0.134
zag+0.134
 Hipp+0.132
 Hero+0.127
Neg logit contributions
 face-0.138
 makeup-0.135
vel-0.135
 spit-0.135
 blush-0.128
Token saw
Token ID2497
Feature activation-9.39e-02

Pos logit contributions
 spit+0.024
 face+0.023
 makeup+0.022
vel+0.021
 blush+0.020
Neg logit contributions
rob-0.055
zag-0.052
 Hipp-0.050
girls-0.048
 steep-0.048
Token clown
Token ID25573
Feature activation+8.31e-02

Pos logit contributions
 makeup+0.120
 face+0.119
vel+0.118
 spit+0.117
 blush+0.109
Neg logit contributions
rob-0.197
zag-0.185
 Hipp-0.181
 Hero-0.172
 steep-0.172
Tokens
Token ID82
Feature activation+1.10e-02

Pos logit contributions
rob+0.125
zag+0.113
 Hipp+0.112
 Hero+0.105
 steep+0.103
Neg logit contributions
vel-0.155
 makeup-0.155
 face-0.153
 spit-0.152
 blush-0.145
Token and
Token ID290
Feature activation-2.47e-03

Pos logit contributions
rob+0.025
zag+0.024
 Hipp+0.024
 Hero+0.023
 steep+0.022
Neg logit contributions
vel-0.012
 makeup-0.012
 face-0.011
 spit-0.011
 blush-0.011
Token ac
Token ID936
Feature activation+2.10e-02

Pos logit contributions
 face+0.004
 makeup+0.004
 spit+0.004
 blush+0.003
 her+0.003
Neg logit contributions
rob-0.005
zag-0.005
 Hipp-0.004
 steep-0.004
girls-0.004
Tokenrob
Token ID22609
Feature activation+3.91e-01

Pos logit contributions
rob+0.008
 Hipp+0.007
zag+0.007
 steep+0.005
 Hero+0.005
Neg logit contributions
vel-0.061
 makeup-0.061
 face-0.059
 spit-0.059
 blush-0.058
Tokenats
Token ID1381
Feature activation+5.00e-02

Pos logit contributions
rob+0.618
zag+0.560
 Hipp+0.544
girls+0.513
 Hero+0.511
Neg logit contributions
 makeup-0.701
vel-0.699
 face-0.697
 spit-0.688
 blush-0.659
Token and
Token ID290
Feature activation-3.20e-03

Pos logit contributions
rob+0.117
zag+0.110
 Hipp+0.110
 Hero+0.105
girls+0.104
Neg logit contributions
vel-0.051
 makeup-0.050
 face-0.050
 spit-0.049
 blush-0.045
Token lions
Token ID31420
Feature activation+1.92e-01

Pos logit contributions
 face+0.005
 makeup+0.005
 spit+0.005
 blush+0.005
 dust+0.004
Neg logit contributions
rob-0.006
zag-0.006
 Hipp-0.005
 steep-0.005
 Hero-0.005
Token and
Token ID290
Feature activation-3.55e-03

Pos logit contributions
rob+0.440
zag+0.416
 Hipp+0.415
girls+0.401
 Hero+0.400
Neg logit contributions
vel-0.205
 makeup-0.203
 face-0.196
 spit-0.195
prise-0.182
Token elephants
Token ID25368
Feature activation+2.09e-01

Pos logit contributions
 makeup+0.006
 face+0.006
 spit+0.006
vel+0.006
 blush+0.006
Neg logit contributions
rob-0.006
zag-0.006
 Hipp-0.005
 steep-0.005
 Hero-0.005
Token finally
Token ID3443
Feature activation+1.08e-01

Pos logit contributions
rob+0.271
zag+0.250
 Hipp+0.247
 Hero+0.236
girls+0.236
Neg logit contributions
 makeup-0.189
vel-0.189
 face-0.187
 spit-0.184
 blush-0.174
Token,
Token ID11
Feature activation-2.69e-02

Pos logit contributions
rob+0.262
zag+0.244
 Hipp+0.243
girls+0.235
 Hero+0.234
Neg logit contributions
 makeup-0.107
vel-0.107
 face-0.104
 spit-0.102
 blush-0.094
Token the
Token ID262
Feature activation+3.77e-02

Pos logit contributions
 makeup+0.033
 face+0.032
vel+0.032
 spit+0.031
 blush+0.029
Neg logit contributions
rob-0.059
zag-0.055
 Hipp-0.054
girls-0.052
 Hero-0.052
Token z
Token ID1976
Feature activation+1.27e-01

Pos logit contributions
rob+0.077
 Hipp+0.074
zag+0.073
 Hero+0.070
 steep+0.069
Neg logit contributions
vel-0.049
 makeup-0.046
 spit-0.046
 face-0.045
 blush-0.043
Tokenig
Token ID328
Feature activation+8.49e-02

Pos logit contributions
rob+0.204
 Hipp+0.190
zag+0.182
 Hero+0.178
 steep+0.178
Neg logit contributions
vel-0.221
 face-0.218
 makeup-0.216
 spit-0.211
prise-0.203
Tokenzag
Token ID50183
Feature activation+3.68e-01

Pos logit contributions
rob+0.179
 Hipp+0.166
 Hero+0.157
zag+0.156
girls+0.155
Neg logit contributions
vel-0.110
 face-0.110
 makeup-0.107
 spit-0.106
 blush-0.098
Token had
Token ID550
Feature activation+1.92e-02

Pos logit contributions
rob+0.741
zag+0.687
 Hipp+0.685
 Hero+0.652
girls+0.644
Neg logit contributions
vel-0.493
 makeup-0.491
 face-0.486
 spit-0.479
 blush-0.450
Token an
Token ID281
Feature activation+3.98e-02

Pos logit contributions
rob+0.042
zag+0.039
 Hipp+0.039
 Hero+0.037
girls+0.037
Neg logit contributions
 makeup-0.023
vel-0.023
 face-0.022
 spit-0.022
 blush-0.020
Token idea
Token ID2126
Feature activation+4.28e-03

Pos logit contributions
rob+0.061
 steep+0.059
 Hipp+0.059
zag+0.059
 Hero+0.055
Neg logit contributions
vel-0.065
 makeup-0.065
 blush-0.063
 spit-0.063
prise-0.062
Token.
Token ID13
Feature activation-5.92e-03

Pos logit contributions
rob+0.009
zag+0.009
 Hipp+0.009
 Zig+0.008
 Hero+0.008
Neg logit contributions
vel-0.005
 makeup-0.005
 spit-0.005
 face-0.005
 blush-0.004
Token It
Token ID632
Feature activation-4.49e-02

Pos logit contributions
 makeup+0.008
 face+0.008
vel+0.008
 spit+0.007
She+0.007
Neg logit contributions
rob-0.013
zag-0.011
 steep-0.011
 Hipp-0.011
girls-0.010
Tokenement
Token ID972
Feature activation+1.36e-01

Pos logit contributions
vel+0.031
 makeup+0.031
 face+0.031
 spit+0.030
 blush+0.029
Neg logit contributions
rob-0.030
 Hipp-0.028
zag-0.028
girls-0.026
 steep-0.026
Token as
Token ID355
Feature activation+8.13e-02

Pos logit contributions
rob+0.326
 Hipp+0.302
zag+0.301
 Hero+0.290
girls+0.287
Neg logit contributions
 face-0.134
vel-0.134
 makeup-0.133
 spit-0.127
 blush-0.117
Token the
Token ID262
Feature activation+4.33e-02

Pos logit contributions
rob+0.161
zag+0.149
 Hipp+0.145
girls+0.139
 Hero+0.137
Neg logit contributions
 makeup-0.116
 face-0.114
vel-0.113
 spit-0.112
 blush-0.105
Token z
Token ID1976
Feature activation+1.32e-01

Pos logit contributions
rob+0.086
 Hipp+0.081
zag+0.080
 Hero+0.076
 steep+0.076
Neg logit contributions
vel-0.060
 makeup-0.058
 spit-0.057
 face-0.057
 blush-0.053
Tokenig
Token ID328
Feature activation+8.47e-02

Pos logit contributions
rob+0.240
 Hipp+0.227
zag+0.218
 Hero+0.217
 steep+0.216
Neg logit contributions
vel-0.202
 makeup-0.199
 face-0.197
 spit-0.192
 blush-0.185
Tokenzag
Token ID50183
Feature activation+3.67e-01

Pos logit contributions
rob+0.161
 Hipp+0.147
 Hero+0.141
girls+0.138
 steep+0.136
Neg logit contributions
 face-0.126
vel-0.126
 makeup-0.123
 spit-0.120
 blush-0.115
Token soared
Token ID35292
Feature activation+1.79e-01

Pos logit contributions
rob+0.770
 Hipp+0.713
zag+0.709
 Hero+0.681
girls+0.673
Neg logit contributions
vel-0.466
 makeup-0.464
 face-0.464
 spit-0.454
 blush-0.425
Token in
Token ID287
Feature activation+1.79e-02

Pos logit contributions
rob+0.421
 Hipp+0.383
girls+0.370
zag+0.368
 Hero+0.367
Neg logit contributions
 face-0.194
vel-0.191
 makeup-0.186
 her-0.179
She-0.175
Token the
Token ID262
Feature activation+4.58e-02

Pos logit contributions
rob+0.039
zag+0.036
 Hipp+0.036
 Hero+0.035
girls+0.034
Neg logit contributions
 makeup-0.021
vel-0.021
 face-0.021
 spit-0.021
 blush-0.019
Token sky
Token ID6766
Feature activation+8.31e-02

Pos logit contributions
rob+0.079
zag+0.073
 Hipp+0.072
 steep+0.068
 Hero+0.068
Neg logit contributions
vel-0.076
 makeup-0.075
 spit-0.074
 face-0.073
 blush-0.070
Token.
Token ID13
Feature activation-4.98e-03

Pos logit contributions
rob+0.217
 Hipp+0.201
zag+0.198
 Hero+0.195
girls+0.193
Neg logit contributions
 face-0.067
vel-0.066
 makeup-0.064
 spit-0.061
 blush-0.055
Token hill
Token ID12788
Feature activation+8.04e-02

Pos logit contributions
rob+0.095
zag+0.089
 Hipp+0.088
 steep+0.085
 Hero+0.084
Neg logit contributions
vel-0.070
 spit-0.069
 makeup-0.069
 face-0.067
 blush-0.065
Token in
Token ID287
Feature activation+1.63e-02

Pos logit contributions
rob+0.207
 Hipp+0.190
girls+0.182
 Hero+0.180
zag+0.178
Neg logit contributions
 face-0.071
vel-0.066
 makeup-0.065
 her-0.063
 hand-0.059
Token a
Token ID257
Feature activation-1.10e-02

Pos logit contributions
rob+0.032
zag+0.030
 Hipp+0.030
 Hero+0.029
 steep+0.029
Neg logit contributions
vel-0.023
 makeup-0.022
 spit-0.022
 face-0.022
 blush-0.021
Token z
Token ID1976
Feature activation+1.32e-01

Pos logit contributions
 makeup+0.014
vel+0.014
 spit+0.014
 face+0.014
 blush+0.014
Neg logit contributions
rob-0.022
zag-0.021
 steep-0.021
 Hipp-0.021
 Hero-0.020
Tokenig
Token ID328
Feature activation+8.62e-02

Pos logit contributions
rob+0.230
zag+0.222
 Hipp+0.202
 Zig+0.196
 steep+0.193
Neg logit contributions
 spit-0.219
 makeup-0.219
vel-0.212
 face-0.212
 blush-0.204
Tokenzag
Token ID50183
Feature activation+3.67e-01

Pos logit contributions
rob+0.047
 Hipp+0.038
 Hero+0.030
 Skip+0.024
girls+0.024
Neg logit contributions
vel-0.245
 face-0.245
 makeup-0.237
She-0.233
 spit-0.232
Token pattern
Token ID3912
Feature activation+2.93e-02

Pos logit contributions
rob+0.757
 Hipp+0.711
 Hero+0.670
girls+0.661
zag+0.660
Neg logit contributions
 face-0.502
vel-0.479
 makeup-0.475
 spit-0.465
 blush-0.435
Token.
Token ID13
Feature activation-6.39e-03

Pos logit contributions
rob+0.069
zag+0.066
 Hipp+0.065
 Hero+0.062
 steep+0.062
Neg logit contributions
vel-0.029
 makeup-0.029
 face-0.028
 spit-0.028
 blush-0.025
Token
Token ID198
Feature activation+9.92e-03

Pos logit contributions
 makeup+0.008
 face+0.008
vel+0.008
She+0.008
 spit+0.008
Neg logit contributions
rob-0.014
zag-0.013
 steep-0.012
girls-0.012
 Hipp-0.012
Token
Token ID198
Feature activation+1.06e-02

Pos logit contributions
rob+0.020
zag+0.019
 Hipp+0.018
 Hero+0.018
girls+0.017
Neg logit contributions
vel-0.013
 makeup-0.013
 face-0.013
 spit-0.013
 blush-0.012
TokenWhen
Token ID2215
Feature activation-6.01e-03

Pos logit contributions
rob+0.022
zag+0.021
 Hipp+0.021
 Zig+0.020
 Hero+0.020
Neg logit contributions
 face-0.014
 makeup-0.014
 spit-0.013
vel-0.013
 blush-0.012
Token fly
Token ID6129
Feature activation+1.03e-01

Pos logit contributions
rob+0.074
zag+0.070
 Hipp+0.069
 Hero+0.067
 steep+0.066
Neg logit contributions
vel-0.036
 makeup-0.035
 face-0.035
 spit-0.034
 blush-0.032
Token like
Token ID588
Feature activation-1.31e-03

Pos logit contributions
rob+0.254
 Hipp+0.232
girls+0.224
zag+0.223
 Hero+0.218
Neg logit contributions
 her-0.099
 face-0.097
 makeup-0.095
vel-0.095
She-0.086
Token the
Token ID262
Feature activation+4.62e-02

Pos logit contributions
 makeup+0.002
 face+0.001
vel+0.001
 spit+0.001
 her+0.001
Neg logit contributions
rob-0.003
zag-0.003
 Hipp-0.003
girls-0.003
 steep-0.003
Token z
Token ID1976
Feature activation+1.34e-01

Pos logit contributions
rob+0.090
zag+0.084
 Hipp+0.083
 Hero+0.079
 steep+0.078
Neg logit contributions
vel-0.065
 makeup-0.065
 face-0.064
 spit-0.063
 blush-0.060
Tokenig
Token ID328
Feature activation+8.70e-02

Pos logit contributions
rob+0.262
 Hipp+0.242
zag+0.242
 Hero+0.231
girls+0.228
Neg logit contributions
vel-0.191
 makeup-0.190
 face-0.187
 spit-0.184
 blush-0.175
Tokenzag
Token ID50183
Feature activation+3.67e-01

Pos logit contributions
rob+0.051
 Hipp+0.037
 Hero+0.031
girls+0.027
 Skip+0.024
Neg logit contributions
vel-0.246
 face-0.243
 makeup-0.239
She-0.232
 her-0.232
Token if
Token ID611
Feature activation+4.53e-02

Pos logit contributions
rob+0.781
 Hipp+0.719
zag+0.687
 Hero+0.686
girls+0.677
Neg logit contributions
 face-0.474
vel-0.467
 makeup-0.460
 spit-0.445
 blush-0.418
Token he
Token ID339
Feature activation+3.75e-02

Pos logit contributions
rob+0.095
zag+0.084
girls+0.081
 Hipp+0.078
 Hero+0.075
Neg logit contributions
 makeup-0.062
 her-0.061
 face-0.061
 spit-0.059
vel-0.058
Token just
Token ID655
Feature activation+9.68e-02

Pos logit contributions
rob+0.083
 Hipp+0.075
zag+0.074
 Hero+0.072
girls+0.071
Neg logit contributions
 spit-0.046
vel-0.044
 face-0.044
 makeup-0.042
 dust-0.040
Token opened
Token ID4721
Feature activation+3.82e-02

Pos logit contributions
rob+0.214
zag+0.194
 Hipp+0.194
girls+0.186
 Hero+0.185
Neg logit contributions
 face-0.120
 spit-0.118
 makeup-0.117
vel-0.116
 blush-0.108
Token his
Token ID465
Feature activation-8.98e-03

Pos logit contributions
rob+0.098
zag+0.090
 Hipp+0.088
girls+0.087
 Hero+0.083
Neg logit contributions
 her-0.038
 makeup-0.037
 face-0.035
vel-0.034
 dust-0.031
Token.
Token ID13
Feature activation-8.54e-03

Pos logit contributions
 face+0.022
 makeup+0.022
vel+0.021
 her+0.019
 blush+0.018
Neg logit contributions
rob-0.066
 Hipp-0.062
 Hero-0.060
zag-0.060
 steep-0.059
Token One
Token ID1881
Feature activation+1.44e-01

Pos logit contributions
She+0.009
 her+0.008
 She+0.008
Her+0.007
L+0.007
Neg logit contributions
rob-0.020
 roles-0.018
lights-0.018
zag-0.018
 common-0.017
Token day
Token ID1110
Feature activation+1.12e-02

Pos logit contributions
rob+0.285
 Hipp+0.255
girls+0.252
zag+0.251
 Hero+0.247
Neg logit contributions
 face-0.206
 makeup-0.203
vel-0.200
 spit-0.195
 her-0.191
Token,
Token ID11
Feature activation-2.47e-02

Pos logit contributions
rob+0.028
zag+0.026
girls+0.025
 steep+0.024
 habitats+0.024
Neg logit contributions
 her-0.010
vel-0.009
 face-0.009
 makeup-0.009
 spit-0.009
Token Zig
Token ID24992
Feature activation+2.93e-01

Pos logit contributions
 her+0.050
She+0.047
 face+0.046
 little+0.045
 spit+0.045
Neg logit contributions
rob-0.035
zag-0.031
girls-0.028
 habitats-0.027
lights-0.027
Tokenzag
Token ID50183
Feature activation+3.66e-01

Pos logit contributions
rob+0.324
 Hipp+0.231
 Skip+0.209
 Hero+0.205
 steep+0.202
Neg logit contributions
vel-0.682
 face-0.675
She-0.660
ime-0.656
e-0.645
Token's
Token ID338
Feature activation-7.45e-03

Pos logit contributions
rob+0.781
 Hipp+0.722
zag+0.718
 Hero+0.690
girls+0.684
Neg logit contributions
vel-0.450
 face-0.450
 makeup-0.448
 spit-0.441
 blush-0.407
Token owner
Token ID4870
Feature activation+5.52e-02

Pos logit contributions
vel+0.012
 makeup+0.011
 spit+0.011
 face+0.011
 blush+0.011
Neg logit contributions
rob-0.013
zag-0.013
 Hipp-0.013
 Hero-0.012
 Zig-0.012
Token wanted
Token ID2227
Feature activation-7.15e-02

Pos logit contributions
rob+0.105
zag+0.101
 Hipp+0.101
 Hero+0.097
 Zig+0.095
Neg logit contributions
vel-0.078
 makeup-0.076
 face-0.073
 spit-0.071
 blush-0.070
Token to
Token ID284
Feature activation+1.52e-02

Pos logit contributions
 makeup+0.085
 her+0.082
 face+0.079
 spit+0.074
 dust+0.073
Neg logit contributions
rob-0.167
zag-0.155
 Hipp-0.145
girls-0.143
 steep-0.142
Token take
Token ID1011
Feature activation-9.65e-02

Pos logit contributions
zag+0.031
 Hipp+0.031
rob+0.031
 Zig+0.030
 Hero+0.029
Neg logit contributions
vel-0.019
 makeup-0.016
prise-0.015
 blush-0.015
 spit-0.015
Token had
Token ID550
Feature activation+1.88e-02

Pos logit contributions
rob+0.020
zag+0.019
 Hipp+0.018
girls+0.018
 Hero+0.018
Neg logit contributions
 face-0.010
 spit-0.010
 makeup-0.010
vel-0.010
 blush-0.009
Token their
Token ID511
Feature activation+4.28e-02

Pos logit contributions
rob+0.043
zag+0.041
 Hipp+0.040
 Hero+0.038
girls+0.037
Neg logit contributions
 makeup-0.022
 face-0.021
 spit-0.021
vel-0.021
 her-0.019
Token own
Token ID898
Feature activation+3.98e-02

Pos logit contributions
rob+0.084
zag+0.075
 Hipp+0.075
 Hero+0.071
girls+0.070
Neg logit contributions
 makeup-0.064
 face-0.063
 spit-0.061
vel-0.060
 blush-0.057
Token z
Token ID1976
Feature activation+1.31e-01

Pos logit contributions
rob+0.083
 Hipp+0.075
zag+0.074
 Hero+0.072
girls+0.071
Neg logit contributions
 makeup-0.054
 face-0.053
vel-0.052
 spit-0.051
 blush-0.048
Tokenig
Token ID328
Feature activation+8.22e-02

Pos logit contributions
rob+0.251
 Hipp+0.232
zag+0.231
 Hero+0.221
 steep+0.218
Neg logit contributions
vel-0.190
 makeup-0.188
 face-0.185
 spit-0.182
 blush-0.173
Tokenzag
Token ID50183
Feature activation+3.65e-01

Pos logit contributions
rob+0.055
 Hipp+0.044
 Hero+0.035
 steep+0.032
girls+0.031
Neg logit contributions
vel-0.224
 face-0.222
 makeup-0.221
 spit-0.214
 blush-0.211
Token.
Token ID13
Feature activation-3.49e-03

Pos logit contributions
rob+0.747
 Hipp+0.701
 Hero+0.654
zag+0.644
girls+0.644
Neg logit contributions
 face-0.505
 makeup-0.494
vel-0.487
 spit-0.469
 blush-0.443
Token
Token ID198
Feature activation+1.11e-02

Pos logit contributions
She+0.003
 her+0.003
 hand+0.002
 face+0.002
Her+0.002
Neg logit contributions
rob-0.009
zag-0.009
 steep-0.008
 aboard-0.008
lights-0.008
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
rob+0.030
zag+0.028
 Hipp+0.027
 steep+0.027
girls+0.027
Neg logit contributions
She-0.007
vel-0.007
 face-0.007
 her-0.007
Her-0.007
TokenThe
Token ID464
Feature activation+3.71e-02

Pos logit contributions
rob+0.025
zag+0.023
 Hipp+0.022
girls+0.022
 steep+0.022
Neg logit contributions
vel-0.014
She-0.013
 spit-0.013
Her-0.013
 makeup-0.013
Token two
Token ID734
Feature activation+2.89e-02

Pos logit contributions
rob+0.074
zag+0.068
 Hipp+0.067
 Hero+0.063
girls+0.063
Neg logit contributions
 makeup-0.052
 face-0.052
vel-0.051
 spit-0.051
 blush-0.048
Token can
Token ID460
Feature activation+1.14e-02

Pos logit contributions
rob+0.053
zag+0.049
 Hipp+0.049
 Hero+0.046
girls+0.046
Neg logit contributions
vel-0.045
 makeup-0.045
 face-0.044
 spit-0.043
 blush-0.041
Token make
Token ID787
Feature activation-3.23e-02

Pos logit contributions
rob+0.027
zag+0.026
 Hipp+0.026
 Hero+0.024
girls+0.024
Neg logit contributions
vel-0.011
 makeup-0.011
 spit-0.011
 face-0.011
 blush-0.010
Token the
Token ID262
Feature activation+4.65e-02

Pos logit contributions
vel+0.034
 makeup+0.034
 spit+0.034
 face+0.034
 blush+0.031
Neg logit contributions
rob-0.074
 Hipp-0.069
zag-0.069
 Hero-0.066
 Zig-0.065
Token z
Token ID1976
Feature activation+1.28e-01

Pos logit contributions
rob+0.091
zag+0.085
 Hipp+0.085
 Hero+0.081
 steep+0.080
Neg logit contributions
vel-0.064
 makeup-0.062
 spit-0.061
 face-0.061
 blush-0.058
Tokenig
Token ID328
Feature activation+8.40e-02

Pos logit contributions
rob+0.214
 Hipp+0.206
 Hero+0.197
 steep+0.197
girls+0.192
Neg logit contributions
vel-0.212
 face-0.204
 makeup-0.198
 spit-0.195
prise-0.193
Tokenzag
Token ID50183
Feature activation+3.65e-01

Pos logit contributions
rob+0.158
 Hipp+0.145
 Hero+0.138
girls+0.134
 Skip+0.132
Neg logit contributions
 face-0.129
vel-0.129
 makeup-0.126
 spit-0.122
 blush-0.117
Token another
Token ID1194
Feature activation+1.22e-01

Pos logit contributions
rob+0.762
 Hipp+0.704
zag+0.686
 Hero+0.672
girls+0.661
Neg logit contributions
vel-0.475
 face-0.474
 makeup-0.466
 spit-0.457
 blush-0.427
Token day
Token ID1110
Feature activation+1.49e-02

Pos logit contributions
rob+0.253
 Hipp+0.231
zag+0.227
 Hero+0.223
girls+0.222
Neg logit contributions
 face-0.164
vel-0.163
 makeup-0.162
 spit-0.157
 blush-0.147
Token.
Token ID13
Feature activation-5.39e-03

Pos logit contributions
rob+0.031
zag+0.029
 Hipp+0.029
 Hero+0.027
 Zig+0.027
Neg logit contributions
vel-0.019
 makeup-0.019
 face-0.019
 spit-0.018
 blush-0.017
Token I
Token ID314
Feature activation-2.34e-02

Pos logit contributions
 face+0.006
vel+0.006
She+0.006
 makeup+0.006
 hand+0.006
Neg logit contributions
rob-0.013
zag-0.011
 steep-0.010
ahs-0.010
 Hipp-0.010
Token'm
Token ID1101
Feature activation-9.71e-03

Pos logit contributions
vel+0.034
 makeup+0.033
 face+0.033
 spit+0.033
 blush+0.031
Neg logit contributions
rob-0.046
 Hipp-0.042
zag-0.042
 Hero-0.040
girls-0.039
Token hanging
Token ID10938
Feature activation+3.60e-02

Pos logit contributions
rob+0.070
 Hipp+0.066
zag+0.065
 Hero+0.063
 Zig+0.062
Neg logit contributions
vel-0.043
 makeup-0.042
 spit-0.042
 face-0.042
prise-0.040
Token from
Token ID422
Feature activation+4.70e-02

Pos logit contributions
rob+0.078
zag+0.073
 Hipp+0.072
 Hero+0.069
 steep+0.068
Neg logit contributions
vel-0.043
 makeup-0.043
 face-0.043
 spit-0.042
 blush-0.039
Token the
Token ID262
Feature activation+4.41e-02

Pos logit contributions
rob+0.109
zag+0.103
 Hipp+0.101
girls+0.097
 Hero+0.096
Neg logit contributions
 makeup-0.051
 face-0.049
vel-0.048
 spit-0.048
 her-0.046
Token z
Token ID1976
Feature activation+1.30e-01

Pos logit contributions
rob+0.081
 Hipp+0.078
zag+0.077
 steep+0.075
 Hero+0.074
Neg logit contributions
vel-0.068
 spit-0.062
 makeup-0.062
 face-0.060
prise-0.060
Tokenig
Token ID328
Feature activation+8.31e-02

Pos logit contributions
rob+0.248
 Hipp+0.230
zag+0.229
 Hero+0.218
girls+0.215
Neg logit contributions
vel-0.191
 makeup-0.189
 face-0.188
 spit-0.184
 blush-0.174
Tokenzag
Token ID50183
Feature activation+3.64e-01

Pos logit contributions
rob+0.145
zag+0.133
 Hipp+0.132
 Hero+0.125
girls+0.123
Neg logit contributions
vel-0.134
 makeup-0.134
 face-0.133
 spit-0.131
 blush-0.125
Token.
Token ID13
Feature activation-6.40e-03

Pos logit contributions
rob+0.718
zag+0.691
 Hipp+0.666
 steep+0.642
 Hero+0.636
Neg logit contributions
vel-0.497
 makeup-0.493
 spit-0.484
 face-0.476
 blush-0.452
Token M
Token ID337
Feature activation-7.25e-03

Pos logit contributions
 face+0.010
 spit+0.010
vel+0.009
 makeup+0.009
She+0.009
Neg logit contributions
rob-0.013
zag-0.011
 Hipp-0.011
girls-0.011
 steep-0.010
Tokenomm
Token ID2002
Feature activation+3.98e-02

Pos logit contributions
vel+0.009
 makeup+0.009
 face+0.009
 spit+0.009
 blush+0.009
Neg logit contributions
rob-0.015
zag-0.014
 Hipp-0.014
 Zig-0.013
 steep-0.013
Tokena
Token ID64
Feature activation+4.08e-02

Pos logit contributions
zag+0.085
rob+0.085
 Hipp+0.080
girls+0.077
 Zig+0.076
Neg logit contributions
 makeup-0.049
vel-0.044
 face-0.044
 blush-0.043
 spit-0.043
Token repeated
Token ID5100
Feature activation+1.29e-01

Pos logit contributions
rob+0.082
zag+0.077
 Hipp+0.076
 Hero+0.073
girls+0.072
Neg logit contributions
vel-0.054
 makeup-0.054
 face-0.053
 spit-0.052
 blush-0.050
Token side
Token ID1735
Feature activation-3.58e-02

Pos logit contributions
rob+0.047
zag+0.044
 Hipp+0.044
 Hero+0.042
girls+0.041
Neg logit contributions
vel-0.023
 makeup-0.023
 face-0.023
 spit-0.022
 blush-0.021
Token of
Token ID286
Feature activation-7.13e-02

Pos logit contributions
vel+0.043
 spit+0.042
 makeup+0.042
 face+0.041
 blush+0.039
Neg logit contributions
rob-0.076
zag-0.073
 Hipp-0.073
 Hero-0.070
 Zig-0.070
Token the
Token ID262
Feature activation+4.89e-02

Pos logit contributions
vel+0.093
 makeup+0.090
 face+0.090
 spit+0.089
 blush+0.084
Neg logit contributions
rob-0.149
 Hipp-0.139
zag-0.138
 Hero-0.133
 steep-0.131
Token z
Token ID1976
Feature activation+1.31e-01

Pos logit contributions
rob+0.081
 Hipp+0.076
zag+0.074
 steep+0.073
 Hero+0.070
Neg logit contributions
vel-0.087
 makeup-0.082
 spit-0.082
 face-0.081
 blush-0.079
Tokenig
Token ID328
Feature activation+8.26e-02

Pos logit contributions
rob+0.218
zag+0.203
 Hipp+0.193
 Zig+0.180
girls+0.180
Neg logit contributions
 makeup-0.230
 spit-0.228
vel-0.226
 face-0.225
 blush-0.216
Tokenzag
Token ID50183
Feature activation+3.64e-01

Pos logit contributions
rob+0.174
 Hipp+0.161
 Hero+0.153
zag+0.152
girls+0.150
Neg logit contributions
vel-0.107
 face-0.107
 makeup-0.103
 spit-0.100
 blush-0.094
Token,
Token ID11
Feature activation-1.97e-02

Pos logit contributions
rob+0.729
zag+0.677
 Hipp+0.674
 Hero+0.641
girls+0.633
Neg logit contributions
vel-0.494
 makeup-0.491
 face-0.486
 spit-0.479
 blush-0.450
Token to
Token ID284
Feature activation+1.91e-02

Pos logit contributions
vel+0.023
 makeup+0.023
 face+0.023
 spit+0.022
 blush+0.021
Neg logit contributions
rob-0.043
zag-0.041
 Hipp-0.040
 Hero-0.039
girls-0.038
Token the
Token ID262
Feature activation+4.75e-02

Pos logit contributions
rob+0.043
zag+0.040
 Hipp+0.040
 Hero+0.039
 steep+0.038
Neg logit contributions
vel-0.021
 makeup-0.021
 face-0.021
 spit-0.021
 blush-0.019
Token other
Token ID584
Feature activation+2.41e-02

Pos logit contributions
rob+0.090
 Hipp+0.086
zag+0.085
 steep+0.082
 Hero+0.081
Neg logit contributions
vel-0.070
 makeup-0.068
 spit-0.065
 face-0.064
prise-0.063
Token side
Token ID1735
Feature activation-3.74e-02

Pos logit contributions
rob+0.043
 Hipp+0.043
 Zig+0.040
 steep+0.040
zag+0.040
Neg logit contributions
vel-0.039
 makeup-0.038
prise-0.037
 spit-0.036
 blush-0.036
Token the
Token ID262
Feature activation+4.53e-02

Pos logit contributions
 Hipp+0.012
 Zig+0.012
 aboard+0.011
 Hero+0.011
zag+0.011
Neg logit contributions
prise-0.014
vel-0.013
aky-0.012
 spit-0.012
P-0.012
Token rain
Token ID6290
Feature activation+4.43e-02

Pos logit contributions
 Hipp+0.085
rob+0.084
zag+0.082
 steep+0.079
 Zig+0.076
Neg logit contributions
vel-0.067
 makeup-0.059
 spit-0.059
prise-0.058
 face-0.058
Tokendrops
Token ID49253
Feature activation+1.45e-01

Pos logit contributions
rob+0.083
zag+0.082
 Hipp+0.078
 steep+0.076
 Zig+0.075
Neg logit contributions
vel-0.065
 makeup-0.063
 spit-0.062
prise-0.060
 face-0.060
Token z
Token ID1976
Feature activation+1.31e-01

Pos logit contributions
zag+0.286
rob+0.280
 steep+0.273
 Hipp+0.270
 Zig+0.263
Neg logit contributions
vel-0.189
 makeup-0.186
prise-0.184
 spit-0.178
 face-0.171
Tokenig
Token ID328
Feature activation+8.38e-02

Pos logit contributions
zag+0.229
rob+0.229
 aboard+0.194
 Hipp+0.193
girls+0.187
Neg logit contributions
 spit-0.203
 face-0.201
 worry-0.196
 makeup-0.191
She-0.190
Tokenzag
Token ID50183
Feature activation+3.63e-01

Pos logit contributions
rob+0.146
zag+0.142
 Hipp+0.135
 Zig+0.128
 steep+0.127
Neg logit contributions
 makeup-0.133
vel-0.133
 spit-0.130
 face-0.129
prise-0.124
Token down
Token ID866
Feature activation+1.23e-02

Pos logit contributions
zag+0.695
rob+0.687
 Hipp+0.652
 steep+0.651
 Zig+0.633
Neg logit contributions
vel-0.497
 makeup-0.492
 spit-0.475
prise-0.469
 face-0.455
Token the
Token ID262
Feature activation+4.51e-02

Pos logit contributions
rob+0.028
zag+0.026
 Hipp+0.026
 Hero+0.025
 steep+0.025
Neg logit contributions
vel-0.014
 makeup-0.013
 face-0.013
 spit-0.013
 blush-0.012
Token window
Token ID4324
Feature activation-4.45e-02

Pos logit contributions
rob+0.085
zag+0.079
 Hipp+0.079
 Hero+0.075
 steep+0.074
Neg logit contributions
vel-0.067
 makeup-0.066
 face-0.065
 spit-0.065
 blush-0.061
Token.
Token ID13
Feature activation-6.36e-03

Pos logit contributions
vel+0.057
 makeup+0.056
prise+0.055
 spit+0.054
 blush+0.049
Neg logit contributions
zag-0.090
rob-0.086
 Hipp-0.084
 steep-0.083
 Zig-0.080
Token She
Token ID1375
Feature activation-3.28e-02

Pos logit contributions
 makeup+0.007
 face+0.007
 spit+0.007
vel+0.006
 blush+0.006
Neg logit contributions
rob-0.015
zag-0.014
 Hipp-0.014
girls-0.013
 Hero-0.013
Token hill
Token ID12788
Feature activation+7.80e-02

Pos logit contributions
rob+0.080
zag+0.074
 Hipp+0.074
 Hero+0.070
 steep+0.069
Neg logit contributions
vel-0.058
 makeup-0.058
 face-0.057
 spit-0.057
 blush-0.053
Token and
Token ID290
Feature activation+1.62e-02

Pos logit contributions
rob+0.212
 Hipp+0.195
girls+0.191
zag+0.185
 Hero+0.184
Neg logit contributions
 face-0.056
 her-0.049
 makeup-0.049
 spit-0.047
vel-0.046
Token the
Token ID262
Feature activation+4.75e-02

Pos logit contributions
rob+0.042
zag+0.040
 Hipp+0.038
girls+0.036
xy+0.035
Neg logit contributions
 face-0.015
 spit-0.015
 her-0.015
 makeup-0.014
 dust-0.013
Token z
Token ID1976
Feature activation+1.29e-01

Pos logit contributions
rob+0.087
zag+0.081
 Hipp+0.079
 Hero+0.075
girls+0.075
Neg logit contributions
 makeup-0.073
 face-0.072
vel-0.071
 spit-0.071
 blush-0.067
Tokenig
Token ID328
Feature activation+8.19e-02

Pos logit contributions
rob+0.262
 Hipp+0.247
zag+0.243
 Hero+0.235
 steep+0.234
Neg logit contributions
vel-0.171
 makeup-0.168
 face-0.167
 spit-0.163
 blush-0.152
Tokenzag
Token ID50183
Feature activation+3.63e-01

Pos logit contributions
rob+0.102
 Hipp+0.090
girls+0.082
 Hero+0.082
 Skip+0.079
Neg logit contributions
 face-0.177
vel-0.173
 spit-0.165
 makeup-0.165
 her-0.164
Token path
Token ID3108
Feature activation+3.12e-02

Pos logit contributions
rob+0.765
 Hipp+0.702
 Hero+0.666
girls+0.661
 Skip+0.640
Neg logit contributions
 face-0.517
 spit-0.466
vel-0.454
 makeup-0.453
 dust-0.433
Token in
Token ID287
Feature activation+1.77e-02

Pos logit contributions
rob+0.083
 Hipp+0.077
girls+0.075
zag+0.074
 Hero+0.073
Neg logit contributions
 face-0.025
 her-0.022
 makeup-0.022
 spit-0.021
vel-0.021
Token the
Token ID262
Feature activation+5.12e-02

Pos logit contributions
rob+0.041
zag+0.038
 Hipp+0.037
girls+0.036
 Hero+0.036
Neg logit contributions
 makeup-0.019
 face-0.019
vel-0.019
 spit-0.019
 her-0.017
Token rear
Token ID8286
Feature activation+7.03e-02

Pos logit contributions
rob+0.097
zag+0.090
 Hipp+0.089
 Hero+0.085
 steep+0.084
Neg logit contributions
vel-0.076
 makeup-0.075
 face-0.074
 spit-0.074
 blush-0.070
Tokenview
Token ID1177
Feature activation-2.82e-02

Pos logit contributions
rob+0.152
 Hipp+0.144
 Hero+0.139
 Skip+0.136
girls+0.135
Neg logit contributions
 face-0.089
vel-0.081
 makeup-0.081
 spit-0.080
ime-0.076
Token he
Token ID339
Feature activation+3.50e-02

Pos logit contributions
rob+0.150
zag+0.138
 Hipp+0.134
girls+0.128
 steep+0.128
Neg logit contributions
 face-0.103
 makeup-0.103
vel-0.101
 spit-0.100
 blush-0.094
Token saw
Token ID2497
Feature activation-7.10e-02

Pos logit contributions
rob+0.085
 Hipp+0.079
zag+0.078
 Hero+0.074
 Zig+0.074
Neg logit contributions
 spit-0.035
 face-0.035
vel-0.034
 makeup-0.033
 blush-0.030
Token a
Token ID257
Feature activation-1.11e-02

Pos logit contributions
 makeup+0.068
 face+0.067
vel+0.066
 spit+0.066
 blush+0.059
Neg logit contributions
rob-0.173
zag-0.164
 Hipp-0.160
girls-0.154
 steep-0.154
Token z
Token ID1976
Feature activation+1.30e-01

Pos logit contributions
vel+0.015
 makeup+0.014
 spit+0.013
 blush+0.013
prise+0.013
Neg logit contributions
 steep-0.022
zag-0.022
 Hipp-0.021
rob-0.021
 Hero-0.020
Tokenig
Token ID328
Feature activation+8.23e-02

Pos logit contributions
zag+0.188
rob+0.188
 Hipp+0.163
 Zig+0.156
 Hero+0.155
Neg logit contributions
 makeup-0.251
 spit-0.248
vel-0.243
 face-0.239
 blush-0.234
Tokenzag
Token ID50183
Feature activation+3.63e-01

Pos logit contributions
rob+0.134
zag+0.129
 Hipp+0.121
 steep+0.115
 Zig+0.115
Neg logit contributions
 makeup-0.142
vel-0.140
 spit-0.138
 face-0.137
 blush-0.132
Token branch
Token ID8478
Feature activation+7.91e-02

Pos logit contributions
rob+0.682
zag+0.676
 steep+0.628
 Hipp+0.627
 Zig+0.604
Neg logit contributions
 makeup-0.523
vel-0.519
 spit-0.498
prise-0.492
 face-0.482
Token and
Token ID290
Feature activation+1.55e-02

Pos logit contributions
rob+0.182
zag+0.172
 Hipp+0.170
 Hero+0.163
 steep+0.163
Neg logit contributions
vel-0.084
 makeup-0.084
 face-0.081
 spit-0.081
 blush-0.075
Token decided
Token ID3066
Feature activation+1.62e-02

Pos logit contributions
rob+0.035
zag+0.032
 Hipp+0.032
girls+0.031
 Hero+0.030
Neg logit contributions
 spit-0.018
 face-0.018
 makeup-0.018
vel-0.018
 blush-0.017
Token to
Token ID284
Feature activation+1.82e-02

Pos logit contributions
rob+0.042
zag+0.037
girls+0.036
 Hipp+0.035
 Hero+0.033
Neg logit contributions
 face-0.018
 her-0.017
 makeup-0.016
vel-0.015
 spit-0.015
Token try
Token ID1949
Feature activation-5.58e-02

Pos logit contributions
zag+0.039
 Hipp+0.038
rob+0.038
 Zig+0.037
 Hero+0.037
Neg logit contributions
vel-0.021
 makeup-0.021
prise-0.019
 face-0.019
 spit-0.018
Token slide
Token ID10649
Feature activation+5.91e-02

Pos logit contributions
vel+0.139
 spit+0.130
 makeup+0.129
 face+0.123
 blush+0.123
Neg logit contributions
rob-0.163
 Hipp-0.154
 steep-0.150
zag-0.149
 Hero-0.146
Token with
Token ID351
Feature activation-1.20e-03

Pos logit contributions
rob+0.150
 Hipp+0.142
zag+0.139
girls+0.137
 Hero+0.137
Neg logit contributions
 makeup-0.050
 face-0.049
vel-0.047
 spit-0.046
 blush-0.042
Token a
Token ID257
Feature activation-9.68e-03

Pos logit contributions
vel+0.001
 makeup+0.001
 face+0.001
 spit+0.001
prise+0.001
Neg logit contributions
rob-0.003
 Hipp-0.003
zag-0.002
 steep-0.002
 Hero-0.002
Token z
Token ID1976
Feature activation+1.26e-01

Pos logit contributions
vel+0.014
 makeup+0.013
 spit+0.013
 face+0.012
prise+0.012
Neg logit contributions
rob-0.019
zag-0.018
 steep-0.018
 Hipp-0.018
 Hero-0.017
Tokenig
Token ID328
Feature activation+8.08e-02

Pos logit contributions
rob+0.209
zag+0.198
 Hipp+0.181
 Zig+0.171
 steep+0.170
Neg logit contributions
 makeup-0.220
vel-0.218
 spit-0.218
 face-0.213
 blush-0.206
Tokenzag
Token ID50183
Feature activation+3.63e-01

Pos logit contributions
rob+0.090
 Hipp+0.080
 Hero+0.074
girls+0.073
 Skip+0.070
Neg logit contributions
 face-0.185
vel-0.182
 makeup-0.180
 spit-0.177
 blush-0.172
Token shape
Token ID5485
Feature activation-7.67e-02

Pos logit contributions
rob+0.784
 Hipp+0.734
zag+0.715
 Hero+0.704
girls+0.696
Neg logit contributions
 face-0.443
 makeup-0.437
vel-0.434
 spit-0.428
 blush-0.398
Token.
Token ID13
Feature activation-2.39e-03

Pos logit contributions
vel+0.077
 makeup+0.076
 face+0.074
 spit+0.073
prise+0.068
Neg logit contributions
rob-0.180
zag-0.172
 Hipp-0.169
 steep-0.162
 Hero-0.161
Token Lily
Token ID20037
Feature activation-2.87e-02

Pos logit contributions
 makeup+0.003
 face+0.003
 spit+0.003
vel+0.003
 blush+0.003
Neg logit contributions
rob-0.005
zag-0.005
 steep-0.004
 Hipp-0.004
girls-0.004
Token wanted
Token ID2227
Feature activation-6.83e-02

Pos logit contributions
 face+0.032
vel+0.031
 spit+0.031
 makeup+0.031
 blush+0.028
Neg logit contributions
rob-0.066
 Hipp-0.061
zag-0.060
 Hero-0.058
girls-0.058
Token to
Token ID284
Feature activation+1.92e-02

Pos logit contributions
 makeup+0.083
 her+0.079
 face+0.074
 clean+0.068
 spit+0.068
Neg logit contributions
rob-0.164
zag-0.149
 Hipp-0.142
girls-0.140
 Hero-0.138
Token a
Token ID257
Feature activation-3.06e-02

Pos logit contributions
 makeup+0.003
 face+0.003
 spit+0.002
vel+0.002
 her+0.002
Neg logit contributions
rob-0.006
zag-0.006
 Hipp-0.006
girls-0.005
 Hero-0.005
Token big
Token ID1263
Feature activation-1.08e-01

Pos logit contributions
vel+0.033
 makeup+0.032
 face+0.032
 spit+0.031
 blush+0.029
Neg logit contributions
rob-0.071
zag-0.066
 Hipp-0.066
 Hero-0.063
girls-0.063
Token smile
Token ID8212
Feature activation-5.54e-02

Pos logit contributions
vel+0.121
 makeup+0.118
 spit+0.115
 face+0.115
 blush+0.107
Neg logit contributions
rob-0.244
zag-0.229
 Hipp-0.228
 Hero-0.219
 steep-0.217
Token on
Token ID319
Feature activation+3.35e-02

Pos logit contributions
vel+0.062
 makeup+0.061
 spit+0.060
 face+0.059
prise+0.057
Neg logit contributions
rob-0.123
zag-0.118
 Hipp-0.115
 Hero-0.111
 steep-0.109
Token his
Token ID465
Feature activation-3.02e-02

Pos logit contributions
rob+0.056
 Hipp+0.053
 Hero+0.052
zag+0.052
 Skip+0.050
Neg logit contributions
vel-0.055
prise-0.053
 makeup-0.053
 spit-0.050
 blush-0.049
Token face
Token ID1986
Feature activation-2.53e-01

Pos logit contributions
vel+0.012
prise+0.012
 makeup+0.010
She+0.008
 spit+0.008
Neg logit contributions
rob-0.086
zag-0.086
 Hipp-0.083
 Hero-0.083
 steep-0.081
Token and
Token ID290
Feature activation-6.00e-03

Pos logit contributions
vel+0.264
 makeup+0.262
 face+0.255
 spit+0.255
 blush+0.233
Neg logit contributions
rob-0.581
zag-0.551
 Hipp-0.546
 Hero-0.524
 steep-0.519
Token was
Token ID373
Feature activation+1.31e-02

Pos logit contributions
 face+0.008
 spit+0.007
 makeup+0.007
 her+0.007
 blush+0.007
Neg logit contributions
rob-0.013
zag-0.012
 Hipp-0.012
 steep-0.012
 Hero-0.011
Token carrying
Token ID6872
Feature activation+3.37e-03

Pos logit contributions
rob+0.032
zag+0.029
 Hipp+0.029
 Hero+0.028
girls+0.027
Neg logit contributions
 face-0.014
vel-0.014
 makeup-0.014
 spit-0.013
 blush-0.012
Token his
Token ID465
Feature activation-3.04e-02

Pos logit contributions
rob+0.007
 Hipp+0.006
 Hero+0.006
zag+0.006
 Zig+0.006
Neg logit contributions
vel-0.004
 spit-0.004
 makeup-0.004
 face-0.004
prise-0.004
Token own
Token ID898
Feature activation+1.81e-02

Pos logit contributions
 face+0.042
 makeup+0.040
 spit+0.039
vel+0.037
 hand+0.036
Neg logit contributions
rob-0.065
 Hipp-0.058
zag-0.058
 Zig-0.056
girls-0.055
Token felt
Token ID2936
Feature activation-3.51e-02

Pos logit contributions
 spit+0.024
 face+0.024
 makeup+0.023
vel+0.023
 blush+0.021
Neg logit contributions
rob-0.055
zag-0.051
 Hipp-0.051
girls-0.049
 Hero-0.049
Token a
Token ID257
Feature activation-2.98e-02

Pos logit contributions
vel+0.046
 makeup+0.041
prise+0.040
 spit+0.039
 face+0.039
Neg logit contributions
 Hipp-0.070
rob-0.070
 steep-0.069
 Zig-0.067
 Hero-0.066
Token breeze
Token ID28633
Feature activation-5.32e-02

Pos logit contributions
vel+0.046
 makeup+0.044
ily+0.042
prise+0.042
on+0.041
Neg logit contributions
 steep-0.055
 Hipp-0.047
zag-0.047
field-0.046
 camps-0.044
Token on
Token ID319
Feature activation+3.52e-02

Pos logit contributions
prise+0.070
 makeup+0.069
vel+0.069
 spit+0.067
 face+0.062
Neg logit contributions
zag-0.108
rob-0.105
 Hipp-0.101
 steep-0.096
 aboard-0.095
Token his
Token ID465
Feature activation-2.76e-02

Pos logit contributions
rob+0.054
 Hipp+0.054
 Hero+0.053
 Zig+0.052
 Zac+0.051
Neg logit contributions
vel-0.063
prise-0.061
 makeup-0.058
 spit-0.056
 blush-0.054
Token face
Token ID1986
Feature activation-2.53e-01

Pos logit contributions
prise+0.022
vel+0.022
illy+0.016
 spit+0.015
pped+0.015
Neg logit contributions
zag-0.069
 Hero-0.066
rob-0.065
 steep-0.064
 Zig-0.064
Token.
Token ID13
Feature activation-2.57e-02

Pos logit contributions
prise+0.332
vel+0.327
 makeup+0.317
 spit+0.313
 face+0.294
Neg logit contributions
zag-0.489
rob-0.479
 Hipp-0.470
 steep-0.453
 Hero-0.445
Token He
Token ID679
Feature activation-2.37e-02

Pos logit contributions
vel+0.046
 makeup+0.046
 face+0.046
 spit+0.045
 blush+0.043
Neg logit contributions
rob-0.041
zag-0.037
 Hipp-0.037
 Hero-0.034
girls-0.034
Token wondered
Token ID14028
Feature activation-3.71e-02

Pos logit contributions
 spit+0.026
 face+0.026
 makeup+0.026
vel+0.026
 blush+0.024
Neg logit contributions
rob-0.055
zag-0.051
 Hipp-0.050
girls-0.048
 Hero-0.048
Token what
Token ID644
Feature activation-5.80e-02

Pos logit contributions
vel+0.033
 makeup+0.032
 spit+0.031
 face+0.031
 blush+0.029
Neg logit contributions
rob-0.090
 Hipp-0.086
zag-0.085
 Hero-0.083
 Zig-0.083
Token it
Token ID340
Feature activation-2.13e-02

Pos logit contributions
 makeup+0.072
 face+0.071
 spit+0.070
vel+0.068
 her+0.065
Neg logit contributions
rob-0.125
zag-0.120
 Hipp-0.115
girls-0.111
 Hero-0.109
Token with
Token ID351
Feature activation-1.64e-02

Pos logit contributions
 face+0.009
vel+0.008
 makeup+0.008
 spit+0.008
 her+0.007
Neg logit contributions
rob-0.026
 Hipp-0.024
zag-0.024
girls-0.023
 Hero-0.023
Token a
Token ID257
Feature activation-3.16e-02

Pos logit contributions
vel+0.020
 makeup+0.019
 spit+0.018
 face+0.018
 blush+0.018
Neg logit contributions
rob-0.035
 Hipp-0.033
zag-0.032
 Hero-0.032
 Zig-0.032
Token smile
Token ID8212
Feature activation-5.33e-02

Pos logit contributions
vel+0.036
 makeup+0.035
 spit+0.034
 face+0.033
 blush+0.032
Neg logit contributions
rob-0.070
zag-0.067
 Hipp-0.066
 steep-0.064
 Hero-0.064
Token on
Token ID319
Feature activation+3.42e-02

Pos logit contributions
 makeup+0.056
vel+0.055
 spit+0.054
 face+0.053
 blush+0.049
Neg logit contributions
rob-0.123
zag-0.117
 Hipp-0.116
 Hero-0.111
 steep-0.110
Token his
Token ID465
Feature activation-3.15e-02

Pos logit contributions
rob+0.060
 Hipp+0.058
zag+0.055
 Hero+0.055
 Zig+0.054
Neg logit contributions
vel-0.054
 makeup-0.053
prise-0.051
 spit-0.051
 blush-0.050
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
vel+0.015
 makeup+0.015
 face+0.014
 spit+0.013
 blush+0.011
Neg logit contributions
rob-0.091
zag-0.087
 Hipp-0.086
 Hero-0.084
 steep-0.083
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
 makeup+0.260
vel+0.259
 spit+0.252
 face+0.244
prise+0.235
Neg logit contributions
rob-0.573
zag-0.554
 Hipp-0.546
 Hero-0.522
 steep-0.520
Token<|endoftext|>
Token ID50256
Feature activation-6.12e-02

Pos logit contributions
 face+0.028
She+0.027
vel+0.026
 her+0.026
 hand+0.025
Neg logit contributions
rob-0.054
zag-0.050
girls-0.047
 Hipp-0.046
 steep-0.045
TokenOne
Token ID3198
Feature activation+1.29e-01

Pos logit contributions
 makeup+0.086
vel+0.084
 face+0.081
She+0.079
 her+0.079
Neg logit contributions
rob-0.114
zag-0.111
 Hipp-0.106
 steep-0.105
girls-0.103
Token day
Token ID1110
Feature activation-7.98e-03

Pos logit contributions
rob+0.210
zag+0.197
 Hipp+0.194
 steep+0.183
 Hero+0.181
Neg logit contributions
vel-0.223
 makeup-0.220
 spit-0.216
 face-0.215
 blush-0.207
Token,
Token ID11
Feature activation-4.28e-02

Pos logit contributions
vel+0.010
 makeup+0.010
 spit+0.010
 face+0.009
 blush+0.009
Neg logit contributions
rob-0.017
 Hipp-0.016
zag-0.016
 Zig-0.015
 Hero-0.015
Token.
Token ID13
Feature activation-2.73e-02

Pos logit contributions
rob+0.267
zag+0.257
 Hipp+0.250
 Hero+0.246
 steep+0.244
Neg logit contributions
vel-0.136
 spit-0.128
 makeup-0.128
 face-0.123
prise-0.122
Token She
Token ID1375
Feature activation-5.67e-02

Pos logit contributions
vel+0.035
prise+0.032
 makeup+0.029
 spit+0.028
 face+0.027
Neg logit contributions
 Hipp-0.056
rob-0.054
 Zig-0.052
 Hero-0.052
zag-0.052
Token sees
Token ID7224
Feature activation-4.55e-02

Pos logit contributions
 makeup+0.095
 face+0.094
vel+0.094
 spit+0.093
 blush+0.088
Neg logit contributions
rob-0.097
zag-0.090
 Hipp-0.089
 Hero-0.083
girls-0.082
Token mom
Token ID1995
Feature activation-4.86e-02

Pos logit contributions
vel+0.067
prise+0.057
 face+0.056
 makeup+0.056
 spit+0.055
Neg logit contributions
rob-0.090
 Hipp-0.087
 Hero-0.082
 Zig-0.081
zag-0.080
Token's
Token ID338
Feature activation-2.88e-02

Pos logit contributions
vel+0.077
illy+0.074
P+0.073
prise+0.067
 goodness+0.065
Neg logit contributions
girls-0.074
ousel-0.071
zag-0.069
rob-0.067
 drives-0.066
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
vel+0.039
pped+0.034
She+0.033
P+0.033
prise+0.033
Neg logit contributions
zag-0.050
 fault-0.047
girls-0.046
 missions-0.045
 Hero-0.045
Token.
Token ID13
Feature activation-2.78e-02

Pos logit contributions
prise+0.396
vel+0.372
 goodness+0.332
 makeup+0.326
illy+0.322
Neg logit contributions
zag-0.420
 steep-0.391
 Hipp-0.382
rob-0.380
 Hero-0.367
Token She
Token ID1375
Feature activation-5.74e-02

Pos logit contributions
vel+0.037
prise+0.033
 makeup+0.030
 spit+0.029
aming+0.028
Neg logit contributions
 Hipp-0.057
rob-0.055
 Zig-0.053
 Hero-0.052
zag-0.052
Token is
Token ID318
Feature activation+1.93e-02

Pos logit contributions
vel+0.101
 makeup+0.098
 face+0.096
 spit+0.095
 blush+0.092
Neg logit contributions
rob-0.093
 Hipp-0.084
zag-0.084
 Hero-0.080
 steep-0.078
Token scared
Token ID12008
Feature activation+4.68e-02

Pos logit contributions
zag+0.031
 Hipp+0.031
rob+0.030
 Hero+0.029
 steep+0.029
Neg logit contributions
vel-0.029
 goodness-0.026
prise-0.025
illy-0.025
 file-0.025
Token.
Token ID13
Feature activation-2.82e-02

Pos logit contributions
lights+0.051
 Hipp+0.050
 steep+0.047
 tigers+0.045
 Hero+0.044
Neg logit contributions
prise-0.096
vel-0.096
 file-0.085
 spit-0.085
P-0.084
Token a
Token ID257
Feature activation-3.03e-02

Pos logit contributions
vel+0.025
 makeup+0.023
prise+0.023
 spit+0.023
 blush+0.022
Neg logit contributions
rob-0.027
 Hipp-0.026
 Hero-0.026
 Zig-0.025
 steep-0.025
Token big
Token ID1263
Feature activation-1.07e-01

Pos logit contributions
vel+0.039
 makeup+0.037
 spit+0.035
illy+0.035
Her+0.034
Neg logit contributions
 steep-0.059
zag-0.058
rob-0.058
 Hipp-0.056
 Hero-0.055
Token smile
Token ID8212
Feature activation-5.40e-02

Pos logit contributions
vel+0.142
 makeup+0.132
Her+0.132
 spit+0.131
She+0.130
Neg logit contributions
rob-0.209
 steep-0.204
 Hipp-0.202
zag-0.198
 Hero-0.197
Token on
Token ID319
Feature activation+3.41e-02

Pos logit contributions
 makeup+0.062
 spit+0.061
vel+0.060
prise+0.058
 face+0.058
Neg logit contributions
rob-0.118
zag-0.115
 Hipp-0.110
 Hero-0.107
 steep-0.104
Token his
Token ID465
Feature activation-3.00e-02

Pos logit contributions
 Hipp+0.050
rob+0.049
 Hero+0.048
zag+0.047
 Zig+0.046
Neg logit contributions
prise-0.060
vel-0.059
 makeup-0.058
 blush-0.054
 spit-0.054
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
prise+0.015
vel+0.014
 makeup+0.012
She+0.011
 spit+0.010
Neg logit contributions
zag-0.082
rob-0.081
 Hero-0.080
 Hipp-0.080
 Zig-0.078
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
vel+0.272
 makeup+0.271
 spit+0.267
prise+0.258
 face+0.254
Neg logit contributions
rob-0.550
zag-0.539
 Hipp-0.528
 Hero-0.504
 steep-0.501
Token
Token ID198
Feature activation-6.21e-03

Pos logit contributions
 face+0.032
 spit+0.030
She+0.029
vel+0.028
 hand+0.028
Neg logit contributions
rob-0.052
zag-0.046
 Hipp-0.046
girls-0.044
 Zig-0.043
Token
Token ID198
Feature activation-6.60e-03

Pos logit contributions
 face+0.007
vel+0.007
 spit+0.007
She+0.007
 makeup+0.007
Neg logit contributions
rob-0.014
 Hipp-0.013
zag-0.013
girls-0.012
 Hero-0.012
TokenThe
Token ID464
Feature activation+2.13e-02

Pos logit contributions
vel+0.009
 makeup+0.009
 face+0.009
 spit+0.009
 blush+0.008
Neg logit contributions
rob-0.013
zag-0.013
 Hipp-0.012
 Hero-0.012
girls-0.012
Token farmer
Token ID18739
Feature activation-4.26e-03

Pos logit contributions
rob+0.037
 Hipp+0.035
zag+0.034
 Hero+0.034
 steep+0.033
Neg logit contributions
vel-0.035
 makeup-0.034
 spit-0.033
 blush-0.033
 face-0.032
Token pe
Token ID613
Feature activation-2.33e-03

Pos logit contributions
 Hipp+0.042
rob+0.041
zag+0.041
 steep+0.040
 Claw+0.039
Neg logit contributions
vel-0.041
 makeup-0.035
 blush-0.035
She-0.035
prise-0.034
Tokenaches
Token ID3694
Feature activation+7.61e-02

Pos logit contributions
 makeup+0.004
 face+0.004
vel+0.004
 spit+0.004
 blush+0.004
Neg logit contributions
rob-0.004
zag-0.004
 Hipp-0.004
 steep-0.003
 Zig-0.003
Token and
Token ID290
Feature activation-5.37e-03

Pos logit contributions
rob+0.145
zag+0.144
 steep+0.140
 Hipp+0.135
 Hero+0.132
Neg logit contributions
vel-0.104
 makeup-0.101
 spit-0.099
prise-0.099
 face-0.095
Token made
Token ID925
Feature activation-2.63e-03

Pos logit contributions
vel+0.008
 makeup+0.007
prise+0.007
 face+0.007
ime+0.006
Neg logit contributions
rob-0.010
 Hipp-0.010
 Hero-0.009
girls-0.009
 Zig-0.009
Token a
Token ID257
Feature activation-3.17e-02

Pos logit contributions
vel+0.003
 makeup+0.003
 face+0.003
 spit+0.003
prise+0.003
Neg logit contributions
rob-0.006
 Hipp-0.005
zag-0.005
 Zig-0.005
 Hero-0.005
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
vel+0.043
 makeup+0.040
pped+0.040
illy+0.039
aming+0.038
Neg logit contributions
 steep-0.063
zag-0.061
 Hipp-0.058
 Zig-0.056
rob-0.056
Token.
Token ID13
Feature activation-2.99e-02

Pos logit contributions
prise+0.347
 makeup+0.331
vel+0.320
illy+0.319
 goodness+0.315
Neg logit contributions
zag-0.477
 Hipp-0.449
rob-0.433
 steep-0.424
girls-0.424
Token They
Token ID1119
Feature activation+2.55e-03

Pos logit contributions
 face+0.045
 spit+0.043
 hand+0.039
 her+0.038
 makeup+0.037
Neg logit contributions
rob-0.076
zag-0.062
ousel-0.056
ahs-0.056
 steep-0.053
Token did
Token ID750
Feature activation-3.05e-02

Pos logit contributions
rob+0.004
 Hipp+0.004
 steep+0.004
girls+0.004
 Hero+0.004
Neg logit contributions
vel-0.004
 makeup-0.003
prise-0.003
 goodness-0.003
ime-0.003
Token not
Token ID407
Feature activation+4.62e-02

Pos logit contributions
 face+0.042
 spit+0.042
 makeup+0.041
vel+0.040
 blush+0.038
Neg logit contributions
rob-0.066
 Hipp-0.059
zag-0.058
 Hero-0.055
girls-0.055
Token want
Token ID765
Feature activation-1.28e-01

Pos logit contributions
 steep+0.066
 Claw+0.065
 Hipp+0.065
 Hero+0.062
 common+0.061
Neg logit contributions
vel-0.072
aming-0.068
 goodness-0.067
Her-0.065
illy-0.065
Token a
Token ID257
Feature activation-3.18e-02

Pos logit contributions
vel+0.021
 makeup+0.019
 spit+0.019
prise+0.018
 face+0.018
Neg logit contributions
rob-0.035
 Hipp-0.035
 Hero-0.033
 Zig-0.033
 Skip-0.033
Token big
Token ID1263
Feature activation-1.09e-01

Pos logit contributions
vel+0.037
 makeup+0.037
 spit+0.035
 face+0.033
 blush+0.032
Neg logit contributions
rob-0.069
zag-0.067
 Hipp-0.065
 steep-0.064
 Hero-0.062
Token smile
Token ID8212
Feature activation-5.41e-02

Pos logit contributions
vel+0.125
 makeup+0.121
 spit+0.119
 face+0.113
prise+0.109
Neg logit contributions
rob-0.238
 Hipp-0.227
zag-0.226
 steep-0.219
 Hero-0.216
Token on
Token ID319
Feature activation+3.31e-02

Pos logit contributions
 makeup+0.068
 spit+0.068
prise+0.066
vel+0.065
 face+0.063
Neg logit contributions
zag-0.110
rob-0.110
 Hipp-0.104
 Zig-0.099
 Hero-0.098
Token her
Token ID607
Feature activation-7.58e-02

Pos logit contributions
 Hipp+0.081
 Zig+0.078
rob+0.076
zag+0.076
 Hero+0.075
Neg logit contributions
prise-0.028
vel-0.025
 makeup-0.023
 file-0.021
 spit-0.020
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
prise+0.035
vel+0.031
 makeup+0.030
 spit+0.026
She+0.025
Neg logit contributions
zag-0.212
rob-0.211
 Hipp-0.206
 Zig-0.203
 Hero-0.202
Token.
Token ID13
Feature activation-2.41e-02

Pos logit contributions
vel+0.280
 makeup+0.279
 spit+0.279
prise+0.273
 face+0.261
Neg logit contributions
rob-0.531
zag-0.531
 Hipp-0.515
 Zig-0.488
 steep-0.487
Token
Token ID220
Feature activation+5.38e-04

Pos logit contributions
vel+0.028
 makeup+0.027
 face+0.027
She+0.026
 spit+0.026
Neg logit contributions
rob-0.054
zag-0.051
 Hipp-0.049
 steep-0.048
girls-0.048
Token
Token ID628
Feature activation+5.42e-02

Pos logit contributions
rob+0.001
zag+0.001
 Hipp+0.001
 Hero+0.001
 steep+0.001
Neg logit contributions
vel-0.001
 makeup-0.001
 face-0.001
 spit-0.001
 blush-0.001
Token
Token ID198
Feature activation-8.24e-03

Pos logit contributions
rob+0.110
zag+0.103
 Hipp+0.101
 steep+0.097
 Hero+0.096
Neg logit contributions
vel-0.072
 makeup-0.072
 face-0.071
 spit-0.070
 blush-0.066
Token
Token ID198
Feature activation-8.20e-03

Pos logit contributions
vel+0.008
 makeup+0.008
 face+0.008
 spit+0.008
 blush+0.007
Neg logit contributions
rob-0.020
zag-0.018
 Hipp-0.018
 Hero-0.017
 steep-0.017
Token.
Token ID13
Feature activation-2.27e-02

Pos logit contributions
prise+0.101
vel+0.099
 makeup+0.098
 blush+0.091
 spit+0.089
Neg logit contributions
zag-0.134
rob-0.128
 steep-0.124
 Hipp-0.121
 Hero-0.118
Token He
Token ID679
Feature activation-2.25e-02

Pos logit contributions
vel+0.043
 makeup+0.042
 face+0.042
 spit+0.041
 blush+0.040
Neg logit contributions
rob-0.034
 Hipp-0.031
zag-0.031
 Hero-0.029
 Zig-0.028
Token saw
Token ID2497
Feature activation-9.32e-02

Pos logit contributions
vel+0.036
 makeup+0.035
prise+0.032
 blush+0.032
 goodness+0.032
Neg logit contributions
rob-0.039
 Hipp-0.037
 Hero-0.037
zag-0.037
 Zig-0.035
Token Tom
Token ID4186
Feature activation-1.39e-02

Pos logit contributions
vel+0.148
 face+0.132
 makeup+0.132
 spit+0.129
prise+0.129
Neg logit contributions
rob-0.177
 Hipp-0.165
 Hero-0.164
 Zig-0.158
zag-0.154
Token's
Token ID338
Feature activation-2.62e-02

Pos logit contributions
prise+0.024
P+0.023
illy+0.023
 makeup+0.022
 goodness+0.021
Neg logit contributions
zag-0.022
ousel-0.021
 Hero-0.020
 Zig-0.019
girls-0.018
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
prise+0.032
vel+0.032
illy+0.027
Her+0.027
She+0.027
Neg logit contributions
zag-0.053
 steep-0.051
 fault-0.049
 Hero-0.049
rob-0.048
Token and
Token ID290
Feature activation-3.68e-03

Pos logit contributions
prise+0.476
vel+0.399
illy+0.391
 goodness+0.388
 makeup+0.374
Neg logit contributions
zag-0.408
 steep-0.346
ahs-0.340
ousel-0.336
ller-0.335
Token knew
Token ID2993
Feature activation-1.08e-01

Pos logit contributions
vel+0.007
prise+0.007
 makeup+0.006
illy+0.006
ucky+0.006
Neg logit contributions
rob-0.005
 Zig-0.005
 Hipp-0.005
 Hero-0.005
 tigers-0.005
Token what
Token ID644
Feature activation-5.75e-02

Pos logit contributions
 makeup+0.113
 face+0.109
vel+0.109
 spit+0.107
 her+0.100
Neg logit contributions
rob-0.257
zag-0.243
 Hipp-0.237
girls-0.229
 Hero-0.227
Token had
Token ID550
Feature activation-6.12e-03

Pos logit contributions
 makeup+0.084
vel+0.084
 face+0.083
 spit+0.082
 blush+0.077
Neg logit contributions
rob-0.111
zag-0.103
 Hipp-0.102
 Hero-0.096
girls-0.096
Token happened
Token ID3022
Feature activation+2.87e-02

Pos logit contributions
vel+0.011
 spit+0.011
 face+0.011
 makeup+0.011
 blush+0.011
Neg logit contributions
rob-0.010
zag-0.009
 Hipp-0.008
 Hero-0.008
 Zig-0.008
Token feels
Token ID5300
Feature activation-5.97e-03

Pos logit contributions
 face+0.077
 spit+0.076
 her+0.076
 mirror+0.076
 cut+0.074
Neg logit contributions
 Hipp-0.104
rob-0.098
 Claw-0.098
zag-0.097
 Whale-0.096
Token the
Token ID262
Feature activation+2.93e-02

Pos logit contributions
vel+0.007
 makeup+0.007
 spit+0.007
 face+0.007
prise+0.006
Neg logit contributions
rob-0.013
 Hipp-0.012
 Hero-0.012
 steep-0.012
 Zig-0.012
Token wind
Token ID2344
Feature activation-5.67e-02

Pos logit contributions
rob+0.056
 steep+0.052
zag+0.052
 Hipp+0.051
 Hero+0.050
Neg logit contributions
vel-0.045
prise-0.041
 spit-0.040
 makeup-0.040
cloth-0.038
Token in
Token ID287
Feature activation+3.22e-03

Pos logit contributions
 makeup+0.067
vel+0.066
 spit+0.065
prise+0.063
 face+0.063
Neg logit contributions
rob-0.124
zag-0.122
 Hipp-0.116
 Hero-0.113
 aboard-0.113
Token his
Token ID465
Feature activation-2.74e-02

Pos logit contributions
rob+0.005
 Hipp+0.005
 Hero+0.005
 Zig+0.005
zag+0.005
Neg logit contributions
vel-0.006
prise-0.005
 makeup-0.005
 spit-0.005
 face-0.005
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
vel+0.035
prise+0.032
 spit+0.030
 makeup+0.028
illy+0.028
Neg logit contributions
rob-0.058
zag-0.057
 Hero-0.054
 Zig-0.053
 steep-0.053
Token and
Token ID290
Feature activation-4.19e-03

Pos logit contributions
prise+0.334
vel+0.327
 makeup+0.324
 spit+0.316
 face+0.297
Neg logit contributions
zag-0.489
rob-0.485
 Hipp-0.451
 steep-0.446
 Hero-0.445
Token the
Token ID262
Feature activation+2.84e-02

Pos logit contributions
 face+0.005
 makeup+0.005
 spit+0.005
 her+0.005
 blush+0.005
Neg logit contributions
rob-0.009
zag-0.009
 Hipp-0.009
girls-0.008
 Hero-0.008
Token pedals
Token ID42563
Feature activation+1.12e-01

Pos logit contributions
rob+0.049
 steep+0.046
 Hipp+0.046
 Hero+0.046
zag+0.045
Neg logit contributions
vel-0.048
prise-0.044
 spit-0.042
 makeup-0.041
cloth-0.040
Token under
Token ID739
Feature activation+3.38e-02

Pos logit contributions
rob+0.251
zag+0.236
 Hipp+0.234
 Hero+0.225
 steep+0.223
Neg logit contributions
vel-0.125
 makeup-0.124
 face-0.121
 spit-0.120
 blush-0.111
Token his
Token ID465
Feature activation-2.80e-02

Pos logit contributions
 Hero+0.046
rob+0.046
 Hipp+0.045
 Zig+0.045
 Zac+0.043
Neg logit contributions
vel-0.067
prise-0.066
 makeup-0.059
 spit-0.058
 blush-0.056
Token
Token ID198
Feature activation-5.28e-03

Pos logit contributions
vel+0.008
 makeup+0.008
 face+0.008
 spit+0.008
 blush+0.007
Neg logit contributions
rob-0.010
zag-0.009
 Hipp-0.009
 Hero-0.009
 Zig-0.009
TokenHer
Token ID9360
Feature activation-4.09e-02

Pos logit contributions
 spit+0.006
 makeup+0.006
 face+0.006
vel+0.006
 dust+0.006
Neg logit contributions
rob-0.011
zag-0.010
 Hero-0.010
 steep-0.010
 Skip-0.010
Token Mom
Token ID11254
Feature activation-8.34e-02

Pos logit contributions
vel+0.057
She+0.050
 makeup+0.050
 spit+0.048
prise+0.048
Neg logit contributions
rob-0.077
zag-0.077
 Hipp-0.076
 Hero-0.072
 steep-0.071
Token saw
Token ID2497
Feature activation-9.41e-02

Pos logit contributions
 makeup+0.132
vel+0.130
 face+0.123
 spit+0.123
prise+0.121
Neg logit contributions
rob-0.137
zag-0.137
 Hipp-0.135
 Hero-0.130
girls-0.126
Token her
Token ID607
Feature activation-7.48e-02

Pos logit contributions
vel+0.126
 spit+0.124
prise+0.121
 face+0.116
 toe+0.110
Neg logit contributions
rob-0.170
 Hero-0.160
 aboard-0.156
 Skip-0.153
 Claw-0.147
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
vel+0.090
prise+0.090
She+0.087
P+0.087
Her+0.084
Neg logit contributions
zag-0.143
 Hero-0.133
 Hipp-0.133
 steep-0.131
rob-0.131
Token and
Token ID290
Feature activation-3.62e-03

Pos logit contributions
prise+0.372
vel+0.347
 makeup+0.323
 spit+0.313
 goodness+0.312
Neg logit contributions
zag-0.464
 steep-0.420
rob-0.415
 Hipp-0.414
 Hero-0.401
Token said
Token ID531
Feature activation-1.54e-02

Pos logit contributions
vel+0.006
 makeup+0.006
prise+0.006
 face+0.005
 spit+0.005
Neg logit contributions
rob-0.006
 Hipp-0.006
zag-0.005
 Hero-0.005
 Zig-0.005
Token "
Token ID366
Feature activation-1.78e-03

Pos logit contributions
vel+0.017
 makeup+0.017
 face+0.017
 spit+0.017
 blush+0.015
Neg logit contributions
rob-0.034
 Hipp-0.032
zag-0.032
 Hero-0.031
 Zig-0.031
TokenLet
Token ID5756
Feature activation-5.60e-02

Pos logit contributions
 face+0.002
vel+0.002
 makeup+0.002
 spit+0.002
prise+0.002
Neg logit contributions
rob-0.004
zag-0.003
 Hipp-0.003
 Hero-0.003
 steep-0.003
Token me
Token ID502
Feature activation-1.33e-01

Pos logit contributions
vel+0.074
 makeup+0.070
 spit+0.070
 blush+0.069
prise+0.068
Neg logit contributions
rob-0.101
zag-0.098
 Hero-0.097
 Hipp-0.096
 Skip-0.095
Token It
Token ID632
Feature activation-6.20e-02

Pos logit contributions
 face+0.042
 spit+0.041
 makeup+0.041
vel+0.040
 blush+0.038
Neg logit contributions
rob-0.051
zag-0.046
 Hipp-0.045
girls-0.043
 Hero-0.043
Token hits
Token ID7127
Feature activation+1.45e-01

Pos logit contributions
 spit+0.091
 face+0.086
 dust+0.081
 spill+0.076
 cut+0.076
Neg logit contributions
rob-0.139
 Hipp-0.118
zag-0.117
 Hero-0.116
lot-0.113
Token Tom
Token ID4186
Feature activation-1.23e-02

Pos logit contributions
rob+0.282
 Hipp+0.268
 Zig+0.262
zag+0.262
 Hero+0.260
Neg logit contributions
vel-0.209
 makeup-0.196
 spit-0.194
prise-0.192
 face-0.190
Token in
Token ID287
Feature activation+7.50e-03

Pos logit contributions
 makeup+0.020
prise+0.020
illy+0.019
 blush+0.018
 spit+0.018
Neg logit contributions
zag-0.023
 Zig-0.019
 steep-0.019
 aboard-0.019
ousel-0.019
Token the
Token ID262
Feature activation+3.44e-02

Pos logit contributions
 Hipp+0.010
 Hero+0.010
 steep+0.010
 Zig+0.010
rob+0.009
Neg logit contributions
vel-0.015
prise-0.014
 blush-0.013
 makeup-0.013
illy-0.013
Token face
Token ID1986
Feature activation-2.52e-01

Pos logit contributions
rob+0.065
 steep+0.065
 Hipp+0.063
zag+0.062
 Zig+0.058
Neg logit contributions
vel-0.052
prise-0.043
 makeup-0.042
 blush-0.041
illy-0.040
Token.
Token ID13
Feature activation-2.82e-02

Pos logit contributions
prise+0.398
 makeup+0.394
vel+0.359
 blush+0.346
 spit+0.345
Neg logit contributions
zag-0.437
 steep-0.397
 Hipp-0.391
 Zac-0.371
 Zig-0.371
Token He
Token ID679
Feature activation-2.23e-02

Pos logit contributions
vel+0.049
 makeup+0.049
 face+0.048
 spit+0.047
 blush+0.046
Neg logit contributions
rob-0.046
zag-0.042
 Hipp-0.042
 Hero-0.040
 Zig-0.039
Token drops
Token ID10532
Feature activation-5.09e-02

Pos logit contributions
 spit+0.034
 face+0.034
 makeup+0.034
vel+0.033
 blush+0.032
Neg logit contributions
rob-0.042
zag-0.039
 Hipp-0.038
 Hero-0.036
 Zig-0.035
Token the
Token ID262
Feature activation+3.37e-02

Pos logit contributions
vel+0.113
prise+0.102
 makeup+0.098
ivering+0.095
 blush+0.094
Neg logit contributions
 Zig-0.064
 steep-0.062
 Hipp-0.062
 aboard-0.062
 Hero-0.061
Token shovel
Token ID33677
Feature activation-1.50e-01

Pos logit contributions
 steep+0.057
zag+0.057
rob+0.056
 Hipp+0.056
 aboard+0.052
Neg logit contributions
vel-0.057
Her-0.050
prise-0.049
 makeup-0.048
 blush-0.047
Token She
Token ID1375
Feature activation-5.43e-02

Pos logit contributions
vel+0.058
prise+0.055
 spit+0.052
 makeup+0.052
aming+0.050
Neg logit contributions
 Hipp-0.037
rob-0.036
 Zig-0.035
 Hero-0.034
zag-0.032
Token had
Token ID550
Feature activation-9.46e-03

Pos logit contributions
vel+0.096
 makeup+0.087
prise+0.084
 goodness+0.081
 blush+0.080
Neg logit contributions
rob-0.090
 Hipp-0.086
 Zig-0.083
 Hero-0.082
zag-0.081
Token shampoo
Token ID47259
Feature activation+7.19e-02

Pos logit contributions
vel+0.013
prise+0.011
 goodness+0.011
ime+0.011
 face+0.011
Neg logit contributions
rob-0.018
 steep-0.017
 Hipp-0.017
 Zig-0.017
 Hero-0.016
Token on
Token ID319
Feature activation+3.46e-02

Pos logit contributions
rob+0.148
zag+0.142
 Hipp+0.132
girls+0.131
 steep+0.130
Neg logit contributions
vel-0.093
prise-0.090
 spit-0.085
 face-0.084
 makeup-0.082
Token her
Token ID607
Feature activation-7.03e-02

Pos logit contributions
rob+0.069
 Hipp+0.066
 Zig+0.066
zag+0.065
 Hero+0.064
Neg logit contributions
prise-0.047
vel-0.047
 spit-0.041
 face-0.038
aming-0.038
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.080
prise+0.078
 makeup+0.068
 spit+0.067
She+0.064
Neg logit contributions
zag-0.152
rob-0.150
 Hipp-0.143
girls-0.142
 Hero-0.140
Token.
Token ID13
Feature activation-2.91e-02

Pos logit contributions
vel+0.310
prise+0.304
 makeup+0.294
 spit+0.292
 face+0.284
Neg logit contributions
zag-0.500
rob-0.497
 Hipp-0.476
 steep-0.469
 Hero-0.458
Token She
Token ID1375
Feature activation-5.49e-02

Pos logit contributions
vel+0.050
prise+0.046
 spit+0.044
 makeup+0.043
 face+0.042
Neg logit contributions
 Hipp-0.047
rob-0.046
 Zig-0.044
 Hero-0.044
zag-0.042
Token was
Token ID373
Feature activation+9.18e-03

Pos logit contributions
vel+0.096
 makeup+0.086
prise+0.084
 goodness+0.080
 face+0.079
Neg logit contributions
rob-0.093
 Hipp-0.086
 Hero-0.083
zag-0.082
 Zig-0.082
Token crying
Token ID13774
Feature activation-5.71e-02

Pos logit contributions
 Hipp+0.017
 steep+0.017
rob+0.016
zag+0.016
 Zig+0.016
Neg logit contributions
vel-0.012
prise-0.011
 file-0.011
 goodness-0.011
 makeup-0.010
Token.
Token ID13
Feature activation-2.94e-02

Pos logit contributions
prise+0.105
 makeup+0.097
vel+0.093
 blush+0.092
 lipstick+0.089
Neg logit contributions
 steep-0.082
rob-0.077
 Hipp-0.076
 Hero-0.076
zag-0.073
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
vel+0.024
 makeup+0.024
 face+0.023
 spit+0.023
 blush+0.021
Neg logit contributions
rob-0.063
zag-0.059
 Hipp-0.059
 Hero-0.056
girls-0.056
Token She
Token ID1375
Feature activation-5.20e-02

Pos logit contributions
vel+0.027
 makeup+0.026
 face+0.025
 spit+0.025
prise+0.024
Neg logit contributions
rob-0.042
 Hipp-0.041
zag-0.040
 Hero-0.040
 Zig-0.039
Token had
Token ID550
Feature activation-5.70e-03

Pos logit contributions
vel+0.079
 makeup+0.076
prise+0.072
 face+0.072
 blush+0.069
Neg logit contributions
rob-0.095
 Hipp-0.088
zag-0.087
 Hero-0.085
 steep-0.084
Token a
Token ID257
Feature activation-2.77e-02

Pos logit contributions
 makeup+0.006
vel+0.006
 face+0.006
 spit+0.006
 blush+0.006
Neg logit contributions
rob-0.013
zag-0.012
 Hipp-0.012
 Hero-0.011
girls-0.011
Token red
Token ID2266
Feature activation-9.07e-03

Pos logit contributions
vel+0.032
 spit+0.029
 makeup+0.028
 face+0.028
 blush+0.027
Neg logit contributions
rob-0.060
zag-0.059
 Hipp-0.057
 steep-0.056
 Hero-0.055
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.012
 spit+0.011
 makeup+0.011
prise+0.011
 blush+0.010
Neg logit contributions
rob-0.018
zag-0.018
 Hipp-0.018
 Hero-0.017
 Zig-0.016
Token and
Token ID290
Feature activation-2.79e-03

Pos logit contributions
vel+0.311
prise+0.308
 makeup+0.290
 spit+0.286
 face+0.281
Neg logit contributions
zag-0.511
rob-0.503
 Hipp-0.478
 steep-0.460
 Hero-0.458
Token a
Token ID257
Feature activation-2.80e-02

Pos logit contributions
vel+0.003
prise+0.003
 makeup+0.003
 face+0.003
 spit+0.003
Neg logit contributions
rob-0.006
 Hipp-0.006
zag-0.006
 Hero-0.006
 steep-0.006
Token hot
Token ID3024
Feature activation-6.09e-02

Pos logit contributions
vel+0.039
 makeup+0.034
prise+0.034
 spit+0.034
ime+0.033
Neg logit contributions
zag-0.053
rob-0.053
 steep-0.052
 Hipp-0.051
 Hero-0.049
Token head
Token ID1182
Feature activation-8.91e-02

Pos logit contributions
vel+0.085
 makeup+0.076
 spit+0.075
prise+0.075
She+0.073
Neg logit contributions
rob-0.123
zag-0.117
 Hipp-0.116
 Hero-0.108
 steep-0.107
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
vel+0.097
 makeup+0.094
 spit+0.090
 face+0.090
prise+0.089
Neg logit contributions
rob-0.198
zag-0.193
 Hipp-0.188
 Hero-0.179
 steep-0.178
Token a
Token ID257
Feature activation-3.11e-02

Pos logit contributions
 face+0.001
 makeup+0.001
vel+0.001
 her+0.001
 spit+0.001
Neg logit contributions
rob-0.003
zag-0.003
 Hipp-0.003
girls-0.003
 steep-0.003
Token big
Token ID1263
Feature activation-1.07e-01

Pos logit contributions
 makeup+0.034
 face+0.034
vel+0.033
 spit+0.032
prise+0.030
Neg logit contributions
rob-0.072
 Hipp-0.067
zag-0.067
girls-0.065
 Hero-0.063
Token smile
Token ID8212
Feature activation-5.31e-02

Pos logit contributions
vel+0.122
 makeup+0.121
 face+0.119
 spit+0.117
 blush+0.109
Neg logit contributions
rob-0.239
zag-0.224
 Hipp-0.223
 Hero-0.214
girls-0.211
Token on
Token ID319
Feature activation+3.43e-02

Pos logit contributions
vel+0.050
 face+0.049
 makeup+0.049
 spit+0.046
 blush+0.044
Neg logit contributions
rob-0.130
 Hipp-0.122
zag-0.120
 Hero-0.116
girls-0.116
Token his
Token ID465
Feature activation-2.94e-02

Pos logit contributions
rob+0.062
 Hipp+0.059
zag+0.057
 Hero+0.056
 Zig+0.055
Neg logit contributions
vel-0.052
 makeup-0.052
 spit-0.050
prise-0.049
 face-0.048
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.010
 makeup+0.009
prise+0.008
 spit+0.008
 blush+0.006
Neg logit contributions
rob-0.086
zag-0.085
 Hipp-0.083
 Hero-0.082
 Zig-0.081
Token.
Token ID13
Feature activation-2.29e-02

Pos logit contributions
vel+0.226
 makeup+0.223
 face+0.222
 spit+0.213
 blush+0.196
Neg logit contributions
rob-0.625
zag-0.583
 Hipp-0.583
 Hero-0.561
girls-0.556
Token He
Token ID679
Feature activation-2.06e-02

Pos logit contributions
 face+0.029
 her+0.026
She+0.025
 makeup+0.024
 hand+0.024
Neg logit contributions
rob-0.054
girls-0.048
zag-0.047
 Hipp-0.044
 steep-0.044
Token waved
Token ID26834
Feature activation+1.04e-01

Pos logit contributions
 face+0.020
 spit+0.019
 cut+0.017
 her+0.017
 dress+0.015
Neg logit contributions
rob-0.052
 Hipp-0.048
girls-0.048
zag-0.047
 Claw-0.046
Token and
Token ID290
Feature activation-3.89e-03

Pos logit contributions
rob+0.170
zag+0.153
 Hipp+0.148
girls+0.141
 steep+0.136
Neg logit contributions
 face-0.193
 makeup-0.187
vel-0.187
 spit-0.183
 her-0.177
Token waved
Token ID26834
Feature activation+1.04e-01

Pos logit contributions
 face+0.005
 her+0.005
 spit+0.004
 makeup+0.004
vel+0.004
Neg logit contributions
rob-0.009
zag-0.008
 Hipp-0.008
girls-0.008
 Hero-0.008
Token feel
Token ID1254
Feature activation-8.80e-02

Pos logit contributions
 face+0.001
 clean+0.001
 spit+0.001
 makeup+0.001
 wipe+0.001
Neg logit contributions
rob-0.004
 Hipp-0.004
zag-0.004
girls-0.004
 Hero-0.004
Token the
Token ID262
Feature activation+2.41e-02

Pos logit contributions
vel+0.113
 makeup+0.112
 face+0.109
 spit+0.109
 blush+0.103
Neg logit contributions
rob-0.182
 Hipp-0.172
zag-0.169
 Hero-0.164
 steep-0.162
Token wind
Token ID2344
Feature activation-5.70e-02

Pos logit contributions
rob+0.051
 Hipp+0.047
zag+0.047
 steep+0.046
 Hero+0.045
Neg logit contributions
vel-0.032
 makeup-0.030
 spit-0.029
prise-0.029
 face-0.028
Token on
Token ID319
Feature activation+3.46e-02

Pos logit contributions
 makeup+0.061
vel+0.061
 face+0.058
 spit+0.058
prise+0.056
Neg logit contributions
rob-0.130
zag-0.125
 Hipp-0.122
 Hero-0.117
 steep-0.116
Token his
Token ID465
Feature activation-3.00e-02

Pos logit contributions
 Hipp+0.046
rob+0.045
 Zig+0.044
 Hero+0.043
zag+0.042
Neg logit contributions
prise-0.070
vel-0.066
 makeup-0.062
 spit-0.061
 blush-0.060
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.022
prise+0.020
 makeup+0.020
 spit+0.019
 blush+0.017
Neg logit contributions
rob-0.079
zag-0.076
 Hipp-0.073
 Hero-0.073
 steep-0.073
Token.
Token ID13
Feature activation-2.35e-02

Pos logit contributions
 makeup+0.278
vel+0.277
 spit+0.270
prise+0.268
 face+0.262
Neg logit contributions
rob-0.543
zag-0.536
 Hipp-0.518
 steep-0.502
 Hero-0.500
Token
Token ID198
Feature activation-4.68e-03

Pos logit contributions
 face+0.035
 makeup+0.035
 spit+0.034
vel+0.033
She+0.032
Neg logit contributions
rob-0.045
zag-0.042
 Hipp-0.039
 Hero-0.039
girls-0.039
Token
Token ID198
Feature activation-5.03e-03

Pos logit contributions
vel+0.007
 makeup+0.006
 face+0.006
 spit+0.006
 blush+0.006
Neg logit contributions
rob-0.009
zag-0.008
 Hipp-0.008
 Hero-0.008
girls-0.008
TokenOne
Token ID3198
Feature activation+1.30e-01

Pos logit contributions
 makeup+0.010
 face+0.009
vel+0.009
 blush+0.009
 spit+0.009
Neg logit contributions
rob-0.007
 Hipp-0.007
zag-0.007
 steep-0.007
 Zig-0.006
Token day
Token ID1110
Feature activation-7.73e-03

Pos logit contributions
rob+0.213
zag+0.199
 Hipp+0.195
 steep+0.185
 Hero+0.183
Neg logit contributions
vel-0.229
 makeup-0.226
 spit-0.221
 face-0.220
 blush-0.212
Token a
Token ID257
Feature activation-3.07e-02

Pos logit contributions
 face+0.002
 makeup+0.002
 spit+0.002
vel+0.002
 blush+0.001
Neg logit contributions
rob-0.003
 Hipp-0.003
zag-0.003
girls-0.003
 Hero-0.003
Token big
Token ID1263
Feature activation-1.06e-01

Pos logit contributions
vel+0.038
 makeup+0.037
 spit+0.036
 face+0.035
 blush+0.034
Neg logit contributions
rob-0.064
zag-0.062
 Hipp-0.061
 steep-0.059
 Hero-0.058
Token smile
Token ID8212
Feature activation-5.31e-02

Pos logit contributions
vel+0.123
 makeup+0.121
 spit+0.118
 face+0.116
 blush+0.110
Neg logit contributions
rob-0.231
zag-0.218
 Hipp-0.216
 Hero-0.208
 steep-0.208
Token on
Token ID319
Feature activation+3.43e-02

Pos logit contributions
 makeup+0.063
vel+0.062
 spit+0.062
prise+0.061
 face+0.058
Neg logit contributions
rob-0.111
zag-0.110
 Hipp-0.104
 Hero-0.101
 steep-0.100
Token his
Token ID465
Feature activation-2.92e-02

Pos logit contributions
 Hipp+0.051
rob+0.050
 Hero+0.050
 Zig+0.048
zag+0.047
Neg logit contributions
prise-0.063
vel-0.059
 makeup-0.058
 blush-0.054
 spit-0.053
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
prise+0.016
 makeup+0.015
vel+0.013
She+0.012
 blush+0.011
Neg logit contributions
zag-0.079
rob-0.076
 Hero-0.076
 Hipp-0.075
 Zig-0.074
Token.
Token ID13
Feature activation-2.02e-02

Pos logit contributions
vel+0.282
 makeup+0.280
 spit+0.275
prise+0.272
 face+0.264
Neg logit contributions
rob-0.535
zag-0.527
 Hipp-0.512
 Hero-0.491
 steep-0.489
Token He
Token ID679
Feature activation-2.07e-02

Pos logit contributions
 face+0.032
vel+0.032
 makeup+0.032
 spit+0.031
 blush+0.029
Neg logit contributions
rob-0.037
zag-0.034
 Hipp-0.033
girls-0.032
 steep-0.031
Token remembered
Token ID12086
Feature activation+2.77e-03

Pos logit contributions
 spit+0.022
 face+0.022
vel+0.020
 makeup+0.019
 cut+0.019
Neg logit contributions
rob-0.050
zag-0.045
 Hipp-0.045
girls-0.044
 steep-0.043
Token his
Token ID465
Feature activation-2.94e-02

Pos logit contributions
rob+0.006
zag+0.006
 Hipp+0.006
 Hero+0.005
 steep+0.005
Neg logit contributions
vel-0.003
 makeup-0.003
 face-0.003
 spit-0.003
 blush-0.003
Token dream
Token ID4320
Feature activation+1.40e-02

Pos logit contributions
vel+0.038
 face+0.038
 makeup+0.038
 spit+0.037
 blush+0.034
Neg logit contributions
rob-0.062
 Hipp-0.057
zag-0.057
 Hero-0.054
girls-0.054
Token at
Token ID379
Feature activation-2.17e-02

Pos logit contributions
 face+0.017
 makeup+0.016
vel+0.016
 spit+0.015
 blush+0.014
Neg logit contributions
rob-0.064
zag-0.061
 Hipp-0.060
girls-0.058
 Zig-0.058
Token Lily
Token ID20037
Feature activation-5.34e-02

Pos logit contributions
 makeup+0.023
 face+0.023
vel+0.023
 spit+0.022
 blush+0.021
Neg logit contributions
rob-0.050
zag-0.047
 Hipp-0.047
 Hero-0.045
 steep-0.045
Token with
Token ID351
Feature activation-1.54e-02

Pos logit contributions
prise+0.077
 makeup+0.074
vel+0.072
 spit+0.071
 blush+0.069
Neg logit contributions
zag-0.097
rob-0.092
 Hero-0.092
 Hipp-0.090
ousel-0.088
Token a
Token ID257
Feature activation-3.09e-02

Pos logit contributions
vel+0.024
prise+0.020
 makeup+0.019
illy+0.019
ime+0.018
Neg logit contributions
rob-0.028
 Hero-0.028
 Hipp-0.026
 steep-0.026
 Skip-0.026
Token proud
Token ID6613
Feature activation+1.50e-02

Pos logit contributions
vel+0.039
 makeup+0.037
 spit+0.035
prise+0.034
 face+0.033
Neg logit contributions
rob-0.063
zag-0.061
 steep-0.060
 Hipp-0.058
 Hero-0.057
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
zag+0.027
rob+0.027
 steep+0.026
 Hipp+0.026
 Hero+0.025
Neg logit contributions
vel-0.019
pped-0.017
prise-0.017
 makeup-0.017
She-0.016
Token.
Token ID13
Feature activation-2.69e-02

Pos logit contributions
vel+0.249
 makeup+0.247
 face+0.240
 spit+0.238
 blush+0.218
Neg logit contributions
rob-0.593
zag-0.561
 Hipp-0.558
 Hero-0.536
girls-0.530
Token He
Token ID679
Feature activation-2.50e-02

Pos logit contributions
vel+0.048
 makeup+0.048
 face+0.048
 spit+0.047
 blush+0.045
Neg logit contributions
rob-0.043
zag-0.039
 Hipp-0.038
 Hero-0.036
girls-0.036
Token kissed
Token ID27946
Feature activation+2.92e-02

Pos logit contributions
 spit+0.029
 face+0.028
 makeup+0.027
vel+0.027
 blush+0.025
Neg logit contributions
rob-0.057
zag-0.054
 Hipp-0.053
girls-0.051
 Zig-0.050
Token her
Token ID607
Feature activation-7.43e-02

Pos logit contributions
 Hero+0.066
rob+0.065
 Zig+0.064
 Hipp+0.064
 Zac+0.062
Neg logit contributions
vel-0.030
prise-0.027
 spit-0.024
ime-0.022
 goodness-0.021
Token on
Token ID319
Feature activation+3.42e-02

Pos logit contributions
vel+0.081
 makeup+0.080
 spit+0.077
 face+0.076
prise+0.072
Neg logit contributions
rob-0.169
zag-0.161
 Hipp-0.159
 Hero-0.154
 steep-0.151
Token let
Token ID1309
Feature activation-4.06e-02

Pos logit contributions
vel+0.004
 makeup+0.004
 face+0.004
 spit+0.004
 blush+0.004
Neg logit contributions
rob-0.006
zag-0.005
 Hipp-0.005
 Hero-0.005
 steep-0.005
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
 makeup+0.047
vel+0.047
 spit+0.043
prise+0.043
 blush+0.043
Neg logit contributions
rob-0.089
 Hipp-0.085
zag-0.084
 Hero-0.082
 Zig-0.082
Token sunshine
Token ID34488
Feature activation-4.87e-02

Pos logit contributions
rob+0.041
 Hipp+0.039
girls+0.036
 Hero+0.036
 Zig+0.035
Neg logit contributions
vel-0.043
 makeup-0.040
prise-0.040
cloth-0.038
Her-0.038
Token warm
Token ID5814
Feature activation-9.35e-02

Pos logit contributions
vel+0.054
 makeup+0.051
prise+0.048
 spit+0.046
 lipstick+0.044
Neg logit contributions
zag-0.107
rob-0.105
 Hipp-0.104
 Zig-0.101
girls-0.100
Token his
Token ID465
Feature activation-2.99e-02

Pos logit contributions
vel+0.110
 makeup+0.106
 spit+0.103
 face+0.102
prise+0.098
Neg logit contributions
rob-0.207
 Hipp-0.195
zag-0.192
 Hero-0.185
 Zig-0.184
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.039
 makeup+0.036
prise+0.036
She+0.035
 blush+0.034
Neg logit contributions
 Hipp-0.059
zag-0.059
rob-0.058
 Hero-0.056
girls-0.056
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
vel+0.266
 makeup+0.263
 spit+0.251
 face+0.251
prise+0.237
Neg logit contributions
rob-0.566
zag-0.547
 Hipp-0.537
 steep-0.516
 Hero-0.514
Token It
Token ID632
Feature activation-6.63e-02

Pos logit contributions
 face+0.032
 makeup+0.030
 spit+0.029
vel+0.028
 her+0.027
Neg logit contributions
rob-0.048
zag-0.042
girls-0.040
 Hipp-0.038
 steep-0.038
Token felt
Token ID2936
Feature activation-3.30e-02

Pos logit contributions
 spit+0.076
 face+0.073
vel+0.067
 dust+0.066
 her+0.066
Neg logit contributions
rob-0.155
zag-0.143
 Hipp-0.143
girls-0.142
 Hero-0.139
Token really
Token ID1107
Feature activation-3.28e-02

Pos logit contributions
vel+0.041
 makeup+0.039
prise+0.037
 spit+0.036
 blush+0.036
Neg logit contributions
 Hipp-0.067
rob-0.066
 steep-0.065
 Zig-0.063
 Hero-0.062
Token good
Token ID922
Feature activation-4.03e-02

Pos logit contributions
vel+0.033
 makeup+0.033
 face+0.032
 spit+0.031
 blush+0.029
Neg logit contributions
rob-0.077
 Hipp-0.073
zag-0.072
 steep-0.070
 Hero-0.069
Token a
Token ID257
Feature activation-3.09e-02

Pos logit contributions
vel+0.026
 spit+0.022
ivering+0.021
 makeup+0.021
 file+0.021
Neg logit contributions
rob-0.029
 Hipp-0.029
 Hero-0.029
 Skip-0.028
 aboard-0.027
Token big
Token ID1263
Feature activation-1.08e-01

Pos logit contributions
vel+0.037
 spit+0.034
 makeup+0.033
 face+0.031
She+0.031
Neg logit contributions
rob-0.065
zag-0.064
 Hipp-0.062
 steep-0.062
 Hero-0.060
Token smile
Token ID8212
Feature activation-5.42e-02

Pos logit contributions
vel+0.140
 spit+0.128
 makeup+0.127
She+0.125
Her+0.122
Neg logit contributions
rob-0.218
zag-0.208
 Hipp-0.207
 steep-0.205
 Hero-0.202
Token on
Token ID319
Feature activation+3.33e-02

Pos logit contributions
 makeup+0.060
 spit+0.058
vel+0.058
 face+0.055
prise+0.054
Neg logit contributions
rob-0.121
zag-0.117
 Hipp-0.113
 Hero-0.109
 Zig-0.107
Token his
Token ID465
Feature activation-3.12e-02

Pos logit contributions
 Hipp+0.046
rob+0.043
 Hero+0.042
 Arnold+0.042
 Zac+0.042
Neg logit contributions
prise-0.061
vel-0.059
 makeup-0.056
 file-0.054
 spit-0.054
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.016
prise+0.016
 makeup+0.014
She+0.011
 spit+0.011
Neg logit contributions
zag-0.084
rob-0.082
 Hipp-0.081
 Hero-0.081
 Zig-0.080
Token.
Token ID13
Feature activation-2.75e-02

Pos logit contributions
vel+0.241
 makeup+0.240
 face+0.233
 spit+0.232
 blush+0.211
Neg logit contributions
rob-0.599
zag-0.568
 Hipp-0.564
 Hero-0.541
 steep-0.536
Token What
Token ID1867
Feature activation-8.89e-02

Pos logit contributions
 makeup+0.038
 face+0.037
vel+0.036
 spit+0.035
She+0.035
Neg logit contributions
rob-0.056
zag-0.053
 Hipp-0.048
 Hero-0.048
girls-0.048
Token a
Token ID257
Feature activation-3.19e-02

Pos logit contributions
vel+0.084
 makeup+0.084
 face+0.082
 spit+0.081
 blush+0.074
Neg logit contributions
rob-0.215
zag-0.203
 Hipp-0.202
 Hero-0.194
 steep-0.192
Token great
Token ID1049
Feature activation-1.53e-02

Pos logit contributions
vel+0.046
 makeup+0.043
 spit+0.043
 blush+0.042
cloth+0.041
Neg logit contributions
rob-0.058
 Hipp-0.056
 Hero-0.054
 steep-0.054
zag-0.053
Token day
Token ID1110
Feature activation-9.78e-03

Pos logit contributions
vel+0.021
 makeup+0.020
 spit+0.020
 face+0.019
 blush+0.019
Neg logit contributions
rob-0.031
zag-0.029
 Hipp-0.029
 Hero-0.028
 steep-0.027
Token with
Token ID351
Feature activation-1.69e-02

Pos logit contributions
 face+0.011
vel+0.010
 makeup+0.010
 spit+0.010
 her+0.009
Neg logit contributions
rob-0.029
 Hipp-0.027
zag-0.027
girls-0.026
 Hero-0.026
Token a
Token ID257
Feature activation-3.24e-02

Pos logit contributions
vel+0.020
 spit+0.018
 face+0.017
 makeup+0.016
 blush+0.016
Neg logit contributions
rob-0.038
 Hipp-0.036
 Hero-0.035
 Zig-0.035
 Skip-0.034
Token smile
Token ID8212
Feature activation-5.33e-02

Pos logit contributions
vel+0.033
 makeup+0.032
 spit+0.031
 face+0.030
 blush+0.028
Neg logit contributions
rob-0.076
zag-0.072
 Hipp-0.072
 steep-0.069
 Hero-0.069
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
 makeup+0.060
vel+0.059
 spit+0.059
 face+0.056
prise+0.054
Neg logit contributions
rob-0.118
zag-0.114
 Hipp-0.112
 Hero-0.107
 Zig-0.105
Token her
Token ID607
Feature activation-7.76e-02

Pos logit contributions
 Hipp+0.088
rob+0.084
 Zig+0.083
 Hero+0.082
 Skip+0.081
Neg logit contributions
vel-0.025
prise-0.023
 spit-0.021
 makeup-0.020
 file-0.019
Token face
Token ID1986
Feature activation-2.51e-01

Pos logit contributions
vel+0.016
 makeup+0.015
 spit+0.011
prise+0.008
 blush+0.007
Neg logit contributions
rob-0.242
zag-0.234
 Hipp-0.233
 Hero-0.226
 steep-0.225
Token.
Token ID13
Feature activation-2.08e-02

Pos logit contributions
vel+0.273
 makeup+0.271
 spit+0.269
 face+0.257
prise+0.252
Neg logit contributions
rob-0.553
zag-0.539
 Hipp-0.530
 Hero-0.504
 steep-0.502
Token
Token ID198
Feature activation-5.76e-03

Pos logit contributions
vel+0.031
 makeup+0.031
 face+0.030
 spit+0.030
 blush+0.028
Neg logit contributions
rob-0.039
zag-0.036
 Hipp-0.036
 Hero-0.034
 Zig-0.034
Token
Token ID198
Feature activation-6.10e-03

Pos logit contributions
 makeup+0.008
vel+0.008
 spit+0.007
 face+0.007
 blush+0.007
Neg logit contributions
rob-0.012
zag-0.011
 Hipp-0.011
 Zig-0.011
 Hero-0.010
TokenShe
Token ID3347
Feature activation-7.37e-02

Pos logit contributions
 makeup+0.011
 face+0.010
 blush+0.010
 spit+0.010
 lipstick+0.010
Neg logit contributions
zag-0.010
rob-0.009
 Hipp-0.009
 Zig-0.009
 Skip-0.009
Token had
Token ID550
Feature activation-3.82e-03

Pos logit contributions
 face+0.069
 her+0.065
 spit+0.063
 hand+0.058
 clean+0.058
Neg logit contributions
rob-0.184
 Hipp-0.171
girls-0.170
zag-0.170
 steep-0.166
Token car
Token ID1097
Feature activation+3.69e-02

Pos logit contributions
rob+0.071
zag+0.065
 Hipp+0.065
 Hero+0.061
girls+0.061
Neg logit contributions
vel-0.062
 makeup-0.062
 face-0.061
 spit-0.061
 blush-0.057
Token to
Token ID284
Feature activation+1.23e-02

Pos logit contributions
rob+0.086
 Hipp+0.079
zag+0.077
girls+0.075
 Hero+0.074
Neg logit contributions
 makeup-0.041
 face-0.041
vel-0.039
 spit-0.038
 her-0.036
Token zoom
Token ID19792
Feature activation+1.14e-01

Pos logit contributions
rob+0.029
zag+0.028
 Hipp+0.028
 Zig+0.026
 Hero+0.026
Neg logit contributions
vel-0.013
 makeup-0.012
 spit-0.011
 face-0.011
 blush-0.011
Token around
Token ID1088
Feature activation+7.43e-02

Pos logit contributions
rob+0.279
 Hipp+0.263
zag+0.253
girls+0.253
field+0.245
Neg logit contributions
 face-0.111
 makeup-0.108
 her-0.105
vel-0.101
 lipstick-0.090
Token even
Token ID772
Feature activation+1.22e-01

Pos logit contributions
rob+0.168
zag+0.157
 Hipp+0.156
 Hero+0.150
girls+0.148
Neg logit contributions
vel-0.082
 makeup-0.082
 face-0.081
 spit-0.079
 blush-0.074
Token faster
Token ID5443
Feature activation+2.66e-01

Pos logit contributions
rob+0.216
 Hipp+0.197
zag+0.196
 Zig+0.183
girls+0.183
Neg logit contributions
 face-0.199
vel-0.199
 makeup-0.199
 spit-0.195
 blush-0.184
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
rob+0.668
 Hipp+0.630
zag+0.629
 Hero+0.600
girls+0.599
Neg logit contributions
 face-0.235
 makeup-0.231
vel-0.227
 spit-0.214
 her-0.197
Token His
Token ID2399
Feature activation+1.69e-02

Pos logit contributions
 face+0.020
 spit+0.019
 makeup+0.018
vel+0.018
She+0.017
Neg logit contributions
rob-0.024
zag-0.020
girls-0.019
 Hero-0.019
 Hipp-0.019
Token mom
Token ID1995
Feature activation-4.02e-02

Pos logit contributions
rob+0.041
 Hipp+0.037
zag+0.037
 Hero+0.036
girls+0.035
Neg logit contributions
 face-0.018
 makeup-0.018
 spit-0.017
vel-0.017
 blush-0.015
Token smiled
Token ID13541
Feature activation+7.58e-02

Pos logit contributions
vel+0.057
 makeup+0.057
 face+0.056
 spit+0.055
prise+0.052
Neg logit contributions
rob-0.076
zag-0.072
 Hipp-0.071
 Hero-0.068
girls-0.066
Token again
Token ID757
Feature activation+1.79e-01

Pos logit contributions
rob+0.152
zag+0.151
 Hipp+0.150
 Hero+0.145
 steep+0.143
Neg logit contributions
 makeup-0.091
vel-0.090
 spit-0.088
prise-0.087
 blush-0.082
Token snap
Token ID11495
Feature activation-4.00e-04

Pos logit contributions
zag+0.076
rob+0.073
 steep+0.071
 Skip+0.069
 Hero+0.069
Neg logit contributions
 makeup-0.042
vel-0.040
prise-0.040
 spit-0.038
 face-0.035
Token,
Token ID11
Feature activation-2.67e-02

Pos logit contributions
vel+0.000
 spit+0.000
 makeup+0.000
 face+0.000
prise+0.000
Neg logit contributions
rob-0.001
zag-0.001
 Hipp-0.001
 Hero-0.001
 Zig-0.001
Token the
Token ID262
Feature activation+3.84e-02

Pos logit contributions
 makeup+0.032
 face+0.031
vel+0.030
 spit+0.030
 her+0.030
Neg logit contributions
rob-0.060
zag-0.055
 Hipp-0.053
girls-0.052
 Hero-0.051
Token whip
Token ID22972
Feature activation+1.07e-01

Pos logit contributions
rob+0.073
zag+0.069
 Hipp+0.068
 steep+0.066
 Hero+0.066
Neg logit contributions
vel-0.056
 makeup-0.054
 spit-0.053
prise-0.052
 face-0.052
Token moved
Token ID3888
Feature activation+5.79e-02

Pos logit contributions
rob+0.209
zag+0.198
 Hipp+0.194
 Hero+0.186
 steep+0.184
Neg logit contributions
vel-0.147
 makeup-0.147
 face-0.142
 spit-0.141
 blush-0.133
Token faster
Token ID5443
Feature activation+2.68e-01

Pos logit contributions
rob+0.108
zag+0.105
 Hipp+0.104
 steep+0.102
 Zig+0.101
Neg logit contributions
 spit-0.080
 makeup-0.080
vel-0.079
 face-0.078
prise-0.077
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
rob+0.585
zag+0.555
 Hipp+0.545
 steep+0.527
 Hero+0.526
Neg logit contributions
vel-0.312
 makeup-0.311
 spit-0.306
 face-0.301
prise-0.285
Token faster
Token ID5443
Feature activation+2.68e-01

Pos logit contributions
rob+0.019
zag+0.018
 habitats+0.017
 Hipp+0.017
girls+0.016
Neg logit contributions
 her-0.018
 clean-0.018
 face-0.018
 makeup-0.018
 spit-0.018
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
rob+0.593
zag+0.561
 Hipp+0.555
 Hero+0.534
 steep+0.533
Neg logit contributions
vel-0.303
 makeup-0.302
 spit-0.294
 face-0.290
prise-0.278
Token Now
Token ID2735
Feature activation-1.27e-02

Pos logit contributions
She+0.017
 makeup+0.017
 face+0.017
 her+0.017
vel+0.016
Neg logit contributions
rob-0.027
zag-0.023
girls-0.022
 Hero-0.022
 steep-0.022
Token it
Token ID340
Feature activation-1.09e-02

Pos logit contributions
vel+0.015
 makeup+0.015
 face+0.014
 spit+0.014
 blush+0.013
Neg logit contributions
rob-0.028
zag-0.026
 Hipp-0.026
 Hero-0.025
 steep-0.025
Token across
Token ID1973
Feature activation-2.37e-02

Pos logit contributions
rob+0.157
zag+0.139
field+0.135
 Hipp+0.134
girls+0.131
Neg logit contributions
 her-0.055
 face-0.052
 hand-0.046
 clean-0.046
 makeup-0.045
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
 makeup+0.021
 face+0.020
 her+0.020
vel+0.019
 spit+0.019
Neg logit contributions
rob-0.061
zag-0.057
 Hipp-0.054
girls-0.053
 Hero-0.052
Token pool
Token ID5933
Feature activation+4.53e-02

Pos logit contributions
rob+0.040
zag+0.036
 Hipp+0.036
 Hero+0.034
girls+0.033
Neg logit contributions
vel-0.043
 makeup-0.043
 face-0.043
 spit-0.042
 blush-0.040
Token,
Token ID11
Feature activation-4.07e-02

Pos logit contributions
rob+0.114
 Hipp+0.105
zag+0.103
girls+0.100
 Hero+0.100
Neg logit contributions
 face-0.042
vel-0.039
 makeup-0.039
 spit-0.038
 her-0.034
Token swimming
Token ID14899
Feature activation+9.55e-02

Pos logit contributions
 face+0.043
 hand+0.039
 spit+0.038
 clean+0.038
 makeup+0.037
Neg logit contributions
rob-0.100
zag-0.089
 Hipp-0.088
girls-0.086
 Hero-0.084
Token faster
Token ID5443
Feature activation+2.53e-01

Pos logit contributions
rob+0.259
 Hipp+0.232
zag+0.232
girls+0.224
 Hero+0.223
Neg logit contributions
 face-0.076
 makeup-0.063
vel-0.063
 clean-0.062
 spit-0.061
Token and
Token ID290
Feature activation-2.94e-03

Pos logit contributions
rob+0.646
 Hipp+0.602
zag+0.598
 Hero+0.575
girls+0.568
Neg logit contributions
 face-0.224
 makeup-0.205
vel-0.203
 spit-0.192
 her-0.187
Token faster
Token ID5443
Feature activation+2.52e-01

Pos logit contributions
 clean+0.005
 face+0.004
 spit+0.004
 dirt+0.004
 her+0.004
Neg logit contributions
rob-0.006
zag-0.005
 Hipp-0.005
 habitats-0.005
 Hero-0.004
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
rob+0.622
zag+0.580
 Hipp+0.573
 Hero+0.552
girls+0.543
Neg logit contributions
 face-0.242
vel-0.230
 makeup-0.229
 spit-0.223
 her-0.200
Token
Token ID198
Feature activation-4.98e-03

Pos logit contributions
 face+0.030
 makeup+0.029
 spit+0.028
vel+0.028
 hand+0.027
Neg logit contributions
rob-0.044
zag-0.037
girls-0.034
 steep-0.034
 Hipp-0.033
Token
Token ID198
Feature activation-4.77e-03

Pos logit contributions
vel+0.006
 face+0.006
 makeup+0.006
 spit+0.006
She+0.006
Neg logit contributions
rob-0.011
 Hipp-0.010
zag-0.010
girls-0.010
 Hero-0.009
Token
Token ID198
Feature activation+6.15e-04

Pos logit contributions
vel+0.005
 makeup+0.005
 face+0.005
 spit+0.005
 blush+0.004
Neg logit contributions
rob-0.008
zag-0.007
 Hipp-0.007
 Hero-0.007
 steep-0.007
TokenThe
Token ID464
Feature activation+2.72e-02

Pos logit contributions
rob+0.001
zag+0.001
 Hipp+0.001
 Zig+0.001
 Hero+0.001
Neg logit contributions
 face-0.001
 makeup-0.001
 spit-0.001
 blush-0.001
vel-0.001
Token little
Token ID1310
Feature activation-1.79e-01

Pos logit contributions
rob+0.052
 Hipp+0.050
zag+0.049
 Hero+0.047
 steep+0.046
Neg logit contributions
vel-0.039
 makeup-0.038
 spit-0.037
 face-0.037
 blush-0.036
Token squirrel
Token ID33039
Feature activation-4.20e-03

Pos logit contributions
vel+0.227
 makeup+0.223
 face+0.220
 spit+0.218
 blush+0.204
Neg logit contributions
rob-0.377
 Hipp-0.352
zag-0.351
 Hero-0.335
 steep-0.331
Token ran
Token ID4966
Feature activation-1.25e-02

Pos logit contributions
vel+0.005
 face+0.005
 spit+0.005
 makeup+0.005
 blush+0.005
Neg logit contributions
rob-0.009
 Hipp-0.008
zag-0.008
 Hero-0.008
 steep-0.008
Token faster
Token ID5443
Feature activation+2.73e-01

Pos logit contributions
 face+0.014
 makeup+0.014
vel+0.014
 spit+0.013
 her+0.013
Neg logit contributions
rob-0.029
zag-0.026
 Hipp-0.026
girls-0.025
 Hero-0.024
Token,
Token ID11
Feature activation-2.10e-02

Pos logit contributions
rob+0.662
 Hipp+0.615
zag+0.613
 Hero+0.588
girls+0.588
Neg logit contributions
 face-0.268
vel-0.265
 makeup-0.260
 spit-0.250
 her-0.227
Token but
Token ID475
Feature activation-2.00e-02

Pos logit contributions
 face+0.024
 makeup+0.022
 spit+0.022
vel+0.022
 her+0.021
Neg logit contributions
rob-0.050
zag-0.045
 Hipp-0.044
girls-0.043
 Hero-0.042
Token the
Token ID262
Feature activation+4.55e-02

Pos logit contributions
 her+0.025
 face+0.025
vel+0.023
 spit+0.023
 makeup+0.023
Neg logit contributions
rob-0.046
zag-0.039
girls-0.038
 Hipp-0.037
 habitats-0.036
Token fox
Token ID21831
Feature activation+6.04e-02

Pos logit contributions
rob+0.099
 Hipp+0.096
zag+0.094
 Hero+0.091
 steep+0.091
Neg logit contributions
vel-0.054
 makeup-0.051
 spit-0.049
 face-0.048
prise-0.048
Token was
Token ID373
Feature activation+3.30e-02

Pos logit contributions
rob+0.134
 Hipp+0.120
zag+0.120
 Hero+0.116
girls+0.115
Neg logit contributions
 spit-0.073
 face-0.073
vel-0.072
 makeup-0.070
 blush-0.064
Token<|endoftext|>
Token ID50256
Feature activation-4.74e-02

Pos logit contributions
 face+0.003
She+0.003
 spit+0.003
vel+0.003
 makeup+0.003
Neg logit contributions
rob-0.009
zag-0.008
 steep-0.007
 Hero-0.007
 Hipp-0.007
TokenSam
Token ID16305
Feature activation-2.55e-02

Pos logit contributions
 makeup+0.051
vel+0.050
 her+0.048
She+0.048
 face+0.048
Neg logit contributions
rob-0.103
zag-0.099
 Hipp-0.096
 steep-0.096
girls-0.093
Token was
Token ID373
Feature activation+3.32e-02

Pos logit contributions
vel+0.024
 makeup+0.022
 face+0.022
 spit+0.022
 blush+0.020
Neg logit contributions
rob-0.063
zag-0.059
 Hipp-0.058
 Hero-0.057
 steep-0.056
Token picking
Token ID10868
Feature activation-5.75e-02

Pos logit contributions
rob+0.072
 Hipp+0.068
zag+0.068
 Hero+0.065
 steep+0.065
Neg logit contributions
vel-0.038
 makeup-0.037
 face-0.036
 spit-0.036
 blush-0.034
Token wild
Token ID4295
Feature activation+2.74e-02

Pos logit contributions
vel+0.083
 spit+0.081
 face+0.079
 makeup+0.078
prise+0.076
Neg logit contributions
rob-0.112
 Hipp-0.105
zag-0.102
 Hero-0.098
 Zig-0.097
Tokenfl
Token ID2704
Feature activation+2.56e-01

Pos logit contributions
rob+0.059
zag+0.056
 Hipp+0.054
 steep+0.052
 Hero+0.052
Neg logit contributions
 makeup-0.035
 face-0.033
vel-0.032
 spit-0.032
 blush-0.031
Tokenowers
Token ID3618
Feature activation+5.19e-02

Pos logit contributions
rob+0.416
zag+0.373
 Hipp+0.359
girls+0.338
 Zig+0.322
Neg logit contributions
 face-0.468
 spit-0.466
vel-0.458
 makeup-0.445
 blush-0.428
Token in
Token ID287
Feature activation+1.51e-02

Pos logit contributions
rob+0.111
 Hipp+0.109
zag+0.109
 steep+0.103
 aboard+0.102
Neg logit contributions
vel-0.059
 spit-0.058
 makeup-0.056
 face-0.056
prise-0.054
Token the
Token ID262
Feature activation+4.29e-02

Pos logit contributions
 Hipp+0.023
rob+0.023
 aboard+0.022
 steep+0.021
 Hero+0.021
Neg logit contributions
vel-0.026
 spit-0.025
 blush-0.024
 face-0.023
prise-0.023
Token me
Token ID502
Feature activation-1.10e-01

Pos logit contributions
rob+0.077
 Hipp+0.074
 steep+0.070
zag+0.070
 Hero+0.068
Neg logit contributions
vel-0.069
 spit-0.064
 face-0.059
 blush-0.059
prise-0.058
Tokenadow
Token ID4584
Feature activation+4.54e-02

Pos logit contributions
vel+0.162
 spit+0.161
 makeup+0.161
 face+0.157
 blush+0.152
Neg logit contributions
zag-0.196
rob-0.191
 Hipp-0.177
 steep-0.176
girls-0.169
Token comfortable
Token ID6792
Feature activation-3.24e-03

Pos logit contributions
rob+0.142
zag+0.133
 Hipp+0.133
 Hero+0.127
 steep+0.126
Neg logit contributions
vel-0.077
 makeup-0.077
 face-0.075
 spit-0.074
 blush-0.070
Token and
Token ID290
Feature activation+6.05e-04

Pos logit contributions
 face+0.004
 makeup+0.004
vel+0.004
 spit+0.004
 her+0.003
Neg logit contributions
rob-0.007
zag-0.007
 Hipp-0.007
 steep-0.006
girls-0.006
Token relaxed
Token ID18397
Feature activation+9.43e-03

Pos logit contributions
rob+0.001
zag+0.001
 Hipp+0.001
 Hero+0.001
girls+0.001
Neg logit contributions
vel-0.001
 makeup-0.001
 face-0.001
 spit-0.001
 blush-0.001
Token as
Token ID355
Feature activation+6.52e-02

Pos logit contributions
rob+0.022
zag+0.021
 Hipp+0.021
 Hero+0.020
 steep+0.020
Neg logit contributions
vel-0.010
 makeup-0.009
 spit-0.009
 face-0.009
 blush-0.008
Token he
Token ID339
Feature activation+2.00e-02

Pos logit contributions
rob+0.123
zag+0.110
 Hipp+0.106
girls+0.104
 Hero+0.099
Neg logit contributions
 face-0.101
 makeup-0.100
vel-0.100
 spit-0.098
 her-0.096
Token always
Token ID1464
Feature activation+7.97e-02

Pos logit contributions
rob+0.042
zag+0.039
 Hipp+0.038
 Hero+0.036
 steep+0.036
Neg logit contributions
 spit-0.026
vel-0.026
 face-0.026
 makeup-0.025
 blush-0.024
Token did
Token ID750
Feature activation-2.14e-02

Pos logit contributions
rob+0.168
zag+0.157
 Hipp+0.157
 Hero+0.150
girls+0.149
Neg logit contributions
vel-0.100
 face-0.100
 makeup-0.100
 spit-0.099
 blush-0.092
Token outside
Token ID2354
Feature activation-2.68e-02

Pos logit contributions
 makeup+0.024
vel+0.024
 spit+0.023
 face+0.023
 blush+0.022
Neg logit contributions
rob-0.047
zag-0.045
 Hipp-0.044
 Hero-0.042
 steep-0.042
Token.
Token ID13
Feature activation-2.02e-02

Pos logit contributions
vel+0.030
 makeup+0.029
 spit+0.029
 face+0.029
 blush+0.027
Neg logit contributions
rob-0.060
zag-0.056
 Hipp-0.056
 Hero-0.054
 steep-0.053
Token He
Token ID679
Feature activation-1.76e-02

Pos logit contributions
 face+0.032
 spit+0.030
vel+0.030
 makeup+0.029
She+0.029
Neg logit contributions
rob-0.040
zag-0.036
 Hipp-0.035
girls-0.034
 Zig-0.032
Token also
Token ID635
Feature activation+1.60e-01

Pos logit contributions
 spit+0.020
 face+0.019
vel+0.017
 dust+0.017
 cut+0.017
Neg logit contributions
rob-0.043
zag-0.039
 Hipp-0.039
girls-0.037
 Zig-0.037
Token stop
Token ID2245
Feature activation-6.49e-02

Pos logit contributions
 Hipp+0.095
zag+0.092
 Hero+0.087
rob+0.086
 steep+0.085
Neg logit contributions
vel-0.084
 makeup-0.081
prise-0.076
pled-0.075
aming-0.074
Token smiling
Token ID16755
Feature activation+7.63e-02

Pos logit contributions
vel+0.082
prise+0.082
 makeup+0.079
 spit+0.077
 face+0.074
Neg logit contributions
 Hipp-0.122
rob-0.120
zag-0.116
 aboard-0.112
 Hero-0.111
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
rob+0.159
 Hipp+0.155
zag+0.155
 Hero+0.150
 steep+0.148
Neg logit contributions
 makeup-0.085
vel-0.085
 spit-0.084
prise-0.082
 face-0.078
Token<|endoftext|>
Token ID50256
Feature activation-5.32e-02

Pos logit contributions
 face+0.024
vel+0.024
 makeup+0.024
 spit+0.023
 blush+0.022
Neg logit contributions
rob-0.032
zag-0.030
 Hipp-0.029
girls-0.028
 steep-0.027
TokenHe
Token ID1544
Feature activation-4.50e-02

Pos logit contributions
 makeup+0.077
vel+0.076
 face+0.074
 spit+0.072
She+0.072
Neg logit contributions
rob-0.098
zag-0.093
 Hipp-0.091
 steep-0.089
girls-0.086
Tokenidi
Token ID19830
Feature activation+1.71e-01

Pos logit contributions
vel+0.060
 makeup+0.059
 face+0.058
 spit+0.056
 blush+0.054
Neg logit contributions
rob-0.091
zag-0.084
 Hipp-0.084
 Hero-0.080
 steep-0.079
Token had
Token ID550
Feature activation+6.77e-03

Pos logit contributions
rob+0.361
 Hipp+0.337
zag+0.336
 Hero+0.322
girls+0.317
Neg logit contributions
vel-0.216
 makeup-0.212
 face-0.208
 spit-0.205
 blush-0.193
Token a
Token ID257
Feature activation-2.36e-02

Pos logit contributions
rob+0.017
zag+0.016
 Hipp+0.016
 Hero+0.015
girls+0.015
Neg logit contributions
 makeup-0.006
vel-0.006
 face-0.006
 spit-0.006
 blush-0.005
Token big
Token ID1263
Feature activation-9.99e-02

Pos logit contributions
vel+0.028
 makeup+0.026
 spit+0.026
 face+0.026
 blush+0.024
Neg logit contributions
rob-0.052
zag-0.049
 Hipp-0.049
 Hero-0.047
 steep-0.046
Token problem
Token ID1917
Feature activation+6.36e-02

Pos logit contributions
vel+0.127
 spit+0.121
 makeup+0.119
 face+0.116
 blush+0.110
Neg logit contributions
rob-0.210
zag-0.196
 Hipp-0.196
 Hero-0.188
 steep-0.188
Token,
Token ID11
Feature activation-3.60e-02

Pos logit contributions
rob+0.139
zag+0.135
 Hipp+0.131
 steep+0.125
 Hero+0.125
Neg logit contributions
vel-0.070
 spit-0.069
 face-0.068
 makeup-0.067
 blush-0.064
Token car
Token ID1097
Feature activation+3.88e-02

Pos logit contributions
rob+0.073
zag+0.067
 Hipp+0.067
 Hero+0.064
 steep+0.063
Neg logit contributions
vel-0.073
 makeup-0.069
 spit-0.069
 face-0.068
 blush-0.066
Token went
Token ID1816
Feature activation-5.13e-02

Pos logit contributions
rob+0.095
 Hipp+0.088
girls+0.083
zag+0.083
 Skip+0.082
Neg logit contributions
 face-0.042
 spit-0.041
 makeup-0.036
 cut-0.035
vel-0.033
Token too
Token ID1165
Feature activation+1.35e-01

Pos logit contributions
 makeup+0.058
 face+0.056
vel+0.054
 spit+0.053
 blush+0.050
Neg logit contributions
rob-0.119
zag-0.109
 Hipp-0.109
girls-0.103
 Hero-0.102
Token fast
Token ID3049
Feature activation+1.08e-01

Pos logit contributions
rob+0.276
 Hipp+0.255
zag+0.255
 Hero+0.242
girls+0.241
Neg logit contributions
vel-0.179
 makeup-0.178
 face-0.177
 spit-0.174
 blush-0.162
Token and
Token ID290
Feature activation+1.30e-02

Pos logit contributions
rob+0.247
zag+0.234
 Hipp+0.230
 Hero+0.224
 steep+0.221
Neg logit contributions
vel-0.117
 makeup-0.116
 spit-0.114
 face-0.113
 blush-0.106
Token hit
Token ID2277
Feature activation+9.92e-02

Pos logit contributions
rob+0.035
zag+0.031
 Hipp+0.029
girls+0.029
 habitats+0.028
Neg logit contributions
 spit-0.013
 face-0.013
 her-0.013
 drop-0.012
 clean-0.012
Token a
Token ID257
Feature activation-1.29e-02

Pos logit contributions
rob+0.208
zag+0.194
 Hipp+0.193
 Hero+0.183
girls+0.182
Neg logit contributions
vel-0.127
 makeup-0.127
 face-0.125
 spit-0.123
 blush-0.115
Token wall
Token ID3355
Feature activation-5.53e-02

Pos logit contributions
vel+0.021
 makeup+0.021
illy+0.020
prise+0.020
 spit+0.019
Neg logit contributions
 steep-0.022
zag-0.021
rob-0.021
 Hipp-0.020
 Hero-0.020
Token.
Token ID13
Feature activation-7.36e-03

Pos logit contributions
 makeup+0.066
vel+0.065
prise+0.062
 face+0.061
 spit+0.061
Neg logit contributions
zag-0.116
rob-0.115
 steep-0.111
 Hipp-0.108
 Hero-0.106
Token The
Token ID383
Feature activation+5.32e-02

Pos logit contributions
 face+0.009
 spit+0.009
 makeup+0.009
vel+0.008
 blush+0.008
Neg logit contributions
rob-0.016
zag-0.015
 Hipp-0.015
girls-0.014
 Hero-0.013
Token toy
Token ID13373
Feature activation-2.85e-02

Pos logit contributions
rob+0.075
zag+0.072
 Hero+0.070
 steep+0.070
 Hipp+0.069
Neg logit contributions
vel-0.106
illy-0.095
prise-0.095
 spit-0.094
 makeup-0.093
Token with
Token ID351
Feature activation-1.74e-02

Pos logit contributions
 spit+0.080
vel+0.080
prise+0.079
 worry+0.079
 blush+0.077
Neg logit contributions
rob-0.159
zag-0.142
 Hero-0.141
 Hipp-0.138
 Zig-0.137
Token his
Token ID465
Feature activation-2.99e-02

Pos logit contributions
vel+0.031
prise+0.029
 spit+0.028
 face+0.027
 blush+0.027
Neg logit contributions
rob-0.030
 Hipp-0.027
 Hero-0.026
zag-0.026
 Zig-0.026
Token toys
Token ID14958
Feature activation-8.15e-02

Pos logit contributions
 makeup+0.030
 face+0.030
vel+0.030
 spit+0.029
 blush+0.026
Neg logit contributions
rob-0.071
zag-0.067
 Hipp-0.066
 Hero-0.064
 steep-0.063
Token,
Token ID11
Feature activation-4.34e-02

Pos logit contributions
vel+0.098
 spit+0.094
 makeup+0.092
 face+0.091
prise+0.089
Neg logit contributions
rob-0.179
zag-0.170
 Hipp-0.164
 Hero-0.162
 steep-0.159
Token but
Token ID475
Feature activation-3.60e-02

Pos logit contributions
vel+0.064
 makeup+0.061
 spit+0.059
 face+0.059
prise+0.058
Neg logit contributions
rob-0.084
 Hipp-0.078
zag-0.077
 Hero-0.074
 steep-0.074
Token one
Token ID530
Feature activation+1.18e-01

Pos logit contributions
 her+0.049
 makeup+0.045
 face+0.043
 worry+0.041
 spit+0.040
Neg logit contributions
rob-0.079
girls-0.074
zag-0.073
 Hipp-0.071
 Hero-0.068
Token day
Token ID1110
Feature activation-9.07e-03

Pos logit contributions
rob+0.142
zag+0.139
 Hipp+0.137
 steep+0.125
 Hero+0.125
Neg logit contributions
vel-0.252
 makeup-0.237
 spit-0.233
 blush-0.230
 face-0.229
Token his
Token ID465
Feature activation-2.99e-02

Pos logit contributions
vel+0.017
 spit+0.017
 makeup+0.016
prise+0.016
 face+0.016
Neg logit contributions
rob-0.013
 Hipp-0.012
zag-0.012
 Zig-0.012
 Hero-0.011
Token favorite
Token ID4004
Feature activation+6.32e-02

Pos logit contributions
vel+0.042
 spit+0.038
 makeup+0.037
 face+0.036
prise+0.036
Neg logit contributions
rob-0.059
zag-0.058
 Hipp-0.057
 Hero-0.054
 Zig-0.053
Token toy
Token ID13373
Feature activation-4.23e-02

Pos logit contributions
rob+0.120
zag+0.114
 Hipp+0.111
 Hero+0.106
 Zig+0.103
Neg logit contributions
vel-0.097
prise-0.087
 spit-0.086
 makeup-0.086
She-0.085
Token broke
Token ID6265
Feature activation-4.16e-03

Pos logit contributions
vel+0.063
 makeup+0.060
 spit+0.059
 face+0.059
prise+0.057
Neg logit contributions
rob-0.080
zag-0.076
 Hipp-0.075
 Hero-0.071
 Zig-0.070
Token,
Token ID11
Feature activation-3.55e-02

Pos logit contributions
 makeup+0.056
vel+0.055
 face+0.054
 spit+0.052
 blush+0.049
Neg logit contributions
rob-0.145
zag-0.136
 Hipp-0.135
 Hero-0.130
girls-0.129
Token she
Token ID673
Feature activation+4.31e-03

Pos logit contributions
vel+0.035
 makeup+0.035
 face+0.034
 spit+0.034
 blush+0.031
Neg logit contributions
rob-0.084
zag-0.079
 Hipp-0.079
 Hero-0.076
 steep-0.075
Token improved
Token ID6596
Feature activation+5.97e-02

Pos logit contributions
rob+0.009
 Hipp+0.009
zag+0.009
 Hero+0.008
 Zig+0.008
Neg logit contributions
 spit-0.005
 makeup-0.005
 face-0.005
vel-0.005
 blush-0.005
Token the
Token ID262
Feature activation+3.18e-02

Pos logit contributions
rob+0.141
zag+0.133
 Hipp+0.132
 Hero+0.128
 steep+0.127
Neg logit contributions
vel-0.058
 makeup-0.057
 face-0.056
 spit-0.056
 blush-0.051
Token world
Token ID995
Feature activation-4.40e-02

Pos logit contributions
rob+0.051
zag+0.048
 steep+0.048
 Hipp+0.047
 Hero+0.046
Neg logit contributions
vel-0.055
 spit-0.053
 makeup-0.052
 blush-0.050
 face-0.050
Token one
Token ID530
Feature activation+1.24e-01

Pos logit contributions
 makeup+0.045
vel+0.044
 face+0.043
 spit+0.041
 her+0.039
Neg logit contributions
rob-0.105
 Hipp-0.097
zag-0.096
girls-0.093
 Hero-0.092
Token little
Token ID1310
Feature activation-1.86e-01

Pos logit contributions
rob+0.267
zag+0.256
 Hipp+0.252
 steep+0.243
 Hero+0.242
Neg logit contributions
vel-0.144
 makeup-0.141
 spit-0.139
 face-0.138
 blush-0.130
Token bit
Token ID1643
Feature activation-6.98e-02

Pos logit contributions
 makeup+0.238
 face+0.236
vel+0.235
 spit+0.230
 blush+0.216
Neg logit contributions
rob-0.392
zag-0.364
 Hipp-0.360
 Hero-0.343
 Zig-0.340
Token at
Token ID379
Feature activation-1.69e-02

Pos logit contributions
vel+0.078
 makeup+0.077
 face+0.076
 spit+0.075
 blush+0.069
Neg logit contributions
rob-0.155
 Hipp-0.147
zag-0.147
 steep-0.141
 Hero-0.140
Token a
Token ID257
Feature activation-2.58e-02

Pos logit contributions
 makeup+0.019
vel+0.019
 face+0.019
 spit+0.018
 blush+0.017
Neg logit contributions
rob-0.038
 Hipp-0.036
zag-0.036
 Hero-0.034
girls-0.034
Token time
Token ID640
Feature activation-2.44e-02

Pos logit contributions
 makeup+0.037
 spit+0.037
vel+0.036
 blush+0.036
 face+0.036
Neg logit contributions
zag-0.046
rob-0.046
 Hipp-0.046
 steep-0.045
 Hero-0.043
Token was
Token ID373
Feature activation+1.83e-02

Pos logit contributions
 spit+0.024
 makeup+0.024
 face+0.024
vel+0.024
 dust+0.022
Neg logit contributions
rob-0.048
 Hipp-0.045
zag-0.044
girls-0.043
 Zig-0.042
Token his
Token ID465
Feature activation-2.88e-02

Pos logit contributions
rob+0.046
zag+0.043
 Hipp+0.042
girls+0.041
 Hero+0.040
Neg logit contributions
 makeup-0.017
 face-0.017
vel-0.017
 spit-0.016
 her-0.016
Token reward
Token ID6721
Feature activation+1.50e-02

Pos logit contributions
 face+0.040
 makeup+0.040
vel+0.038
 spit+0.038
 blush+0.036
Neg logit contributions
rob-0.060
 Hipp-0.053
zag-0.053
girls-0.051
 Hero-0.051
Token!
Token ID0
Feature activation-1.40e-02

Pos logit contributions
rob+0.035
zag+0.033
 Hipp+0.033
 Hero+0.032
girls+0.031
Neg logit contributions
vel-0.015
 makeup-0.015
 face-0.015
 spit-0.015
 blush-0.013
Token Jack
Token ID3619
Feature activation-3.49e-02

Pos logit contributions
vel+0.021
 makeup+0.021
 face+0.021
 spit+0.021
 blush+0.019
Neg logit contributions
rob-0.026
zag-0.024
 Hipp-0.024
 Hero-0.023
 Zig-0.022
Token was
Token ID373
Feature activation+1.76e-02

Pos logit contributions
 face+0.045
vel+0.045
 makeup+0.045
 spit+0.044
 blush+0.041
Neg logit contributions
rob-0.073
 Hipp-0.068
zag-0.067
 Hero-0.064
 steep-0.064
Token so
Token ID523
Feature activation+2.49e-02

Pos logit contributions
rob+0.043
zag+0.040
 Hipp+0.040
 Hero+0.038
 steep+0.038
Neg logit contributions
vel-0.017
 makeup-0.017
 face-0.016
 spit-0.016
 blush-0.015
Token happy
Token ID3772
Feature activation-4.60e-02

Pos logit contributions
 Hipp+0.043
zag+0.041
 steep+0.041
rob+0.041
 Zig+0.040
Neg logit contributions
 makeup-0.038
vel-0.037
 blush-0.035
 lipstick-0.034
 file-0.033
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
 face+0.050
 makeup+0.049
vel+0.049
 spit+0.047
 her+0.043
Neg logit contributions
rob-0.108
zag-0.100
 Hipp-0.099
girls-0.095
 steep-0.095
Token He
Token ID679
Feature activation-1.96e-02

Pos logit contributions
 face+0.031
 makeup+0.030
vel+0.029
 spit+0.029
She+0.028
Neg logit contributions
rob-0.036
zag-0.033
 Hipp-0.033
girls-0.031
 steep-0.031
Token learned
Token ID4499
Feature activation+2.10e-03

Pos logit contributions
 face+0.023
 spit+0.022
 makeup+0.021
vel+0.020
 her+0.019
Neg logit contributions
rob-0.045
zag-0.042
 Hipp-0.042
girls-0.040
 steep-0.040
Token things
Token ID1243
Feature activation-6.90e-02

Pos logit contributions
vel+0.038
 makeup+0.037
 spit+0.037
 blush+0.036
 face+0.036
Neg logit contributions
rob-0.041
zag-0.036
 steep-0.036
 Hipp-0.036
 Hero-0.034
Token with
Token ID351
Feature activation-8.33e-03

Pos logit contributions
 makeup+0.069
vel+0.068
 face+0.067
 spit+0.065
 blush+0.060
Neg logit contributions
rob-0.165
 Hipp-0.154
zag-0.153
 Hero-0.147
girls-0.146
Token blocks
Token ID7021
Feature activation+1.70e-02

Pos logit contributions
vel+0.011
 makeup+0.011
 spit+0.011
 face+0.011
prise+0.010
Neg logit contributions
rob-0.016
zag-0.016
 Hipp-0.016
 steep-0.015
 Hero-0.015
Token,
Token ID11
Feature activation-3.23e-02

Pos logit contributions
rob+0.042
 Hipp+0.039
zag+0.039
 Hero+0.038
 Zig+0.037
Neg logit contributions
 makeup-0.016
vel-0.016
 face-0.015
 spit-0.015
 blush-0.014
Token like
Token ID588
Feature activation-1.45e-02

Pos logit contributions
 makeup+0.042
 face+0.041
 spit+0.040
vel+0.040
 blush+0.038
Neg logit contributions
rob-0.068
zag-0.063
 Hipp-0.063
 Hero-0.060
girls-0.059
Token houses
Token ID7777
Feature activation+7.39e-02

Pos logit contributions
vel+0.022
 makeup+0.021
 face+0.021
 spit+0.021
 blush+0.020
Neg logit contributions
rob-0.027
 Hipp-0.025
zag-0.025
 Hero-0.024
 Zig-0.024
Token,
Token ID11
Feature activation-3.27e-02

Pos logit contributions
rob+0.184
 Hipp+0.172
zag+0.171
 Hero+0.164
 Zig+0.163
Neg logit contributions
 makeup-0.067
 face-0.066
vel-0.066
 spit-0.063
 blush-0.058
Token cars
Token ID5006
Feature activation+9.95e-02

Pos logit contributions
 makeup+0.048
 face+0.047
 spit+0.046
vel+0.045
 blush+0.044
Neg logit contributions
rob-0.063
zag-0.059
 Hipp-0.059
 Hero-0.055
girls-0.055
Token,
Token ID11
Feature activation-3.31e-02

Pos logit contributions
rob+0.219
zag+0.209
 Hipp+0.203
 Hero+0.198
girls+0.196
Neg logit contributions
vel-0.116
 makeup-0.113
 spit-0.112
 face-0.110
 blush-0.104
Token and
Token ID290
Feature activation+5.28e-03

Pos logit contributions
 makeup+0.047
 face+0.046
vel+0.046
 spit+0.045
 blush+0.043
Neg logit contributions
rob-0.065
zag-0.061
 Hipp-0.060
 Hero-0.056
girls-0.056
Token towers
Token ID18028
Feature activation+5.19e-02

Pos logit contributions
rob+0.009
 Hipp+0.008
zag+0.008
 Hero+0.008
 steep+0.008
Neg logit contributions
vel-0.009
 makeup-0.008
 face-0.008
 spit-0.008
 blush-0.008
Token took
Token ID1718
Feature activation-9.30e-02

Pos logit contributions
 face+0.021
 spit+0.021
vel+0.021
 makeup+0.020
 blush+0.019
Neg logit contributions
rob-0.038
zag-0.034
 Hipp-0.034
girls-0.033
 Hero-0.032
Token his
Token ID465
Feature activation-2.37e-02

Pos logit contributions
vel+0.128
 makeup+0.127
 spit+0.126
 face+0.120
 blush+0.119
Neg logit contributions
rob-0.179
 Hipp-0.169
 Hero-0.168
 aboard-0.166
 Zig-0.165
Token treasure
Token ID14068
Feature activation+1.81e-02

Pos logit contributions
vel+0.036
 makeup+0.035
 spit+0.035
 face+0.035
 blush+0.033
Neg logit contributions
rob-0.043
zag-0.041
 Hipp-0.040
 Hero-0.039
 steep-0.038
Token and
Token ID290
Feature activation+2.82e-03

Pos logit contributions
rob+0.038
zag+0.037
 Hipp+0.036
 Hero+0.035
 steep+0.035
Neg logit contributions
vel-0.022
 makeup-0.021
 spit-0.021
 face-0.020
 blush-0.020
Token went
Token ID1816
Feature activation-6.27e-02

Pos logit contributions
rob+0.006
zag+0.005
 Hipp+0.005
 Hero+0.005
girls+0.005
Neg logit contributions
vel-0.004
 makeup-0.004
 face-0.004
 spit-0.004
 blush-0.003
Token running
Token ID2491
Feature activation+3.56e-02

Pos logit contributions
 makeup+0.069
 face+0.069
vel+0.068
 spit+0.063
 blush+0.061
Neg logit contributions
rob-0.145
 Hipp-0.134
zag-0.132
girls-0.128
 Hero-0.127
Token back
Token ID736
Feature activation+8.35e-03

Pos logit contributions
rob+0.085
 Hipp+0.077
zag+0.076
girls+0.074
 Hero+0.073
Neg logit contributions
 face-0.039
 makeup-0.038
vel-0.036
 her-0.036
 blush-0.033
Token home
Token ID1363
Feature activation-5.95e-03

Pos logit contributions
rob+0.021
 Hipp+0.019
girls+0.018
zag+0.018
 Hero+0.018
Neg logit contributions
 her-0.008
 makeup-0.008
 face-0.008
 hand-0.007
 clean-0.007
Token with
Token ID351
Feature activation-1.37e-02

Pos logit contributions
vel+0.006
 makeup+0.005
 face+0.005
 spit+0.005
 blush+0.005
Neg logit contributions
rob-0.015
 Hipp-0.014
zag-0.014
 Hero-0.013
girls-0.013
Token a
Token ID257
Feature activation-2.61e-02

Pos logit contributions
vel+0.020
 makeup+0.019
 spit+0.019
 blush+0.018
 face+0.018
Neg logit contributions
rob-0.025
 Hipp-0.024
 Hero-0.023
 Zig-0.023
 steep-0.023
Token big
Token ID1263
Feature activation-1.04e-01

Pos logit contributions
vel+0.034
 makeup+0.032
 spit+0.031
 blush+0.029
She+0.028
Neg logit contributions
zag-0.052
 steep-0.051
rob-0.051
 Hipp-0.050
 Hero-0.049
Token,
Token ID11
Feature activation-3.86e-02

Pos logit contributions
 makeup+0.062
vel+0.059
 face+0.059
 spit+0.055
 her+0.053
Neg logit contributions
rob-0.156
zag-0.147
 Hipp-0.145
 Hero-0.138
 steep-0.138
Token the
Token ID262
Feature activation+2.95e-02

Pos logit contributions
 makeup+0.043
vel+0.042
 face+0.042
 spit+0.040
 blush+0.038
Neg logit contributions
rob-0.088
zag-0.083
 Hipp-0.081
 Hero-0.078
girls-0.077
Token rabbit
Token ID22746
Feature activation-1.68e-02

Pos logit contributions
rob+0.057
zag+0.053
 Hipp+0.053
 Hero+0.050
 steep+0.050
Neg logit contributions
vel-0.044
 makeup-0.043
 spit-0.042
 face-0.042
 blush-0.040
Token was
Token ID373
Feature activation+1.76e-02

Pos logit contributions
 face+0.024
 spit+0.024
 makeup+0.024
 her+0.024
vel+0.023
Neg logit contributions
rob-0.032
zag-0.028
 Hipp-0.028
 steep-0.027
 Hero-0.026
Token right
Token ID826
Feature activation-2.69e-02

Pos logit contributions
rob+0.043
 Hipp+0.039
zag+0.039
girls+0.038
 Hero+0.038
Neg logit contributions
 her-0.018
 makeup-0.018
vel-0.017
 face-0.017
 spit-0.016
Token there
Token ID612
Feature activation+3.22e-02

Pos logit contributions
 makeup+0.026
vel+0.026
 face+0.026
 spit+0.024
 her+0.022
Neg logit contributions
rob-0.066
 Hipp-0.061
zag-0.061
 Hero-0.059
 Zig-0.058
Token with
Token ID351
Feature activation-1.44e-02

Pos logit contributions
rob+0.065
zag+0.062
 Hipp+0.062
 Hero+0.059
 steep+0.059
Neg logit contributions
vel-0.041
 makeup-0.040
 spit-0.040
 face-0.040
 blush-0.037
Token her
Token ID607
Feature activation-7.29e-02

Pos logit contributions
vel+0.015
 face+0.014
 spit+0.014
 makeup+0.014
prise+0.013
Neg logit contributions
rob-0.033
 Hipp-0.031
zag-0.031
 Hero-0.030
girls-0.030
Token -
Token ID532
Feature activation+4.01e-02

Pos logit contributions
vel+0.093
 makeup+0.092
 face+0.091
 spit+0.090
 blush+0.085
Neg logit contributions
rob-0.153
zag-0.143
 Hipp-0.142
 Hero-0.136
 steep-0.134
Token even
Token ID772
Feature activation+1.14e-01

Pos logit contributions
rob+0.092
zag+0.086
 Hipp+0.083
girls+0.080
 Hero+0.080
Neg logit contributions
 makeup-0.045
vel-0.044
 face-0.044
 spit-0.042
 her-0.040
Token when
Token ID618
Feature activation+7.52e-03

Pos logit contributions
rob+0.255
zag+0.239
 Hipp+0.238
 Hero+0.227
girls+0.225
Neg logit contributions
vel-0.129
 makeup-0.129
 face-0.127
 spit-0.125
 blush-0.116
Token there
Token ID612
Feature activation+3.51e-02

Pos logit contributions
vel+0.043
 makeup+0.042
 face+0.042
 spit+0.042
 blush+0.040
Neg logit contributions
rob-0.080
zag-0.079
 Hipp-0.078
 steep-0.075
 Zig-0.075
Token was
Token ID373
Feature activation+2.00e-02

Pos logit contributions
rob+0.062
zag+0.059
 Hipp+0.058
 Zig+0.056
 Hero+0.054
Neg logit contributions
vel-0.056
 makeup-0.054
 face-0.053
 spit-0.053
 blush-0.052
Token an
Token ID281
Feature activation+2.52e-02

Pos logit contributions
rob+0.043
 Hipp+0.041
zag+0.040
 Zig+0.040
 Hero+0.039
Neg logit contributions
vel-0.024
 face-0.023
 spit-0.022
 makeup-0.022
 blush-0.021
Token empty
Token ID6565
Feature activation-6.18e-02

Pos logit contributions
 Hipp+0.043
rob+0.042
 steep+0.039
 Hero+0.038
zag+0.038
Neg logit contributions
vel-0.041
 blush-0.038
 makeup-0.038
 spit-0.037
prise-0.037
Token circle
Token ID9197
Feature activation+2.05e-02

Pos logit contributions
vel+0.094
 spit+0.090
 makeup+0.090
 face+0.089
 blush+0.085
Neg logit contributions
rob-0.115
zag-0.107
 Hipp-0.107
 Hero-0.101
 steep-0.100
Token.
Token ID13
Feature activation-1.91e-02

Pos logit contributions
rob+0.047
zag+0.045
 Hipp+0.044
 steep+0.042
 Hero+0.042
Neg logit contributions
vel-0.022
 spit-0.021
 makeup-0.021
 face-0.020
prise-0.020
Token Nothing
Token ID10528
Feature activation+5.99e-02

Pos logit contributions
 makeup+0.029
 face+0.028
vel+0.028
 spit+0.028
 blush+0.026
Neg logit contributions
rob-0.037
zag-0.034
 Hipp-0.032
girls-0.031
 Hero-0.031
Token was
Token ID373
Feature activation+1.91e-02

Pos logit contributions
rob+0.138
zag+0.125
 Hipp+0.123
girls+0.122
 Hero+0.117
Neg logit contributions
 makeup-0.070
 face-0.070
 spit-0.068
 dust-0.065
 her-0.065
Token inside
Token ID2641
Feature activation+4.08e-02

Pos logit contributions
rob+0.045
zag+0.041
 Hipp+0.041
girls+0.040
 Hero+0.039
Neg logit contributions
 makeup-0.021
 face-0.021
vel-0.020
 spit-0.020
 blush-0.018
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
rob+0.077
 Hipp+0.074
zag+0.074
 steep+0.073
 Hero+0.071
Neg logit contributions
vel-0.056
 makeup-0.054
 spit-0.054
 blush-0.052
 face-0.051
Token circle
Token ID9197
Feature activation+2.00e-02

Pos logit contributions
zag+0.049
 steep+0.048
rob+0.047
 Hipp+0.046
 Hero+0.044
Neg logit contributions
vel-0.050
 spit-0.046
Her-0.045
She-0.043
 makeup-0.043
TokenSlow
Token ID36423
Feature activation+4.92e-02

Pos logit contributions
rob+0.008
zag+0.007
 Hipp+0.007
 Hero+0.007
 Zig+0.007
Neg logit contributions
 face-0.006
 makeup-0.006
 spit-0.005
vel-0.005
 blush-0.005
Tokenly
Token ID306
Feature activation-1.34e-01

Pos logit contributions
rob+0.143
zag+0.134
 Hipp+0.132
girls+0.129
 Hero+0.126
Neg logit contributions
 face-0.028
 makeup-0.026
vel-0.024
 spit-0.022
 blush-0.020
Token,
Token ID11
Feature activation-3.13e-02

Pos logit contributions
vel+0.154
 makeup+0.153
 face+0.149
 spit+0.148
 blush+0.138
Neg logit contributions
rob-0.294
zag-0.278
 Hipp-0.276
 Hero-0.266
 Zig-0.262
Token the
Token ID262
Feature activation+3.66e-02

Pos logit contributions
 face+0.038
 makeup+0.037
vel+0.036
 spit+0.036
 blush+0.034
Neg logit contributions
rob-0.070
zag-0.065
 Hipp-0.063
girls-0.061
 Hero-0.061
Token mom
Token ID1995
Feature activation-3.94e-02

Pos logit contributions
rob+0.081
zag+0.077
 Hipp+0.077
 Hero+0.074
 steep+0.073
Neg logit contributions
vel-0.042
 makeup-0.040
 face-0.039
 spit-0.039
 blush-0.036
Tokenmy
Token ID1820
Feature activation-1.07e-01

Pos logit contributions
vel+0.036
 makeup+0.035
 spit+0.034
 face+0.034
 blush+0.030
Neg logit contributions
rob-0.096
zag-0.094
 Hipp-0.091
 Hero-0.088
girls-0.088
Token got
Token ID1392
Feature activation-7.63e-02

Pos logit contributions
 face+0.116
vel+0.114
 spit+0.112
 makeup+0.109
 dust+0.102
Neg logit contributions
rob-0.249
 Hipp-0.227
zag-0.226
 steep-0.218
 Hero-0.215
Token back
Token ID736
Feature activation+1.50e-02

Pos logit contributions
vel+0.100
 makeup+0.093
 face+0.092
 spit+0.092
 blush+0.087
Neg logit contributions
rob-0.151
 Hipp-0.150
zag-0.142
 Hero-0.141
 aboard-0.141
Token to
Token ID284
Feature activation+1.11e-02

Pos logit contributions
rob+0.035
zag+0.033
 Hipp+0.032
 Hero+0.031
girls+0.031
Neg logit contributions
vel-0.016
 makeup-0.016
 face-0.016
 spit-0.015
 blush-0.014
Token work
Token ID670
Feature activation-6.25e-03

Pos logit contributions
rob+0.023
 Hipp+0.022
zag+0.021
 Zig+0.021
 Hero+0.021
Neg logit contributions
vel-0.015
 makeup-0.014
 spit-0.013
 face-0.013
 blush-0.013
Token.
Token ID13
Feature activation-1.69e-02

Pos logit contributions
vel+0.006
 makeup+0.006
 face+0.006
 spit+0.006
 blush+0.006
Neg logit contributions
rob-0.015
 Hipp-0.014
zag-0.014
 Hero-0.013
girls-0.013
Token scared
Token ID12008
Feature activation+5.28e-02

Pos logit contributions
vel+0.038
prise+0.036
 makeup+0.035
 blush+0.033
ime+0.032
Neg logit contributions
 Hipp-0.046
 steep-0.045
 Hero-0.042
 Zig-0.042
rob-0.042
Token when
Token ID618
Feature activation+9.54e-03

Pos logit contributions
 steep+0.082
 Hipp+0.082
rob+0.078
 Zig+0.078
zag+0.075
Neg logit contributions
prise-0.093
 spit-0.090
vel-0.090
 makeup-0.088
 blush-0.088
Token he
Token ID339
Feature activation+2.25e-02

Pos logit contributions
rob+0.017
zag+0.015
 Hipp+0.015
girls+0.014
 Hero+0.014
Neg logit contributions
 face-0.016
 makeup-0.016
 spit-0.015
vel-0.015
 her-0.015
Token saw
Token ID2497
Feature activation-8.79e-02

Pos logit contributions
rob+0.045
 Hipp+0.044
zag+0.043
 steep+0.042
 Zig+0.042
Neg logit contributions
vel-0.030
 makeup-0.029
 face-0.027
prise-0.026
 blush-0.026
Token a
Token ID257
Feature activation-2.64e-02

Pos logit contributions
 makeup+0.089
 face+0.087
vel+0.086
 spit+0.085
 blush+0.077
Neg logit contributions
rob-0.209
zag-0.198
 Hipp-0.194
girls-0.186
 Hero-0.186
Token big
Token ID1263
Feature activation-1.03e-01

Pos logit contributions
vel+0.034
 makeup+0.031
 blush+0.030
 spit+0.030
prise+0.029
Neg logit contributions
 steep-0.053
 Hipp-0.053
zag-0.053
rob-0.052
 Hero-0.050
Token bird
Token ID6512
Feature activation+1.74e-02

Pos logit contributions
vel+0.164
 spit+0.150
 makeup+0.149
prise+0.148
Her+0.147
Neg logit contributions
rob-0.187
 Hipp-0.179
 steep-0.174
zag-0.171
 Hero-0.168
Token nearby
Token ID6716
Feature activation-2.67e-02

Pos logit contributions
zag+0.034
rob+0.033
 Hipp+0.032
 Zig+0.030
ousel+0.030
Neg logit contributions
 makeup-0.023
vel-0.023
prise-0.022
 spit-0.022
 blush-0.022
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
vel+0.031
 makeup+0.030
prise+0.029
 face+0.028
 spit+0.028
Neg logit contributions
rob-0.058
 Hipp-0.056
zag-0.055
 Zig-0.053
 Hero-0.053
Token
Token ID220
Feature activation+8.16e-03

Pos logit contributions
 face+0.025
 spit+0.023
 makeup+0.022
 hand+0.022
 her+0.021
Neg logit contributions
rob-0.044
zag-0.040
girls-0.037
 habitats-0.036
 steep-0.035
Token
Token ID198
Feature activation-1.41e-03

Pos logit contributions
rob+0.017
 Hipp+0.016
zag+0.016
 Hero+0.015
girls+0.015
Neg logit contributions
vel-0.011
 face-0.010
 makeup-0.010
 spit-0.010
She-0.010
Token park
Token ID3952
Feature activation+9.39e-03

Pos logit contributions
rob+0.055
zag+0.051
 Hipp+0.050
 steep+0.049
 Hero+0.048
Neg logit contributions
vel-0.050
 spit-0.047
 face-0.044
 blush-0.044
 makeup-0.043
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
rob+0.022
zag+0.021
 Hipp+0.021
 Hero+0.020
 steep+0.020
Neg logit contributions
vel-0.010
 makeup-0.009
 spit-0.009
 face-0.009
 blush-0.008
Token They
Token ID1119
Feature activation+9.73e-03

Pos logit contributions
 face+0.032
 spit+0.031
 her+0.031
 makeup+0.030
She+0.030
Neg logit contributions
rob-0.040
zag-0.036
girls-0.034
 Hipp-0.032
 Hero-0.032
Token saw
Token ID2497
Feature activation-9.08e-02

Pos logit contributions
rob+0.020
 Hipp+0.019
zag+0.019
 steep+0.018
 Zig+0.018
Neg logit contributions
vel-0.013
 makeup-0.013
 face-0.012
 spit-0.012
prise-0.012
Token a
Token ID257
Feature activation-2.51e-02

Pos logit contributions
vel+0.091
 makeup+0.087
 face+0.086
 spit+0.085
 blush+0.078
Neg logit contributions
rob-0.217
 Hipp-0.203
zag-0.203
 Hero-0.196
 Zig-0.194
Token big
Token ID1263
Feature activation-1.03e-01

Pos logit contributions
vel+0.033
 spit+0.029
 makeup+0.029
 blush+0.028
 face+0.028
Neg logit contributions
rob-0.052
zag-0.050
 Hipp-0.050
 steep-0.050
 Hero-0.047
Token tree
Token ID5509
Feature activation+1.34e-02

Pos logit contributions
vel+0.171
 spit+0.162
 makeup+0.157
 face+0.154
prise+0.152
Neg logit contributions
rob-0.181
 Hipp-0.166
zag-0.163
 steep-0.161
 Hero-0.156
Token with
Token ID351
Feature activation-1.08e-02

Pos logit contributions
rob+0.031
zag+0.030
 Hipp+0.029
 steep+0.029
 Zig+0.028
Neg logit contributions
vel-0.014
 makeup-0.014
 spit-0.013
 face-0.013
 blush-0.012
Token many
Token ID867
Feature activation-2.93e-02

Pos logit contributions
vel+0.018
prise+0.016
 face+0.015
 makeup+0.015
 spit+0.015
Neg logit contributions
 Hipp-0.019
rob-0.019
 steep-0.018
 Zig-0.018
 tigers-0.017
Token branches
Token ID13737
Feature activation+1.07e-02

Pos logit contributions
vel+0.050
prise+0.047
 makeup+0.047
 spit+0.046
 face+0.046
Neg logit contributions
rob-0.048
 steep-0.045
 Hipp-0.045
zag-0.043
 Zig-0.042
Token.
Token ID13
Feature activation-2.14e-02

Pos logit contributions
rob+0.026
zag+0.025
 Hipp+0.025
 Hero+0.024
girls+0.023
Neg logit contributions
vel-0.010
 makeup-0.010
 face-0.010
 spit-0.010
 blush-0.009
Token After
Token ID2293
Feature activation+4.83e-02

Pos logit contributions
 face+0.033
 spit+0.031
 makeup+0.030
 clean+0.027
 blush+0.026
Neg logit contributions
rob-0.049
zag-0.044
girls-0.040
 Hipp-0.039
field-0.039
Token a
Token ID257
Feature activation-2.80e-02

Pos logit contributions
rob+0.111
 Hipp+0.105
zag+0.104
 Hero+0.101
 Zig+0.100
Neg logit contributions
vel-0.052
 makeup-0.050
 face-0.050
 spit-0.049
 blush-0.046
Token while
Token ID981
Feature activation-4.96e-02

Pos logit contributions
vel+0.038
 makeup+0.037
 face+0.036
 spit+0.036
 blush+0.034
Neg logit contributions
rob-0.056
zag-0.053
 Hipp-0.053
 Hero-0.050
 steep-0.050
Token,
Token ID11
Feature activation-4.00e-02

Pos logit contributions
 face+0.042
 makeup+0.040
vel+0.039
 spit+0.038
 her+0.035
Neg logit contributions
rob-0.129
zag-0.119
 Hipp-0.116
girls-0.114
 Hero-0.113
Token Tim
Token ID5045
Feature activation-4.82e-02

Pos logit contributions
 face+0.047
 her+0.046
 spit+0.045
 makeup+0.045
 clean+0.040
Neg logit contributions
rob-0.092
zag-0.087
girls-0.081
 habitats-0.079
 Hipp-0.078
Tokenmy
Token ID1820
Feature activation-1.09e-01

Pos logit contributions
vel+0.048
 makeup+0.048
 spit+0.046
 face+0.044
 blush+0.043
Neg logit contributions
rob-0.113
zag-0.113
 Hero-0.104
 Hipp-0.103
girls-0.103
Token saw
Token ID2497
Feature activation-9.27e-02

Pos logit contributions
vel+0.122
 makeup+0.121
 face+0.117
 spit+0.115
 blush+0.109
Neg logit contributions
rob-0.246
zag-0.232
 Hipp-0.230
 Hero-0.221
 Zig-0.218
Token the
Token ID262
Feature activation+2.40e-02

Pos logit contributions
 face+0.071
 makeup+0.068
 spit+0.064
 her+0.063
 dust+0.055
Neg logit contributions
rob-0.248
zag-0.245
 Hipp-0.225
girls-0.224
 steep-0.222
Token dog
Token ID3290
Feature activation-3.81e-02

Pos logit contributions
rob+0.053
zag+0.049
 Hipp+0.048
 Zig+0.046
girls+0.046
Neg logit contributions
 face-0.029
 makeup-0.029
 spit-0.028
vel-0.028
 blush-0.025
Token hiding
Token ID11816
Feature activation+5.18e-02

Pos logit contributions
vel+0.048
 makeup+0.047
 spit+0.044
prise+0.044
 face+0.044
Neg logit contributions
rob-0.076
 Hipp-0.076
zag-0.076
 Hero-0.073
 Zig-0.072
Token behind
Token ID2157
Feature activation+6.24e-02

Pos logit contributions
rob+0.116
zag+0.109
 Hipp+0.108
 Hero+0.103
girls+0.102
Neg logit contributions
vel-0.059
 makeup-0.059
 face-0.058
 spit-0.057
 blush-0.053
Token hungry
Token ID14720
Feature activation-1.80e-02

Pos logit contributions
vel+0.011
prise+0.011
 makeup+0.010
 blush+0.010
 envelope+0.010
Neg logit contributions
 steep-0.011
 Hipp-0.010
zag-0.010
 Zig-0.009
 Hero-0.008
Token.
Token ID13
Feature activation-9.24e-03

Pos logit contributions
prise+0.034
vel+0.032
 spit+0.031
 blush+0.030
 makeup+0.029
Neg logit contributions
rob-0.025
 steep-0.024
zag-0.023
 Hipp-0.022
 Hero-0.022
Token She
Token ID1375
Feature activation-3.50e-02

Pos logit contributions
vel+0.013
prise+0.013
 spit+0.012
 makeup+0.011
aming+0.011
Neg logit contributions
 Hipp-0.017
zag-0.017
 Zig-0.017
rob-0.017
 Hero-0.016
Token wanted
Token ID2227
Feature activation-7.18e-02

Pos logit contributions
vel+0.050
 makeup+0.048
 face+0.045
prise+0.044
 blush+0.044
Neg logit contributions
rob-0.067
 Hipp-0.064
zag-0.063
 Hero-0.061
 Zig-0.060
Token to
Token ID284
Feature activation+1.44e-02

Pos logit contributions
 makeup+0.099
 face+0.097
vel+0.097
 spit+0.096
 blush+0.090
Neg logit contributions
rob-0.145
zag-0.135
 Hipp-0.133
 Hero-0.126
girls-0.126
Token eat
Token ID4483
Feature activation-1.08e-01

Pos logit contributions
 Hipp+0.025
 Hero+0.023
 Claw+0.023
zag+0.023
 Zig+0.023
Neg logit contributions
vel-0.024
aming-0.019
 makeup-0.019
pled-0.019
prise-0.018
Token a
Token ID257
Feature activation-1.55e-02

Pos logit contributions
vel+0.141
prise+0.129
 face+0.127
 spit+0.126
ime+0.125
Neg logit contributions
rob-0.223
 Hipp-0.216
 Zig-0.202
 Hero-0.201
 steep-0.194
Token snack
Token ID26906
Feature activation-3.23e-02

Pos logit contributions
vel+0.022
 makeup+0.021
 spit+0.021
 face+0.021
 blush+0.020
Neg logit contributions
rob-0.030
 Hipp-0.028
zag-0.028
 Hero-0.027
 steep-0.027
Token,
Token ID11
Feature activation-2.57e-02

Pos logit contributions
vel+0.046
 spit+0.044
prise+0.042
 makeup+0.042
 face+0.042
Neg logit contributions
rob-0.061
zag-0.060
 steep-0.056
 Hipp-0.056
 Hero-0.055
Token but
Token ID475
Feature activation-2.04e-02

Pos logit contributions
vel+0.047
prise+0.046
ime+0.043
aming+0.041
 makeup+0.041
Neg logit contributions
 steep-0.035
 Hipp-0.035
 Zig-0.035
rob-0.034
 Hero-0.033
Token she
Token ID673
Feature activation+1.32e-02

Pos logit contributions
vel+0.018
 makeup+0.015
 face+0.015
 spit+0.015
prise+0.014
Neg logit contributions
rob-0.050
 Hipp-0.049
 Zig-0.048
zag-0.048
 steep-0.047