TOP ACTIVATIONS
MAX = 12.176

. " Check mate !" declared Elsa . Her
pieces to try and check mate your opponent ."
s King in check mate . The little
enough to find your soul mate , don 't be afraid
popular that everyone wanted a pair of the same .
I could use an extra pair of hands ." The boy
naughty so he took a pair of his mum 's clothes
makes v room - v room sounds . "
. He had a big pair of scissors that he loved
When the timer went off , they took
. She bought him a pair of new shoes . They
fairy gave Benny a special pair of shoes that made him
When the timer finally be ep ed ,
. Lily picked out a pair with her favorite cartoon character
" They make a nice pair ." " I
c ival took out a pair of scissors and said :
moments to check for the date can save you from a
because he had a new pair of shoes . The shoes
When Lucy marked the date , a rainbow - col
a calendar and mark the date with a cr ay on

MIN ACTIVATIONS
MIN = -13.816

by one 1 , 2 ,
rare silence that added to the
something strange the mirror was making
from overhead it was a switch
of school it was an important
something special a pool ! It
t help it â he reached out and
those in need â even <|endoftext|> One day
anxious anymore he knew he was
and rocked higher and higher .
, look it â
it forever things are only available
special taxi it fit three people
my planet let â
lovely things a big slide ,
They forgot they were supposed to
was too late â the ice melted and
something incredible a magical plant !
her peace she just needs to
a normal penny â it was special .

INTERVAL 5.678 - 12.176
CONTAINS 0.532%

set with colorful patterns on them . At
Jake said , " Yes please ! But I 'd like
play with toy soldiers and pretend they were in a war
and pe ck ed at them . Tim and Mia screamed
can smell them and touch them , but we can 't

INTERVAL -0.820 - 5.678
CONTAINS 73.028%

us our coins back ." Tom says . They
back soon . <|endoftext|> L ily liked to play with her
smiled and said , " It 's OK . That 's
was a little girl named Mia . She loved to spend
noise coming from her bedroom . She stopped and listened ,

INTERVAL -7.318 - -0.820
CONTAINS 25.920%

Lily . You can play with my car . And I
off she would look up at her mom and say
One day , there was a long circle . It needed
said . Sab ina felt sad . She apologised
idea . <|endoftext|> Once upon a time , there was a

INTERVAL -13.816 - -7.318
CONTAINS 0.520%

she saw the little boy 's kind eyes . She felt
, " Sure , let 's print a picture of the
And he did ! Pete 's speech was one of the
Mom said , " It 's OK , Tommy . That
kids . Now , let 's go inside and have some
Token.
Token ID13
Feature activation-4.34e-01

Pos logit contributions
+0.021
ages+0.018
's+0.018
aul+0.018
ience+0.017
Neg logit contributions
 them-0.013
mate-0.013
 polar-0.011
 wreck-0.011
 tow-0.011
Token
Token ID198
Feature activation-4.59e-01

Pos logit contributions
+0.029
ages+0.027
 decisions+0.026
aul+0.026
adow+0.025
Neg logit contributions
 them-0.028
mate-0.024
inn-0.022
 tow-0.022
 ramp-0.021
Token
Token ID198
Feature activation-4.66e-01

Pos logit contributions
+0.031
's+0.027
ages+0.025
aul+0.024
cious+0.023
Neg logit contributions
mate-0.030
 them-0.029
 wreck-0.028
 polar-0.027
 tow-0.027
Token"
Token ID1
Feature activation+2.12e-01

Pos logit contributions
+0.032
ages+0.031
aul+0.030
 decisions+0.030
's+0.029
Neg logit contributions
 them-0.027
mate-0.026
inn-0.022
 tow-0.022
 ramp-0.021
TokenCheck
Token ID9787
Feature activation+8.22e-01

Pos logit contributions
mate+0.011
 them+0.011
 tow+0.009
 polar+0.009
 wreck+0.009
Neg logit contributions
-0.017
's-0.015
ages-0.015
aul-0.015
 decisions-0.014
Tokenmate
Token ID9830
Feature activation+1.22e+01

Pos logit contributions
 them+0.042
 tow+0.041
 polar+0.040
 wreck+0.040
 snowball+0.038
Neg logit contributions
-0.065
's-0.058
ages-0.057
 decisions-0.053
cious-0.052
Token!"
Token ID2474
Feature activation+3.64e+00

Pos logit contributions
mate+0.548
 them+0.536
 wreck+0.428
 polar+0.411
 ramp+0.410
Neg logit contributions
-1.037
aul-0.914
ages-0.912
's-0.905
 List-0.903
Token declared
Token ID6875
Feature activation+2.17e+00

Pos logit contributions
 them+0.244
mate+0.201
 stuffed+0.190
 his+0.190
 tant+0.184
Neg logit contributions
-0.219
aul-0.214
 decisions-0.212
adow-0.211
ages-0.210
Token Elsa
Token ID19226
Feature activation-2.09e+00

Pos logit contributions
 them+0.127
mate+0.115
 his+0.100
 polar+0.099
 stuffed+0.097
Neg logit contributions
-0.163
ages-0.148
aul-0.144
bey-0.141
aut-0.139
Token.
Token ID13
Feature activation-4.56e-01

Pos logit contributions
+0.174
aul+0.167
 List+0.163
bey+0.162
 pays+0.161
Neg logit contributions
 them-0.085
mate-0.077
 captain-0.067
 polar-0.065
 control-0.063
Token Her
Token ID2332
Feature activation-2.19e-01

Pos logit contributions
+0.032
ages+0.028
 decisions+0.028
ience+0.027
aul+0.027
Neg logit contributions
 them-0.029
mate-0.027
 tow-0.024
inn-0.024
 polar-0.022
Token pieces
Token ID5207
Feature activation-1.82e-01

Pos logit contributions
+0.020
's+0.017
ages+0.016
aul+0.015
 pays+0.015
Neg logit contributions
mate-0.015
 them-0.015
 polar-0.014
 tow-0.014
 wreck-0.014
Token to
Token ID284
Feature activation-2.83e-01

Pos logit contributions
+0.014
's+0.012
ages+0.012
aul+0.012
cious+0.012
Neg logit contributions
 them-0.010
mate-0.010
 wreck-0.008
 tow-0.008
 polar-0.008
Token try
Token ID1949
Feature activation+2.71e+00

Pos logit contributions
+0.021
's+0.018
aul+0.014
ages+0.014
 pays+0.014
Neg logit contributions
mate-0.018
 snowball-0.017
 polar-0.017
inn-0.016
 tant-0.016
Token and
Token ID290
Feature activation-5.46e-01

Pos logit contributions
mate+0.140
 them+0.128
 polar+0.125
 tow+0.122
 wreck+0.122
Neg logit contributions
-0.222
's-0.200
ages-0.187
aul-0.181
cious-0.175
Token check
Token ID2198
Feature activation+7.19e-01

Pos logit contributions
+0.046
's+0.041
ages+0.040
aul+0.039
cious+0.038
Neg logit contributions
mate-0.026
 them-0.026
 wreck-0.022
 polar-0.022
 tow-0.022
Tokenmate
Token ID9830
Feature activation+1.22e+01

Pos logit contributions
mate+0.032
 them+0.029
 polar+0.029
 wreck+0.029
 tow+0.028
Neg logit contributions
-0.063
's-0.056
ages-0.054
aul-0.052
 pays-0.051
Token your
Token ID534
Feature activation+9.03e-01

Pos logit contributions
 them+0.648
mate+0.643
 wreck+0.549
 tow+0.545
 polar+0.543
Neg logit contributions
-0.962
's-0.837
ages-0.829
aul-0.794
cious-0.773
Token opponent
Token ID6125
Feature activation-2.83e+00

Pos logit contributions
mate+0.056
 them+0.055
 wreck+0.050
 polar+0.049
 tow+0.049
Neg logit contributions
-0.064
's-0.055
ages-0.054
aul-0.052
cious-0.050
Token."
Token ID526
Feature activation+1.98e+00

Pos logit contributions
+0.218
ages+0.189
aul+0.188
 List+0.186
's+0.184
Neg logit contributions
 them-0.152
mate-0.145
 wreck-0.125
 ramp-0.124
 captain-0.119
Token
Token ID198
Feature activation-4.47e-01

Pos logit contributions
 them+0.112
mate+0.109
 tow+0.098
 wreck+0.096
 ramp+0.095
Neg logit contributions
-0.149
's-0.130
ages-0.130
aul-0.123
cious-0.122
Token
Token ID198
Feature activation-4.32e-01

Pos logit contributions
+0.029
's+0.025
ages+0.023
aul+0.022
bey+0.021
Neg logit contributions
mate-0.032
 them-0.030
 polar-0.029
 wreck-0.029
 captain-0.028
Token
Token ID8151
Feature activation-5.21e+00

Pos logit contributions
+0.129
aul+0.121
 Michelle+0.110
 List+0.109
 decisions+0.106
Neg logit contributions
mate-0.232
 them-0.230
 ramp-0.223
 racer-0.217
 puck-0.217
Tokens
Token ID82
Feature activation-4.89e-01

Pos logit contributions
+0.365
ages+0.336
aul+0.330
cious+0.322
's+0.322
Neg logit contributions
 them-0.294
mate-0.294
inn-0.253
 tow-0.249
 wreck-0.247
Token King
Token ID2677
Feature activation-2.37e+00

Pos logit contributions
+0.036
's+0.031
ages+0.031
aul+0.030
cious+0.029
Neg logit contributions
mate-0.028
 them-0.028
 wreck-0.025
 tow-0.024
 ramp-0.024
Token in
Token ID287
Feature activation-3.15e-01

Pos logit contributions
+0.105
 List+0.092
aul+0.090
ages+0.087
bey+0.085
Neg logit contributions
mate-0.196
 them-0.193
 wreck-0.176
 captain-0.172
 racer-0.172
Token check
Token ID2198
Feature activation+6.48e-01

Pos logit contributions
+0.024
's+0.020
 pays+0.017
 decisions+0.017
ages+0.017
Neg logit contributions
mate-0.018
 polar-0.018
 them-0.018
 ramp-0.017
inn-0.017
Tokenmate
Token ID9830
Feature activation+1.21e+01

Pos logit contributions
mate+0.035
 them+0.035
 wreck+0.031
 polar+0.031
 tow+0.030
Neg logit contributions
-0.051
's-0.044
ages-0.043
aul-0.041
cious-0.040
Token.
Token ID13
Feature activation-1.91e-01

Pos logit contributions
mate+0.687
 them+0.680
 wreck+0.605
 polar+0.604
 tow+0.599
Neg logit contributions
-0.917
's-0.800
ages-0.780
aul-0.742
cious-0.722
Token
Token ID198
Feature activation-3.81e-01

Pos logit contributions
+0.016
's+0.014
ages+0.014
aul+0.013
cious+0.013
Neg logit contributions
mate-0.010
 them-0.010
 wreck-0.008
 polar-0.008
 tow-0.008
Token
Token ID198
Feature activation-3.86e-01

Pos logit contributions
+0.021
's+0.016
ages+0.013
aul+0.012
 List+0.012
Neg logit contributions
mate-0.033
 captain-0.031
 polar-0.031
 wreck-0.031
 spoiler-0.030
TokenThe
Token ID464
Feature activation-9.45e-01

Pos logit contributions
+0.033
's+0.026
ages+0.024
 List+0.022
aut+0.022
Neg logit contributions
mate-0.022
 them-0.022
 polar-0.021
ware-0.020
 captain-0.019
Token little
Token ID1310
Feature activation+4.44e-01

Pos logit contributions
+0.074
ages+0.067
's+0.065
aul+0.065
cious+0.062
Neg logit contributions
mate-0.050
 them-0.049
 wreck-0.045
 polar-0.044
 tow-0.044
Token enough
Token ID1576
Feature activation+5.01e-01

Pos logit contributions
+0.300
ages+0.279
cious+0.267
aul+0.265
's+0.259
Neg logit contributions
 them-0.191
mate-0.178
 wreck-0.148
 polar-0.143
 tow-0.143
Token to
Token ID284
Feature activation-4.11e-01

Pos logit contributions
 them+0.027
mate+0.025
 wreck+0.022
 tow+0.022
 polar+0.021
Neg logit contributions
-0.041
ages-0.037
's-0.036
aul-0.035
cious-0.034
Token find
Token ID1064
Feature activation+6.23e-01

Pos logit contributions
+0.033
's+0.029
ages+0.029
aul+0.027
cious+0.027
Neg logit contributions
mate-0.021
 them-0.021
 wreck-0.018
 polar-0.018
 tow-0.018
Token your
Token ID534
Feature activation+7.52e-01

Pos logit contributions
 them+0.041
mate+0.036
 tow+0.032
 wreck+0.031
 polar+0.031
Neg logit contributions
-0.046
ages-0.041
aul-0.039
cious-0.038
's-0.038
Token soul
Token ID5848
Feature activation-5.46e+00

Pos logit contributions
 them+0.044
mate+0.042
 wreck+0.040
 polar+0.038
 tow+0.038
Neg logit contributions
-0.056
ages-0.048
's-0.047
aul-0.047
cious-0.045
Tokenmate
Token ID9830
Feature activation+1.20e+01

Pos logit contributions
+0.429
ages+0.386
aul+0.378
 List+0.367
cious+0.366
Neg logit contributions
 them-0.289
mate-0.274
 wreck-0.229
 captain-0.226
 polar-0.221
Token,
Token ID11
Feature activation-2.58e-01

Pos logit contributions
 them+0.677
mate+0.659
 tow+0.518
 wreck+0.508
 control+0.506
Neg logit contributions
-0.870
ages-0.791
aul-0.788
 List-0.759
cious-0.737
Token don
Token ID836
Feature activation-3.60e+00

Pos logit contributions
ages+0.016
+0.016
cious+0.015
aul+0.015
aut+0.014
Neg logit contributions
 them-0.018
mate-0.016
 captain-0.014
 tow-0.014
 wreck-0.014
Token't
Token ID470
Feature activation+4.50e+00

Pos logit contributions
+0.319
ages+0.303
's+0.292
cious+0.291
aul+0.291
Neg logit contributions
 them-0.148
mate-0.138
 wreck-0.113
 tow-0.113
 ramp-0.106
Token be
Token ID307
Feature activation+1.84e+00

Pos logit contributions
 them+0.244
mate+0.242
 wreck+0.217
 polar+0.212
 tow+0.209
Neg logit contributions
-0.348
ages-0.306
's-0.305
aul-0.290
cious-0.283
Token afraid
Token ID7787
Feature activation-2.43e+00

Pos logit contributions
 them+0.123
mate+0.119
 wreck+0.110
 polar+0.109
 tow+0.106
Neg logit contributions
-0.122
ages-0.102
's-0.102
aul-0.097
cious-0.094
Token popular
Token ID2968
Feature activation+1.67e+00

Pos logit contributions
+0.132
ages+0.115
's+0.114
aul+0.109
cious+0.107
Neg logit contributions
 them-0.071
mate-0.069
 wreck-0.063
 polar-0.061
 tow-0.061
Token that
Token ID326
Feature activation+1.04e+00

Pos logit contributions
mate+0.090
 them+0.089
 tow+0.080
inn+0.079
 polar+0.079
Neg logit contributions
-0.129
's-0.115
ages-0.110
aul-0.104
 decisions-0.102
Token everyone
Token ID2506
Feature activation-2.09e+00

Pos logit contributions
 them+0.065
mate+0.063
 wreck+0.056
 polar+0.055
 tow+0.055
Neg logit contributions
-0.072
ages-0.065
's-0.062
aul-0.062
cious-0.061
Token wanted
Token ID2227
Feature activation+4.01e-01

Pos logit contributions
+0.141
ages+0.127
aul+0.120
's+0.119
cious+0.118
Neg logit contributions
 them-0.130
mate-0.125
 wreck-0.115
 polar-0.110
 tow-0.108
Token a
Token ID257
Feature activation-7.23e-01

Pos logit contributions
 them+0.022
mate+0.020
 wreck+0.016
 tow+0.016
 polar+0.016
Neg logit contributions
-0.032
ages-0.029
aul-0.028
's-0.028
cious-0.028
Token pair
Token ID5166
Feature activation+9.67e+00

Pos logit contributions
+0.056
's+0.049
ages+0.045
aul+0.044
cious+0.043
Neg logit contributions
mate-0.041
 them-0.041
 polar-0.036
inn-0.035
 tow-0.035
Token of
Token ID286
Feature activation+3.06e+00

Pos logit contributions
 ramp+0.542
 polar+0.541
 snowball+0.535
 them+0.531
mate+0.518
Neg logit contributions
-0.775
's-0.661
ages-0.590
aul-0.539
cious-0.535
Token the
Token ID262
Feature activation-2.28e-02

Pos logit contributions
mate+0.191
 them+0.174
 ramp+0.170
inn+0.170
 wreck+0.170
Neg logit contributions
-0.221
's-0.190
ages-0.176
 decisions-0.167
aul-0.165
Token same
Token ID976
Feature activation+2.05e+00

Pos logit contributions
+0.002
ages+0.001
's+0.001
aul+0.001
cious+0.001
Neg logit contributions
mate-0.001
 them-0.001
 wreck-0.001
 polar-0.001
 tow-0.001
Token.
Token ID13
Feature activation-6.42e-02

Pos logit contributions
mate+0.111
 them+0.109
 polar+0.100
inn+0.099
 tow+0.099
Neg logit contributions
-0.161
's-0.143
ages-0.131
 decisions-0.126
aul-0.124
Token
Token ID220
Feature activation-8.52e-01

Pos logit contributions
+0.004
ages+0.004
's+0.004
aul+0.004
cious+0.003
Neg logit contributions
 them-0.004
mate-0.004
 tow-0.004
 polar-0.004
 wreck-0.004
Token I
Token ID314
Feature activation-2.77e+00

Pos logit contributions
+0.036
ages+0.032
's+0.032
aul+0.030
cious+0.030
Neg logit contributions
 them-0.032
mate-0.032
 tow-0.028
 polar-0.028
 wreck-0.028
Token could
Token ID714
Feature activation+1.13e+00

Pos logit contributions
+0.198
's+0.166
ages+0.149
aul+0.141
bey+0.139
Neg logit contributions
mate-0.183
 them-0.176
 ramp-0.164
 polar-0.162
 tow-0.161
Token use
Token ID779
Feature activation+2.63e+00

Pos logit contributions
mate+0.064
 them+0.059
inn+0.055
 polar+0.055
 tow+0.053
Neg logit contributions
-0.093
's-0.080
ages-0.073
aul-0.068
cious-0.066
Token an
Token ID281
Feature activation-2.18e+00

Pos logit contributions
mate+0.159
 polar+0.143
 them+0.142
 wreck+0.138
 tow+0.137
Neg logit contributions
-0.197
's-0.170
ages-0.155
aul-0.148
 pays-0.147
Token extra
Token ID3131
Feature activation+2.78e+00

Pos logit contributions
+0.159
's+0.135
ages+0.125
aul+0.121
 decisions+0.120
Neg logit contributions
mate-0.136
 them-0.134
 polar-0.121
 tow-0.117
 wreck-0.117
Token pair
Token ID5166
Feature activation+9.53e+00

Pos logit contributions
mate+0.152
 them+0.150
 wreck+0.133
 polar+0.132
 tow+0.131
Neg logit contributions
-0.217
's-0.190
ages-0.186
aul-0.177
cious-0.172
Token of
Token ID286
Feature activation+2.81e+00

Pos logit contributions
 polar+0.496
mate+0.488
 them+0.487
 snowball+0.475
 ramp+0.469
Neg logit contributions
-0.799
's-0.688
ages-0.629
aul-0.578
cious-0.569
Token hands
Token ID2832
Feature activation-2.97e+00

Pos logit contributions
mate+0.168
 wreck+0.151
 ramp+0.146
inn+0.144
 them+0.143
Neg logit contributions
-0.218
's-0.189
ages-0.172
cious-0.160
aul-0.160
Token."
Token ID526
Feature activation+1.75e+00

Pos logit contributions
+0.228
's+0.199
ages+0.197
aul+0.189
cious+0.185
Neg logit contributions
 them-0.163
mate-0.161
 wreck-0.140
 polar-0.139
 tow-0.137
Token The
Token ID383
Feature activation-1.55e+00

Pos logit contributions
 them+0.099
mate+0.093
 tow+0.083
 polar+0.082
inn+0.080
Neg logit contributions
-0.126
ages-0.118
's-0.112
cious-0.111
 decisions-0.110
Token boy
Token ID2933
Feature activation+2.15e+00

Pos logit contributions
+0.120
's+0.105
ages+0.102
aul+0.098
cious+0.095
Neg logit contributions
mate-0.085
 them-0.084
 wreck-0.074
 polar-0.074
 tow-0.074
Token naughty
Token ID45128
Feature activation-8.35e-01

Pos logit contributions
 them+0.180
 his+0.167
 polar+0.161
 wreck+0.155
mate+0.154
Neg logit contributions
-0.223
ages-0.197
grand-0.194
ama-0.193
aul-0.192
Token so
Token ID523
Feature activation+3.65e+00

Pos logit contributions
+0.066
ages+0.059
's+0.057
aul+0.057
cious+0.055
Neg logit contributions
 them-0.043
mate-0.042
 polar-0.038
 wreck-0.037
 ramp-0.036
Token he
Token ID339
Feature activation-4.10e-01

Pos logit contributions
 them+0.171
mate+0.161
 wreck+0.146
 polar+0.145
 tow+0.142
Neg logit contributions
-0.308
's-0.279
ages-0.277
aul-0.269
cious-0.264
Token took
Token ID1718
Feature activation-2.31e+00

Pos logit contributions
+0.027
ages+0.023
's+0.023
aul+0.022
 decisions+0.022
Neg logit contributions
 them-0.027
mate-0.026
 polar-0.024
 wreck-0.024
 tow-0.023
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
+0.180
's+0.159
ages+0.156
aul+0.152
cious+0.147
Neg logit contributions
 them-0.127
mate-0.125
 polar-0.108
 wreck-0.108
 tow-0.107
Token pair
Token ID5166
Feature activation+9.52e+00

Pos logit contributions
+0.100
's+0.088
ages+0.078
aul+0.075
cious+0.074
Neg logit contributions
mate-0.066
 them-0.064
 captain-0.055
 polar-0.055
 tow-0.054
Token of
Token ID286
Feature activation+2.86e+00

Pos logit contributions
mate+0.479
 them+0.476
 ramp+0.476
 polar+0.467
 snowball+0.461
Neg logit contributions
-0.812
's-0.695
ages-0.630
aul-0.570
cious-0.569
Token his
Token ID465
Feature activation+4.27e+00

Pos logit contributions
mate+0.178
 ramp+0.156
 wreck+0.156
 tow+0.150
inn+0.149
Neg logit contributions
-0.212
's-0.183
ages-0.171
 decisions-0.156
ience-0.154
Token mum
Token ID25682
Feature activation-2.66e+00

Pos logit contributions
mate+0.253
 them+0.251
 wreck+0.224
 polar+0.223
 tow+0.222
Neg logit contributions
-0.313
's-0.272
ages-0.265
aul-0.252
cious-0.245
Token's
Token ID338
Feature activation-9.14e+00

Pos logit contributions
 List+0.104
+0.102
 decisions+0.096
aul+0.095
ages+0.094
Neg logit contributions
 them-0.229
mate-0.210
 polar-0.207
 tow-0.200
 load-0.196
Token clothes
Token ID8242
Feature activation-8.58e-01

Pos logit contributions
+0.692
's+0.608
ages+0.586
aul+0.551
cious+0.538
Neg logit contributions
mate-0.525
 them-0.514
 wreck-0.460
 polar-0.457
 tow-0.454
Token makes
Token ID1838
Feature activation-2.33e+00

Pos logit contributions
+0.009
ages+0.008
cious+0.008
aul+0.007
's+0.007
Neg logit contributions
 them-0.010
mate-0.010
 tow-0.009
 wreck-0.009
 polar-0.009
Token v
Token ID410
Feature activation+5.40e+00

Pos logit contributions
+0.187
ages+0.164
's+0.163
aul+0.159
cious+0.156
Neg logit contributions
 them-0.124
mate-0.117
 wreck-0.103
 polar-0.101
 tow-0.098
Tokenroom
Token ID3823
Feature activation+9.93e+00

Pos logit contributions
mate+0.227
 them+0.226
 polar+0.209
 tow+0.201
 wreck+0.194
Neg logit contributions
-0.479
ages-0.444
's-0.440
aul-0.407
ups-0.393
Token-
Token ID12
Feature activation+3.17e-01

Pos logit contributions
mate+0.518
 them+0.505
 polar+0.449
 tow+0.447
 wreck+0.447
Neg logit contributions
-0.804
's-0.714
ages-0.694
aul-0.653
cious-0.639
Tokenv
Token ID85
Feature activation+4.54e+00

Pos logit contributions
mate+0.019
 them+0.018
 polar+0.017
 tow+0.017
 wreck+0.016
Neg logit contributions
-0.024
's-0.021
ages-0.021
aul-0.019
cious-0.018
Tokenroom
Token ID3823
Feature activation+9.49e+00

Pos logit contributions
 polar+0.157
mate+0.155
 tow+0.149
 them+0.145
 firefighter+0.144
Neg logit contributions
's-0.410
-0.408
ages-0.397
ups-0.360
 decisions-0.351
Token sounds
Token ID5238
Feature activation-4.56e+00

Pos logit contributions
mate+0.491
 them+0.473
 tow+0.425
 polar+0.425
 wreck+0.420
Neg logit contributions
-0.778
's-0.696
ages-0.675
aul-0.625
cious-0.617
Token.
Token ID13
Feature activation+5.05e-01

Pos logit contributions
+0.338
's+0.296
ages+0.279
aul+0.253
cious+0.252
Neg logit contributions
mate-0.278
 them-0.260
 tow-0.248
 polar-0.248
 wreck-0.242
Token
Token ID198
Feature activation+4.07e-01

Pos logit contributions
mate+0.031
 them+0.031
 wreck+0.028
 polar+0.028
 tow+0.027
Neg logit contributions
-0.036
's-0.031
ages-0.030
aul-0.029
cious-0.028
Token
Token ID198
Feature activation+3.66e-01

Pos logit contributions
mate+0.032
 wreck+0.030
 captain+0.029
 polar+0.029
 them+0.029
Neg logit contributions
-0.024
's-0.019
 List-0.017
ages-0.016
aul-0.016
Token"
Token ID1
Feature activation+7.66e-01

Pos logit contributions
mate+0.020
 them+0.020
 wreck+0.018
 polar+0.018
 tow+0.018
Neg logit contributions
-0.029
's-0.025
ages-0.024
aul-0.023
cious-0.022
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
+0.262
's+0.229
ages+0.226
aul+0.216
cious+0.211
Neg logit contributions
mate-0.174
 them-0.173
 wreck-0.153
 polar-0.152
 tow-0.150
Token He
Token ID679
Feature activation+2.09e+00

Pos logit contributions
+0.016
's+0.014
ages+0.013
aul+0.013
 List+0.013
Neg logit contributions
mate-0.008
 them-0.008
 wreck-0.006
 polar-0.006
 tow-0.006
Token had
Token ID550
Feature activation-1.19e+00

Pos logit contributions
 them+0.128
mate+0.125
 wreck+0.116
 polar+0.116
 tow+0.112
Neg logit contributions
-0.141
ages-0.125
's-0.120
 decisions-0.119
aul-0.118
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
+0.086
's+0.074
ages+0.074
aul+0.071
ience+0.068
Neg logit contributions
 them-0.072
mate-0.069
 polar-0.063
 wreck-0.063
 tow-0.063
Token big
Token ID1263
Feature activation+1.30e+00

Pos logit contributions
+0.082
's+0.073
ages+0.064
aul+0.063
cious+0.062
Neg logit contributions
 them-0.065
mate-0.063
inn-0.056
room-0.051
 tow-0.050
Token pair
Token ID5166
Feature activation+9.43e+00

Pos logit contributions
mate+0.076
 them+0.075
inn+0.065
 tow+0.063
 polar+0.062
Neg logit contributions
-0.097
's-0.088
ages-0.079
aul-0.078
 decisions-0.075
Token of
Token ID286
Feature activation+2.92e+00

Pos logit contributions
 them+0.591
mate+0.566
 ramp+0.563
 snowball+0.561
 polar+0.556
Neg logit contributions
-0.723
's-0.629
ages-0.555
adow-0.499
grand-0.497
Token scissors
Token ID41786
Feature activation+2.64e+00

Pos logit contributions
mate+0.194
 ramp+0.173
 wreck+0.170
inn+0.168
 tow+0.166
Neg logit contributions
-0.191
's-0.170
ages-0.157
aul-0.148
cious-0.143
Token that
Token ID326
Feature activation+6.47e-01

Pos logit contributions
mate+0.176
 them+0.166
 polar+0.158
 tow+0.158
 snowball+0.156
Neg logit contributions
-0.180
's-0.161
ages-0.150
aul-0.133
cious-0.131
Token he
Token ID339
Feature activation-3.25e-01

Pos logit contributions
 them+0.033
mate+0.032
 wreck+0.028
 polar+0.028
 tow+0.027
Neg logit contributions
-0.053
's-0.046
ages-0.046
aul-0.044
cious-0.044
Token loved
Token ID6151
Feature activation-8.98e-01

Pos logit contributions
+0.020
's+0.017
ages+0.016
aul+0.015
cious+0.014
Neg logit contributions
mate-0.024
 them-0.024
 tow-0.022
 polar-0.022
 wreck-0.021
Token
Token ID220
Feature activation-9.69e-01

Pos logit contributions
 them+0.106
 lot+0.083
 his+0.074
mate+0.073
room+0.071
Neg logit contributions
-0.143
ience-0.135
 rewarding-0.130
 decisions-0.130
cious-0.129
Token
Token ID198
Feature activation-4.76e-01

Pos logit contributions
+0.078
ience+0.071
cious+0.069
ages+0.068
's+0.067
Neg logit contributions
 them-0.050
mate-0.045
 tow-0.040
inn-0.039
 ramp-0.037
Token
Token ID198
Feature activation-4.63e-01

Pos logit contributions
+0.032
's+0.028
ages+0.027
aul+0.025
cious+0.024
Neg logit contributions
mate-0.031
 them-0.030
 wreck-0.028
 polar-0.028
 tow-0.028
TokenWhen
Token ID2215
Feature activation+1.44e+00

Pos logit contributions
+0.033
ages+0.029
's+0.029
aul+0.027
 decisions+0.027
Neg logit contributions
mate-0.028
 them-0.028
 tow-0.024
 wreck-0.024
 ramp-0.024
Token the
Token ID262
Feature activation-3.73e-01

Pos logit contributions
 them+0.082
mate+0.077
 tow+0.068
 wreck+0.067
 polar+0.066
Neg logit contributions
-0.112
ages-0.101
's-0.097
aul-0.096
cious-0.094
Token timer
Token ID19781
Feature activation+9.41e+00

Pos logit contributions
+0.027
's+0.024
ages+0.023
aul+0.021
bey+0.020
Neg logit contributions
mate-0.023
 them-0.023
 wreck-0.020
 polar-0.020
 ramp-0.020
Token went
Token ID1816
Feature activation-3.38e+00

Pos logit contributions
 them+0.531
mate+0.501
 tow+0.478
 polar+0.451
 wreck+0.447
Neg logit contributions
-0.706
ages-0.609
aul-0.603
cious-0.600
 List-0.598
Token off
Token ID572
Feature activation-7.53e-01

Pos logit contributions
+0.225
's+0.197
ages+0.178
aul+0.168
 Michelle+0.167
Neg logit contributions
mate-0.215
 them-0.205
 polar-0.203
 ramp-0.202
 snowball-0.198
Token,
Token ID11
Feature activation-4.05e-01

Pos logit contributions
+0.047
's+0.042
ages+0.036
 pays+0.033
aul+0.033
Neg logit contributions
mate-0.054
 captain-0.048
 puck-0.048
 wreck-0.048
 them-0.048
Token they
Token ID484
Feature activation-1.87e+00

Pos logit contributions
+0.035
's+0.031
ages+0.030
aul+0.029
cious+0.028
Neg logit contributions
mate-0.019
 them-0.018
 wreck-0.016
 polar-0.016
 tow-0.016
Token took
Token ID1718
Feature activation-2.23e+00

Pos logit contributions
+0.126
's+0.110
ages+0.100
aul+0.096
cious+0.091
Neg logit contributions
mate-0.130
 them-0.122
 ramp-0.114
 wreck-0.113
 tow-0.112
Token.
Token ID13
Feature activation-2.82e-01

Pos logit contributions
+0.225
's+0.196
ages+0.196
aul+0.187
cious+0.185
Neg logit contributions
 them-0.135
mate-0.133
 wreck-0.116
 polar-0.114
 tow-0.112
Token She
Token ID1375
Feature activation-7.65e-01

Pos logit contributions
+0.022
's+0.019
ages+0.018
aul+0.018
cious+0.017
Neg logit contributions
mate-0.016
 them-0.016
 wreck-0.014
 polar-0.014
 tow-0.014
Token bought
Token ID5839
Feature activation+1.07e+00

Pos logit contributions
+0.055
 decisions+0.053
ages+0.051
cious+0.048
aul+0.048
Neg logit contributions
 them-0.042
mate-0.038
 polar-0.037
 stuffed-0.035
 wreck-0.035
Token him
Token ID683
Feature activation+3.96e+00

Pos logit contributions
 them+0.055
mate+0.047
 polar+0.044
 tow+0.041
 wreck+0.041
Neg logit contributions
-0.091
ages-0.080
's-0.079
cious-0.076
bey-0.076
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
 them+0.217
mate+0.196
 polar+0.182
 his+0.173
 wreck+0.172
Neg logit contributions
-0.313
ages-0.267
's-0.261
cious-0.260
bey-0.257
Token pair
Token ID5166
Feature activation+9.39e+00

Pos logit contributions
+0.076
's+0.067
aul+0.058
ages+0.057
 List+0.053
Neg logit contributions
 them-0.071
mate-0.071
inn-0.064
 ramp-0.058
 wreck-0.057
Token of
Token ID286
Feature activation+2.96e+00

Pos logit contributions
mate+0.505
 ramp+0.493
 snowball+0.490
 them+0.489
 polar+0.480
Neg logit contributions
-0.776
's-0.679
ages-0.605
aul-0.562
cious-0.544
Token new
Token ID649
Feature activation+1.54e+00

Pos logit contributions
mate+0.202
 wreck+0.185
 ramp+0.178
 tow+0.172
inn+0.166
Neg logit contributions
-0.202
's-0.179
ages-0.150
aul-0.140
 persever-0.138
Token shoes
Token ID10012
Feature activation+1.36e+00

Pos logit contributions
mate+0.092
 wreck+0.084
 them+0.084
 tow+0.082
 polar+0.079
Neg logit contributions
-0.118
's-0.112
ages-0.093
cious-0.086
 decisions-0.085
Token.
Token ID13
Feature activation-2.69e-01

Pos logit contributions
mate+0.083
 them+0.080
 polar+0.074
 wreck+0.073
 tow+0.073
Neg logit contributions
-0.099
's-0.088
ages-0.083
aul-0.078
cious-0.075
Token They
Token ID1119
Feature activation+4.16e-02

Pos logit contributions
+0.019
's+0.016
ages+0.015
aul+0.015
cious+0.014
Neg logit contributions
mate-0.018
 them-0.017
 wreck-0.016
 polar-0.016
 tow-0.015
Token fairy
Token ID25607
Feature activation+7.84e-02

Pos logit contributions
+0.076
ages+0.070
's+0.068
aul+0.065
cious+0.064
Neg logit contributions
mate-0.048
 them-0.047
 polar-0.043
 wreck-0.043
 captain-0.042
Token gave
Token ID2921
Feature activation-2.83e+00

Pos logit contributions
 them+0.005
mate+0.005
 polar+0.004
 wreck+0.004
 tow+0.004
Neg logit contributions
-0.005
ages-0.005
aul-0.005
 decisions-0.005
 List-0.004
Token Benny
Token ID44275
Feature activation-7.55e-02

Pos logit contributions
+0.248
's+0.219
ages+0.218
aul+0.208
cious+0.204
Neg logit contributions
 them-0.131
mate-0.128
 polar-0.108
 wreck-0.106
 tow-0.106
Token a
Token ID257
Feature activation-1.08e+00

Pos logit contributions
+0.006
bey+0.005
ages+0.005
cious+0.005
 List+0.005
Neg logit contributions
 them-0.004
mate-0.003
 his-0.003
 polar-0.003
 snowball-0.003
Token special
Token ID2041
Feature activation-2.24e+00

Pos logit contributions
+0.089
's+0.078
ages+0.076
aul+0.073
cious+0.070
Neg logit contributions
mate-0.055
 them-0.055
 wreck-0.047
 polar-0.047
 tow-0.046
Token pair
Token ID5166
Feature activation+9.37e+00

Pos logit contributions
+0.183
's+0.160
ages+0.154
aul+0.148
 decisions+0.143
Neg logit contributions
 them-0.115
mate-0.114
 polar-0.099
 wreck-0.099
 ramp-0.097
Token of
Token ID286
Feature activation+2.95e+00

Pos logit contributions
mate+0.479
 them+0.474
 ramp+0.473
 polar+0.465
 snowball+0.456
Neg logit contributions
-0.797
's-0.686
ages-0.621
aul-0.576
cious-0.570
Token shoes
Token ID10012
Feature activation+1.26e+00

Pos logit contributions
mate+0.172
 them+0.156
 wreck+0.156
 ramp+0.154
inn+0.151
Neg logit contributions
-0.222
's-0.192
ages-0.179
aul-0.169
 decisions-0.166
Token that
Token ID326
Feature activation+5.33e-01

Pos logit contributions
mate+0.073
 them+0.071
 polar+0.065
 wreck+0.064
 tow+0.064
Neg logit contributions
-0.095
's-0.083
ages-0.079
aul-0.075
cious-0.073
Token made
Token ID925
Feature activation+5.71e-01

Pos logit contributions
 them+0.034
mate+0.032
 polar+0.029
 tow+0.029
 wreck+0.028
Neg logit contributions
-0.036
ages-0.032
aul-0.031
 decisions-0.031
's-0.031
Token him
Token ID683
Feature activation+3.98e+00

Pos logit contributions
mate+0.022
 them+0.022
 wreck+0.018
 polar+0.018
 tow+0.018
Neg logit contributions
-0.053
's-0.048
ages-0.047
aul-0.045
cious-0.044
Token
Token ID220
Feature activation-1.07e+00

Pos logit contributions
ience+0.042
ages+0.041
uch+0.040
+0.039
 decisions+0.039
Neg logit contributions
 them-0.022
 tow-0.018
mate-0.016
 his-0.015
 lot-0.015
Token
Token ID198
Feature activation-5.32e-01

Pos logit contributions
+0.089
ience+0.087
cious+0.082
 decisions+0.080
ages+0.080
Neg logit contributions
 them-0.050
mate-0.041
 tow-0.036
inn-0.034
 ramp-0.033
Token
Token ID198
Feature activation-5.34e-01

Pos logit contributions
+0.039
's+0.035
ages+0.034
aul+0.033
 decisions+0.032
Neg logit contributions
 them-0.031
mate-0.030
 tow-0.027
 polar-0.026
 wreck-0.025
TokenWhen
Token ID2215
Feature activation+1.43e+00

Pos logit contributions
+0.034
ages+0.033
aul+0.032
 decisions+0.032
's+0.031
Neg logit contributions
 them-0.033
mate-0.032
 tow-0.029
inn-0.025
 snowball-0.025
Token the
Token ID262
Feature activation-4.96e-01

Pos logit contributions
 them+0.088
mate+0.078
 tow+0.071
 his+0.067
 lot+0.065
Neg logit contributions
ages-0.104
-0.102
aul-0.097
aut-0.096
cious-0.094
Token timer
Token ID19781
Feature activation+9.36e+00

Pos logit contributions
+0.040
ages+0.035
's+0.035
aul+0.033
cious+0.033
Neg logit contributions
 them-0.026
mate-0.025
 tow-0.023
 wreck-0.023
 polar-0.022
Token finally
Token ID3443
Feature activation+5.89e+00

Pos logit contributions
 them+0.514
mate+0.471
 tow+0.464
 polar+0.432
 wreck+0.428
Neg logit contributions
-0.703
ages-0.616
 List-0.615
aul-0.611
cious-0.603
Token be
Token ID307
Feature activation+1.87e+00

Pos logit contributions
 them+0.334
mate+0.322
 tow+0.290
 wreck+0.284
inn+0.281
Neg logit contributions
-0.436
ages-0.393
's-0.378
aul-0.371
 decisions-0.365
Tokenep
Token ID538
Feature activation+5.49e+00

Pos logit contributions
 them+0.121
mate+0.113
 polar+0.105
 tow+0.104
inn+0.103
Neg logit contributions
-0.127
ages-0.106
's-0.105
aul-0.103
 List-0.103
Tokened
Token ID276
Feature activation-3.04e+00

Pos logit contributions
 them+0.343
mate+0.334
 polar+0.301
 tow+0.298
 wreck+0.297
Neg logit contributions
-0.377
ages-0.317
aul-0.314
 List-0.313
's-0.308
Token,
Token ID11
Feature activation-5.80e-01

Pos logit contributions
+0.235
ages+0.205
's+0.204
aul+0.194
cious+0.191
Neg logit contributions
 them-0.172
mate-0.166
 polar-0.147
 wreck-0.146
 tow-0.146
Token.
Token ID13
Feature activation-5.54e-02

Pos logit contributions
mate+0.023
 them+0.023
 wreck+0.020
 polar+0.020
 tow+0.020
Neg logit contributions
-0.032
's-0.028
ages-0.027
aul-0.026
cious-0.025
Token Lily
Token ID20037
Feature activation+2.69e+00

Pos logit contributions
+0.004
ages+0.003
's+0.003
aul+0.003
cious+0.003
Neg logit contributions
 them-0.003
mate-0.003
 polar-0.003
 tow-0.003
 wreck-0.003
Token picked
Token ID6497
Feature activation+8.13e-01

Pos logit contributions
 them+0.155
 polar+0.134
 snowball+0.131
 stuffed+0.131
 hon+0.129
Neg logit contributions
-0.174
ages-0.173
 decisions-0.171
cious-0.165
aul-0.161
Token out
Token ID503
Feature activation-1.43e+00

Pos logit contributions
 them+0.057
mate+0.053
 polar+0.047
 snowball+0.047
 wreck+0.046
Neg logit contributions
-0.053
ages-0.046
's-0.044
aul-0.043
cious-0.043
Token a
Token ID257
Feature activation-1.00e+00

Pos logit contributions
+0.101
's+0.088
ages+0.083
aul+0.079
cious+0.076
Neg logit contributions
mate-0.090
 them-0.087
 wreck-0.081
 polar-0.080
 ramp-0.080
Token pair
Token ID5166
Feature activation+9.35e+00

Pos logit contributions
+0.078
's+0.069
aul+0.056
ages+0.056
cious+0.054
Neg logit contributions
mate-0.062
 them-0.058
inn-0.053
 captain-0.050
 control-0.050
Token with
Token ID351
Feature activation-1.07e+00

Pos logit contributions
 polar+0.516
mate+0.504
 ramp+0.498
 snowball+0.491
 wreck+0.488
Neg logit contributions
-0.800
's-0.687
ages-0.569
aul-0.537
 pays-0.536
Token her
Token ID607
Feature activation+1.26e+00

Pos logit contributions
+0.073
's+0.062
ages+0.057
aul+0.053
cious+0.052
Neg logit contributions
mate-0.073
 wreck-0.065
 ramp-0.065
 them-0.064
 polar-0.062
Token favorite
Token ID4004
Feature activation+1.76e+00

Pos logit contributions
mate+0.077
 them+0.072
 wreck+0.067
inn+0.066
 tow+0.066
Neg logit contributions
-0.095
's-0.085
ages-0.077
aul-0.073
cious-0.071
Token cartoon
Token ID16251
Feature activation+4.28e+00

Pos logit contributions
mate+0.109
inn+0.099
 wreck+0.094
 ramp+0.094
 firefighter+0.092
Neg logit contributions
-0.131
's-0.124
ages-0.099
cious-0.094
 decisions-0.092
Token character
Token ID2095
Feature activation+4.25e+00

Pos logit contributions
mate+0.241
 them+0.239
 polar+0.211
 wreck+0.210
 tow+0.210
Neg logit contributions
-0.323
's-0.281
ages-0.276
aul-0.265
cious-0.257
Token "
Token ID366
Feature activation+2.38e+00

Pos logit contributions
mate+0.064
 wreck+0.061
 them+0.059
 polar+0.059
 ramp+0.056
Neg logit contributions
-0.058
's-0.047
ages-0.041
 List-0.039
 Michelle-0.039
TokenThey
Token ID2990
Feature activation+1.61e+00

Pos logit contributions
mate+0.155
 them+0.153
 polar+0.140
 wreck+0.140
 tow+0.138
Neg logit contributions
-0.163
's-0.139
ages-0.135
aul-0.127
cious-0.123
Token make
Token ID787
Feature activation+2.78e+00

Pos logit contributions
mate+0.091
 them+0.089
 polar+0.079
 wreck+0.078
 tow+0.078
Neg logit contributions
-0.124
's-0.108
ages-0.105
aul-0.100
cious-0.097
Token a
Token ID257
Feature activation-8.41e-01

Pos logit contributions
mate+0.169
 them+0.163
 polar+0.147
 tow+0.147
 wreck+0.147
Neg logit contributions
-0.204
's-0.178
ages-0.170
aul-0.162
cious-0.156
Token nice
Token ID3621
Feature activation+1.43e+00

Pos logit contributions
+0.062
's+0.055
 decisions+0.046
aul+0.043
 pays+0.042
Neg logit contributions
mate-0.054
 them-0.051
inn-0.047
 detector-0.041
uit-0.041
Token pair
Token ID5166
Feature activation+9.35e+00

Pos logit contributions
mate+0.088
 them+0.082
inn+0.075
 cowboy+0.067
 tant+0.066
Neg logit contributions
-0.109
's-0.104
 decisions-0.087
ages-0.082
aul-0.081
Token."
Token ID526
Feature activation+2.73e+00

Pos logit contributions
 snowball+0.582
 polar+0.582
 ramp+0.565
mate+0.560
 puck+0.541
Neg logit contributions
-0.715
's-0.614
ages-0.509
grand-0.438
adow-0.438
Token
Token ID198
Feature activation+4.12e-01

Pos logit contributions
mate+0.192
 them+0.182
 wreck+0.176
 polar+0.172
 ramp+0.167
Neg logit contributions
-0.176
's-0.150
ages-0.140
aul-0.131
 List-0.127
Token
Token ID198
Feature activation+3.97e-01

Pos logit contributions
mate+0.035
 wreck+0.033
 polar+0.032
 captain+0.032
 stuffed+0.031
Neg logit contributions
-0.022
's-0.017
 List-0.014
ages-0.014
aul-0.013
Token"
Token ID1
Feature activation+8.96e-01

Pos logit contributions
mate+0.025
 them+0.024
 wreck+0.023
 polar+0.023
 ramp+0.022
Neg logit contributions
-0.029
's-0.024
ages-0.023
aul-0.021
cious-0.021
TokenI
Token ID40
Feature activation-3.52e-03

Pos logit contributions
mate+0.062
 them+0.061
 polar+0.059
 wreck+0.059
 ramp+0.055
Neg logit contributions
-0.058
's-0.047
ages-0.046
cious-0.043
aul-0.043
Tokenc
Token ID66
Feature activation-3.21e+00

Pos logit contributions
+0.282
's+0.242
ages+0.235
aul+0.222
cious+0.216
Neg logit contributions
mate-0.260
 them-0.258
 polar-0.232
 wreck-0.232
 tow-0.230
Tokenival
Token ID2473
Feature activation+7.61e-01

Pos logit contributions
+0.220
's+0.181
ages+0.181
aul+0.175
cious+0.173
Neg logit contributions
 them-0.206
mate-0.202
 wreck-0.184
 polar-0.179
 tow-0.177
Token took
Token ID1718
Feature activation-2.24e+00

Pos logit contributions
mate+0.045
 them+0.044
 polar+0.040
 wreck+0.040
 tow+0.039
Neg logit contributions
-0.056
's-0.049
ages-0.047
aul-0.044
cious-0.043
Token out
Token ID503
Feature activation-1.47e+00

Pos logit contributions
+0.190
's+0.172
ages+0.162
 pays+0.152
 decisions+0.150
Neg logit contributions
mate-0.109
 them-0.098
 wreck-0.095
 ramp-0.095
 polar-0.095
Token a
Token ID257
Feature activation-1.12e+00

Pos logit contributions
+0.114
's+0.103
ages+0.097
aul+0.089
 decisions+0.089
Neg logit contributions
mate-0.083
 them-0.074
 ramp-0.071
 wreck-0.071
inn-0.069
Token pair
Token ID5166
Feature activation+9.34e+00

Pos logit contributions
+0.087
's+0.076
ages+0.064
aul+0.062
 pays+0.062
Neg logit contributions
 them-0.068
mate-0.064
inn-0.059
 polar-0.055
room-0.053
Token of
Token ID286
Feature activation+2.89e+00

Pos logit contributions
 them+0.475
mate+0.466
 polar+0.456
 snowball+0.439
 ramp+0.434
Neg logit contributions
-0.803
's-0.700
ages-0.619
aul-0.574
 pays-0.560
Token scissors
Token ID41786
Feature activation+2.76e+00

Pos logit contributions
mate+0.171
 them+0.152
inn+0.150
 tow+0.142
 polar+0.141
Neg logit contributions
-0.211
's-0.189
ages-0.174
 decisions-0.167
aul-0.164
Token and
Token ID290
Feature activation-5.94e-01

Pos logit contributions
mate+0.170
 them+0.165
 polar+0.152
 tow+0.151
 wreck+0.150
Neg logit contributions
-0.200
's-0.177
ages-0.166
aul-0.152
cious-0.149
Token said
Token ID531
Feature activation+5.15e-02

Pos logit contributions
+0.045
aul+0.040
ages+0.039
's+0.039
cious+0.038
Neg logit contributions
 them-0.033
mate-0.031
 tow-0.029
 wreck-0.028
 polar-0.028
Token:
Token ID25
Feature activation-3.60e-01

Pos logit contributions
mate+0.003
 them+0.003
 wreck+0.003
 polar+0.003
 tow+0.003
Neg logit contributions
-0.004
's-0.003
ages-0.003
aul-0.003
cious-0.003
Token moments
Token ID7188
Feature activation-2.88e+00

Pos logit contributions
 them+0.165
mate+0.155
 wreck+0.147
 tant+0.145
 snowball+0.144
Neg logit contributions
-0.187
's-0.164
cious-0.159
 Michelle-0.158
aul-0.154
Token to
Token ID284
Feature activation-2.57e-01

Pos logit contributions
+0.218
ages+0.200
's+0.193
cious+0.190
aul+0.189
Neg logit contributions
 them-0.162
mate-0.153
 wreck-0.128
 tow-0.127
inn-0.123
Token check
Token ID2198
Feature activation+7.63e-01

Pos logit contributions
+0.021
's+0.018
ages+0.018
aul+0.017
cious+0.016
Neg logit contributions
mate-0.014
 them-0.013
 wreck-0.012
 polar-0.012
 tow-0.012
Token for
Token ID329
Feature activation+2.63e+00

Pos logit contributions
 them+0.043
mate+0.040
 wreck+0.031
 tow+0.031
 polar+0.031
Neg logit contributions
-0.060
ages-0.054
's-0.052
aul-0.052
cious-0.051
Token the
Token ID262
Feature activation-2.65e-01

Pos logit contributions
 them+0.168
mate+0.155
 tow+0.137
 wreck+0.137
 polar+0.135
Neg logit contributions
-0.190
ages-0.163
's-0.163
aul-0.154
cious-0.154
Token date
Token ID3128
Feature activation+9.34e+00

Pos logit contributions
+0.019
's+0.017
ages+0.017
aul+0.016
cious+0.015
Neg logit contributions
mate-0.016
 them-0.016
 wreck-0.014
 polar-0.014
 tow-0.014
Token can
Token ID460
Feature activation+9.55e-01

Pos logit contributions
mate+0.524
 them+0.515
 tow+0.434
 wreck+0.428
 polar+0.414
Neg logit contributions
-0.699
ages-0.627
's-0.614
aul-0.605
cious-0.585
Token save
Token ID3613
Feature activation+5.79e-01

Pos logit contributions
mate+0.053
 them+0.051
 polar+0.049
 snowball+0.049
 ramp+0.047
Neg logit contributions
-0.078
's-0.067
ages-0.060
aul-0.057
 decisions-0.055
Token you
Token ID345
Feature activation-4.43e+00

Pos logit contributions
 them+0.037
mate+0.030
 his+0.027
 wreck+0.026
 control+0.025
Neg logit contributions
-0.042
cious-0.039
ages-0.038
 List-0.037
aul-0.036
Token from
Token ID422
Feature activation-4.06e+00

Pos logit contributions
+0.354
 List+0.348
ages+0.347
aul+0.335
bey+0.335
Neg logit contributions
 them-0.201
mate-0.167
 wreck-0.148
 his-0.145
 control-0.140
Token a
Token ID257
Feature activation-9.94e-01

Pos logit contributions
+0.311
's+0.271
ages+0.270
aul+0.255
cious+0.252
Neg logit contributions
 them-0.234
mate-0.226
 wreck-0.201
 polar-0.197
 tow-0.194
Token because
Token ID780
Feature activation-2.16e+00

Pos logit contributions
+0.124
ages+0.106
ience+0.106
aul+0.104
bey+0.103
Neg logit contributions
 them-0.084
mate-0.074
 wreck-0.070
 polar-0.066
 his-0.066
Token he
Token ID339
Feature activation-5.04e-01

Pos logit contributions
+0.177
's+0.155
ages+0.147
aul+0.141
 List+0.137
Neg logit contributions
mate-0.112
 them-0.108
 wreck-0.096
 polar-0.095
 ramp-0.095
Token had
Token ID550
Feature activation-1.46e+00

Pos logit contributions
+0.033
's+0.028
ages+0.027
aul+0.025
cious+0.025
Neg logit contributions
mate-0.034
 them-0.034
 wreck-0.031
 polar-0.031
 tow-0.031
Token a
Token ID257
Feature activation-1.22e+00

Pos logit contributions
+0.103
's+0.088
ages+0.087
aul+0.084
cious+0.080
Neg logit contributions
 them-0.091
mate-0.089
 polar-0.080
 wreck-0.080
 tow-0.080
Token new
Token ID649
Feature activation+1.51e+00

Pos logit contributions
+0.090
's+0.079
ages+0.069
aul+0.067
cious+0.066
Neg logit contributions
mate-0.076
 them-0.075
inn-0.068
 control-0.060
 ramp-0.059
Token pair
Token ID5166
Feature activation+9.34e+00

Pos logit contributions
 them+0.081
mate+0.079
inn+0.072
 tow+0.064
 polar+0.063
Neg logit contributions
-0.118
's-0.109
ages-0.096
 decisions-0.092
aul-0.091
Token of
Token ID286
Feature activation+2.84e+00

Pos logit contributions
 them+0.556
 snowball+0.542
mate+0.538
 ramp+0.533
 polar+0.523
Neg logit contributions
-0.721
's-0.635
ages-0.556
adow-0.503
cious-0.502
Token shoes
Token ID10012
Feature activation+1.37e+00

Pos logit contributions
mate+0.203
 ramp+0.189
 wreck+0.189
 tow+0.183
inn+0.174
Neg logit contributions
-0.173
's-0.155
ages-0.131
aul-0.125
cious-0.123
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
mate+0.094
 them+0.087
 snowball+0.085
 polar+0.084
 tow+0.083
Neg logit contributions
-0.094
's-0.084
ages-0.076
aul-0.067
bey-0.066
Token The
Token ID383
Feature activation-1.67e+00

Pos logit contributions
+0.026
ages+0.022
's+0.022
aul+0.021
cious+0.021
Neg logit contributions
 them-0.018
mate-0.017
 tow-0.015
 wreck-0.015
 polar-0.015
Token shoes
Token ID10012
Feature activation+1.34e+00

Pos logit contributions
+0.120
's+0.110
 pays+0.090
bey+0.089
ages+0.089
Neg logit contributions
mate-0.107
 wreck-0.096
 polar-0.094
 them-0.091
 tow-0.089
Token
Token ID198
Feature activation-3.04e-01

Pos logit contributions
+0.017
's+0.014
ages+0.011
aul+0.011
 List+0.011
Neg logit contributions
mate-0.022
 captain-0.021
 wreck-0.021
 polar-0.021
 puck-0.020
TokenWhen
Token ID2215
Feature activation+1.49e+00

Pos logit contributions
+0.022
's+0.018
ages+0.018
aul+0.017
cious+0.016
Neg logit contributions
mate-0.019
 them-0.019
 polar-0.017
 wreck-0.017
 ramp-0.017
Token Lucy
Token ID22162
Feature activation+2.84e-01

Pos logit contributions
 them+0.081
mate+0.073
 tow+0.064
 wreck+0.060
 polar+0.059
Neg logit contributions
-0.120
ages-0.114
aul-0.108
's-0.107
cious-0.106
Token marked
Token ID7498
Feature activation+2.44e+00

Pos logit contributions
 them+0.016
mate+0.015
 wreck+0.015
 tow+0.015
 polar+0.014
Neg logit contributions
ages-0.018
 decisions-0.018
-0.018
 List-0.018
aul-0.017
Token the
Token ID262
Feature activation-2.90e-01

Pos logit contributions
mate+0.130
 them+0.129
 wreck+0.112
 polar+0.112
 tow+0.111
Neg logit contributions
-0.194
's-0.170
ages-0.167
aul-0.160
cious-0.156
Token date
Token ID3128
Feature activation+9.34e+00

Pos logit contributions
+0.023
ages+0.021
apa+0.020
aul+0.019
bey+0.019
Neg logit contributions
 them-0.015
mate-0.014
 match-0.013
 lot-0.013
 stuffed-0.013
Token,
Token ID11
Feature activation-3.71e-01

Pos logit contributions
mate+0.504
 them+0.497
 tow+0.416
 ramp+0.401
 wreck+0.399
Neg logit contributions
-0.708
ages-0.658
aul-0.631
's-0.611
 decisions-0.607
Token a
Token ID257
Feature activation-1.04e+00

Pos logit contributions
+0.026
ages+0.026
aul+0.024
cious+0.023
bey+0.023
Neg logit contributions
 them-0.023
mate-0.021
 his-0.020
 stuffed-0.019
 tow-0.019
Token rainbow
Token ID27223
Feature activation+5.29e-01

Pos logit contributions
+0.077
's+0.067
ages+0.061
aul+0.059
cious+0.058
Neg logit contributions
 them-0.063
mate-0.062
inn-0.057
 polar-0.055
 wreck-0.054
Token-
Token ID12
Feature activation-4.12e-01

Pos logit contributions
 them+0.030
mate+0.030
 wreck+0.027
 polar+0.026
 tow+0.026
Neg logit contributions
-0.040
's-0.034
ages-0.034
aul-0.033
cious-0.031
Tokencol
Token ID4033
Feature activation-9.36e+00

Pos logit contributions
+0.027
 decisions+0.024
ages+0.024
's+0.023
aul+0.022
Neg logit contributions
 them-0.027
mate-0.025
 tow-0.022
 wreck-0.022
inn-0.022
Token a
Token ID257
Feature activation-1.16e+00

Pos logit contributions
+0.118
ages+0.105
's+0.101
cious+0.100
aul+0.099
Neg logit contributions
 them-0.090
mate-0.081
 tow-0.073
 polar-0.073
 wreck-0.070
Token calendar
Token ID11845
Feature activation-1.99e+00

Pos logit contributions
+0.092
's+0.082
ages+0.076
aul+0.072
cious+0.071
Neg logit contributions
mate-0.063
 them-0.062
inn-0.054
 polar-0.053
 tow-0.053
Token and
Token ID290
Feature activation-5.89e-01

Pos logit contributions
+0.156
ages+0.138
's+0.135
aul+0.132
cious+0.131
Neg logit contributions
mate-0.106
 them-0.104
 wreck-0.090
 tow-0.089
 ramp-0.088
Token mark
Token ID1317
Feature activation+3.37e-02

Pos logit contributions
ages+0.049
aul+0.049
+0.048
aut+0.046
ience+0.046
Neg logit contributions
 them-0.027
mate-0.021
 match-0.021
 tow-0.020
 stuffed-0.020
Token the
Token ID262
Feature activation-3.66e-01

Pos logit contributions
 them+0.002
mate+0.002
 tow+0.002
 polar+0.002
 wreck+0.002
Neg logit contributions
-0.003
's-0.002
ages-0.002
aul-0.002
cious-0.002
Token date
Token ID3128
Feature activation+9.33e+00

Pos logit contributions
+0.028
ages+0.025
apa+0.024
bey+0.024
aul+0.023
Neg logit contributions
 them-0.020
 lot-0.018
mate-0.018
 match-0.016
 stuffed-0.016
Token with
Token ID351
Feature activation-9.75e-01

Pos logit contributions
mate+0.527
 them+0.522
 wreck+0.465
 polar+0.464
 tow+0.459
Neg logit contributions
-0.709
's-0.619
ages-0.603
aul-0.574
cious-0.559
Token a
Token ID257
Feature activation-1.14e+00

Pos logit contributions
+0.070
's+0.060
ages+0.058
aul+0.055
cious+0.053
Neg logit contributions
mate-0.060
 them-0.056
 wreck-0.054
 polar-0.054
 ramp-0.054
Token cr
Token ID1067
Feature activation+4.53e-01

Pos logit contributions
+0.091
's+0.080
ages+0.076
aul+0.073
cious+0.071
Neg logit contributions
mate-0.061
 them-0.061
 polar-0.054
 wreck-0.053
inn-0.052
Tokenay
Token ID323
Feature activation+4.37e+00

Pos logit contributions
mate+0.022
 them+0.021
 polar+0.019
 wreck+0.019
 ramp+0.019
Neg logit contributions
-0.039
's-0.034
ages-0.034
aul-0.033
cious-0.031
Tokenon
Token ID261
Feature activation-4.90e-01

Pos logit contributions
 them+0.283
mate+0.281
 tow+0.244
 wreck+0.238
 polar+0.237
Neg logit contributions
-0.297
's-0.253
ages-0.250
aul-0.241
cious-0.236
Token by
Token ID416
Feature activation-2.64e+00

Pos logit contributions
+0.016
's+0.013
 List+0.009
aul+0.009
ages+0.009
Neg logit contributions
mate-0.026
 captain-0.025
 wreck-0.025
 polar-0.025
 puck-0.025
Token one
Token ID530
Feature activation-5.79e-02

Pos logit contributions
+0.195
's+0.169
ages+0.161
aul+0.153
cious+0.149
Neg logit contributions
mate-0.155
 them-0.150
 polar-0.138
 tow-0.137
 wreck-0.137
Token
Token ID6184
Feature activation-1.97e-03

Pos logit contributions
+0.005
ages+0.004
's+0.004
aul+0.004
cious+0.004
Neg logit contributions
mate-0.003
 them-0.003
 wreck-0.003
 polar-0.003
 tow-0.003
Token
Token ID95
Feature activation+6.27e-02

Pos logit contributions
+0.000
's+0.000
ages+0.000
aul+0.000
cious+0.000
Neg logit contributions
mate-0.000
 them-0.000
 wreck-0.000
 tow-0.000
 polar-0.000
Token
Token ID26391
Feature activation-2.89e+00

Pos logit contributions
mate+0.004
 them+0.004
 tow+0.004
 ramp+0.004
inn+0.004
Neg logit contributions
-0.004
ages-0.003
's-0.003
aul-0.003
bey-0.003
Token
Token ID447
Feature activation-1.36e+01

Pos logit contributions
+0.213
 decisions+0.205
ages+0.198
aul+0.197
ience+0.196
Neg logit contributions
 them-0.137
mate-0.135
 tow-0.123
 ramp-0.122
 racer-0.114
Token
Token ID250
Feature activation+6.69e-02

Pos logit contributions
+0.975
's+0.870
ages+0.863
aul+0.795
 decisions+0.792
Neg logit contributions
mate-0.796
 them-0.776
 wreck-0.706
 ramp-0.696
 tow-0.696
Token 1
Token ID352
Feature activation+1.11e+00

Pos logit contributions
mate+0.004
 them+0.004
 tow+0.004
inn+0.004
 wreck+0.004
Neg logit contributions
-0.004
's-0.004
ages-0.004
aul-0.004
cious-0.004
Token,
Token ID11
Feature activation-9.62e-01

Pos logit contributions
mate+0.061
 them+0.061
 wreck+0.053
 tow+0.053
 polar+0.053
Neg logit contributions
-0.084
's-0.074
ages-0.073
aul-0.070
cious-0.068
Token 2
Token ID362
Feature activation+8.90e-01

Pos logit contributions
+0.046
ages+0.041
's+0.039
aul+0.037
cious+0.035
Neg logit contributions
 them-0.078
mate-0.076
 tow-0.070
 polar-0.070
 wreck-0.070
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
 them+0.048
mate+0.047
 polar+0.041
 wreck+0.040
 tow+0.040
Neg logit contributions
-0.069
's-0.060
ages-0.060
aul-0.057
cious-0.056
Token rare
Token ID4071
Feature activation+4.01e-01

Pos logit contributions
+0.122
's+0.106
ages+0.103
aul+0.098
cious+0.095
Neg logit contributions
mate-0.095
 them-0.094
 wreck-0.083
 polar-0.083
 tow-0.083
Token silence
Token ID9550
Feature activation-2.82e+00

Pos logit contributions
mate+0.022
 them+0.021
 wreck+0.019
 polar+0.019
 tow+0.019
Neg logit contributions
-0.032
's-0.028
ages-0.027
aul-0.026
cious-0.025
Token
Token ID6184
Feature activation-1.47e-01

Pos logit contributions
+0.216
ages+0.194
's+0.189
aul+0.185
cious+0.181
Neg logit contributions
 them-0.152
mate-0.148
 wreck-0.130
 polar-0.127
 tow-0.126
Token
Token ID95
Feature activation+6.08e-02

Pos logit contributions
ages+0.009
+0.009
's+0.009
aul+0.008
 decisions+0.008
Neg logit contributions
mate-0.009
 them-0.009
 tow-0.008
inn-0.008
 ramp-0.008
Token
Token ID26391
Feature activation-2.95e+00

Pos logit contributions
mate+0.004
 them+0.004
inn+0.004
 tow+0.004
 ramp+0.004
Neg logit contributions
ages-0.003
-0.003
's-0.003
aul-0.003
 decisions-0.003
Token
Token ID447
Feature activation-1.35e+01

Pos logit contributions
 decisions+0.182
aul+0.179
+0.178
 List+0.169
 persever+0.169
Neg logit contributions
 them-0.162
mate-0.157
 tow-0.151
 ramp-0.147
 racer-0.144
Token
Token ID250
Feature activation+1.38e-01

Pos logit contributions
+0.968
ages+0.935
's+0.909
 decisions+0.871
cious+0.861
Neg logit contributions
mate-0.713
 them-0.694
 ramp-0.655
 wreck-0.650
 tow-0.630
Token that
Token ID326
Feature activation+1.26e-01

Pos logit contributions
mate+0.009
 them+0.009
 tow+0.008
 wreck+0.008
inn+0.008
Neg logit contributions
-0.009
's-0.008
ages-0.008
aul-0.008
cious-0.007
Token added
Token ID2087
Feature activation-1.90e+00

Pos logit contributions
 them+0.010
mate+0.009
 wreck+0.009
 splash+0.009
 rock+0.008
Neg logit contributions
ages-0.006
assy-0.006
aul-0.006
cious-0.006
bey-0.005
Token to
Token ID284
Feature activation-6.98e-01

Pos logit contributions
+0.138
ages+0.125
's+0.121
aul+0.118
cious+0.117
Neg logit contributions
 them-0.113
mate-0.104
 wreck-0.089
 polar-0.089
 tow-0.088
Token the
Token ID262
Feature activation-7.62e-01

Pos logit contributions
+0.053
ages+0.047
's+0.046
aul+0.045
cious+0.043
Neg logit contributions
 them-0.040
mate-0.038
 wreck-0.034
 polar-0.034
 tow-0.033
Token something
Token ID1223
Feature activation-4.07e+00

Pos logit contributions
 them+0.053
mate+0.050
 wreck+0.044
 polar+0.043
 tow+0.043
Neg logit contributions
-0.065
ages-0.059
's-0.057
aul-0.056
bey-0.054
Token strange
Token ID6283
Feature activation-1.44e+00

Pos logit contributions
+0.295
's+0.255
ages+0.247
aul+0.234
cious+0.228
Neg logit contributions
mate-0.246
 them-0.243
 polar-0.218
 wreck-0.218
 tow-0.216
Token
Token ID6184
Feature activation-3.02e-01

Pos logit contributions
+0.115
ages+0.102
's+0.100
aul+0.098
cious+0.094
Neg logit contributions
 them-0.076
mate-0.074
 wreck-0.063
 polar-0.062
 tow-0.061
Token
Token ID95
Feature activation-7.74e-02

Pos logit contributions
ages+0.020
+0.019
's+0.018
 decisions+0.017
 mindful+0.017
Neg logit contributions
mate-0.018
 ramp-0.017
 them-0.017
 wreck-0.016
 tow-0.016
Token
Token ID26391
Feature activation-3.03e+00

Pos logit contributions
ages+0.004
+0.004
bey+0.004
 decisions+0.004
aul+0.004
Neg logit contributions
mate-0.005
 them-0.005
 ramp-0.005
 tow-0.005
inn-0.005
Token
Token ID447
Feature activation-1.34e+01

Pos logit contributions
 decisions+0.194
aul+0.182
 persever+0.181
ience+0.180
+0.177
Neg logit contributions
 them-0.164
mate-0.151
room-0.148
 ramp-0.147
 tow-0.143
Token
Token ID250
Feature activation+1.59e-01

Pos logit contributions
ages+1.117
 decisions+1.100
+1.081
's+1.033
cious+1.016
Neg logit contributions
 them-0.513
mate-0.499
 ramp-0.465
 wreck-0.451
 tow-0.438
Token the
Token ID262
Feature activation-8.46e-01

Pos logit contributions
mate+0.010
 them+0.010
 tow+0.009
 wreck+0.009
inn+0.009
Neg logit contributions
-0.010
's-0.010
ages-0.009
aul-0.009
ience-0.009
Token mirror
Token ID10162
Feature activation+2.00e-01

Pos logit contributions
+0.067
ages+0.062
's+0.060
aul+0.058
cious+0.056
Neg logit contributions
mate-0.042
 them-0.041
 wreck-0.039
 polar-0.038
 tow-0.036
Token was
Token ID373
Feature activation+1.09e-01

Pos logit contributions
 them+0.011
mate+0.011
 wreck+0.009
 match+0.009
 ramp+0.009
Neg logit contributions
-0.014
 List-0.013
ages-0.013
aul-0.013
 Michelle-0.012
Token making
Token ID1642
Feature activation+3.41e+00

Pos logit contributions
 them+0.006
mate+0.006
 polar+0.005
 wreck+0.005
 tow+0.005
Neg logit contributions
-0.008
ages-0.008
aul-0.007
's-0.007
bey-0.007
Token from
Token ID422
Feature activation-4.40e+00

Pos logit contributions
+0.109
's+0.095
ages+0.089
aul+0.084
cious+0.082
Neg logit contributions
mate-0.083
 them-0.080
 tow-0.073
 wreck-0.073
 ramp-0.072
Token overhead
Token ID16965
Feature activation+1.86e+00

Pos logit contributions
+0.264
's+0.218
 praying+0.206
 Michelle+0.199
 Louise+0.197
Neg logit contributions
mate-0.296
inn-0.270
 ramp-0.257
 tant-0.254
 puck-0.254
Token
Token ID6184
Feature activation-3.24e-01

Pos logit contributions
mate+0.103
 them+0.101
 wreck+0.090
 polar+0.090
 tow+0.089
Neg logit contributions
-0.144
's-0.127
ages-0.122
aul-0.116
cious-0.113
Token
Token ID95
Feature activation-1.71e-01

Pos logit contributions
+0.022
ages+0.021
's+0.020
bey+0.019
 decisions+0.019
Neg logit contributions
mate-0.019
 them-0.018
 wreck-0.018
 ramp-0.017
 tow-0.017
Token
Token ID26391
Feature activation-3.16e+00

Pos logit contributions
+0.010
ages+0.010
bey+0.009
ience+0.009
aul+0.009
Neg logit contributions
mate-0.012
 them-0.011
 tow-0.011
 wreck-0.010
 ramp-0.010
Token
Token ID447
Feature activation-1.34e+01

Pos logit contributions
+0.216
 decisions+0.214
ience+0.205
aul+0.203
 persever+0.203
Neg logit contributions
 them-0.158
mate-0.152
 ramp-0.149
 tow-0.144
 wreck-0.144
Token
Token ID250
Feature activation+1.26e-01

Pos logit contributions
+0.935
ages+0.851
's+0.830
 decisions+0.813
aul+0.766
Neg logit contributions
mate-0.779
 them-0.770
 wreck-0.721
 ramp-0.714
 tow-0.696
Token it
Token ID340
Feature activation+8.60e-01

Pos logit contributions
mate+0.008
 them+0.008
 polar+0.007
 wreck+0.007
 tow+0.007
Neg logit contributions
-0.009
's-0.008
ages-0.008
aul-0.007
cious-0.007
Token was
Token ID373
Feature activation+1.21e-01

Pos logit contributions
 them+0.071
 wreck+0.068
mate+0.067
 polar+0.067
 hon+0.065
Neg logit contributions
ages-0.037
aul-0.036
cious-0.032
oney-0.030
 List-0.030
Token a
Token ID257
Feature activation-1.59e+00

Pos logit contributions
 them+0.007
mate+0.006
 polar+0.006
 tow+0.005
 wreck+0.005
Neg logit contributions
-0.009
ages-0.009
aul-0.009
bey-0.008
cious-0.008
Token switch
Token ID5078
Feature activation+2.57e+00

Pos logit contributions
+0.121
's+0.105
ages+0.099
aul+0.095
cious+0.094
Neg logit contributions
 them-0.091
mate-0.090
inn-0.079
 tow-0.078
 wreck-0.076
Token of
Token ID286
Feature activation+2.60e+00

Pos logit contributions
ages+0.176
aul+0.170
+0.166
ience+0.161
bey+0.161
Neg logit contributions
 them-0.110
mate-0.091
 tow-0.075
 control-0.071
 his-0.071
Token school
Token ID1524
Feature activation+3.02e+00

Pos logit contributions
mate+0.157
 them+0.148
 wreck+0.140
 polar+0.140
 ramp+0.139
Neg logit contributions
-0.190
's-0.163
ages-0.154
aul-0.149
cious-0.144
Token
Token ID6184
Feature activation-3.10e-01

Pos logit contributions
 them+0.150
mate+0.145
 wreck+0.123
 tow+0.120
 ramp+0.119
Neg logit contributions
-0.241
ages-0.219
aul-0.215
's-0.207
cious-0.205
Token
Token ID95
Feature activation-4.43e-02

Pos logit contributions
+0.019
ages+0.019
's+0.018
 decisions+0.017
aul+0.016
Neg logit contributions
mate-0.020
 them-0.019
 wreck-0.018
inn-0.018
 ramp-0.017
Token
Token ID26391
Feature activation-2.96e+00

Pos logit contributions
ages+0.002
+0.002
 decisions+0.002
aul+0.002
ience+0.002
Neg logit contributions
mate-0.003
 them-0.003
 tow-0.003
inn-0.003
room-0.003
Token
Token ID447
Feature activation-1.34e+01

Pos logit contributions
 decisions+0.194
+0.185
aul+0.182
ience+0.177
 persever+0.177
Neg logit contributions
 them-0.161
mate-0.149
room-0.142
 tow-0.140
 ramp-0.138
Token
Token ID250
Feature activation+2.81e-01

Pos logit contributions
+1.098
ages+0.996
's+0.988
 decisions+0.943
cious+0.918
Neg logit contributions
mate-0.643
 them-0.630
 wreck-0.555
 ramp-0.550
 tow-0.547
Token it
Token ID340
Feature activation+9.41e-01

Pos logit contributions
mate+0.018
 them+0.018
 tow+0.016
 wreck+0.016
 polar+0.016
Neg logit contributions
-0.019
's-0.016
ages-0.016
aul-0.015
cious-0.014
Token was
Token ID373
Feature activation+1.06e-01

Pos logit contributions
 them+0.076
mate+0.074
 match+0.071
 wreck+0.068
 ramp+0.067
Neg logit contributions
ages-0.038
aul-0.037
cious-0.034
oney-0.031
 List-0.031
Token an
Token ID281
Feature activation-2.66e+00

Pos logit contributions
 them+0.006
mate+0.006
 tow+0.005
 polar+0.005
 wreck+0.005
Neg logit contributions
-0.008
ages-0.007
's-0.007
aul-0.007
cious-0.007
Token important
Token ID1593
Feature activation-4.50e+00

Pos logit contributions
+0.173
's+0.148
ages+0.143
aul+0.135
cious+0.131
Neg logit contributions
mate-0.180
 them-0.178
 wreck-0.161
 polar-0.161
 tow-0.160
Token something
Token ID1223
Feature activation-4.09e+00

Pos logit contributions
mate+0.053
 them+0.050
 tow+0.047
 ramp+0.047
inn+0.046
Neg logit contributions
-0.050
's-0.044
ages-0.040
aul-0.038
cious-0.036
Token special
Token ID2041
Feature activation-2.51e+00

Pos logit contributions
+0.311
's+0.270
ages+0.236
cious+0.223
aul+0.222
Neg logit contributions
mate-0.253
 them-0.234
 tow-0.217
 polar-0.214
 captain-0.214
Token
Token ID6184
Feature activation-4.24e-01

Pos logit contributions
+0.197
's+0.171
ages+0.171
aul+0.163
cious+0.159
Neg logit contributions
mate-0.136
 them-0.136
 wreck-0.118
 polar-0.117
 tow-0.115
Token
Token ID95
Feature activation-2.18e-01

Pos logit contributions
+0.030
ages+0.027
's+0.026
 decisions+0.025
bey+0.025
Neg logit contributions
mate-0.025
 them-0.023
 ramp-0.023
 wreck-0.023
 tow-0.021
Token
Token ID26391
Feature activation-3.15e+00

Pos logit contributions
+0.013
ages+0.012
bey+0.011
 decisions+0.011
ience+0.011
Neg logit contributions
mate-0.015
 them-0.014
 ramp-0.013
 tow-0.013
 wreck-0.013
Token
Token ID447
Feature activation-1.34e+01

Pos logit contributions
+0.189
 decisions+0.174
aul+0.161
ience+0.161
 persever+0.158
Neg logit contributions
 them-0.200
mate-0.197
 ramp-0.192
room-0.184
 snowball-0.182
Token
Token ID250
Feature activation+1.63e-01

Pos logit contributions
+0.982
ages+0.880
's+0.855
 decisions+0.845
aul+0.798
Neg logit contributions
 them-0.736
mate-0.730
 wreck-0.681
 ramp-0.677
 tow-0.651
Token a
Token ID257
Feature activation-1.46e+00

Pos logit contributions
mate+0.010
 them+0.010
 wreck+0.009
 polar+0.009
 tow+0.009
Neg logit contributions
-0.012
's-0.010
ages-0.010
aul-0.009
cious-0.009
Token pool
Token ID5933
Feature activation+3.35e+00

Pos logit contributions
+0.117
's+0.102
ages+0.097
aul+0.093
cious+0.093
Neg logit contributions
 them-0.080
mate-0.078
inn-0.068
 tow-0.066
 wreck-0.065
Token!
Token ID0
Feature activation+7.77e-01

Pos logit contributions
 them+0.186
mate+0.186
 polar+0.164
 tow+0.163
 wreck+0.162
Neg logit contributions
-0.261
's-0.227
ages-0.217
aul-0.207
cious-0.200
Token It
Token ID632
Feature activation+7.67e-01

Pos logit contributions
mate+0.049
 them+0.048
 tow+0.046
 polar+0.045
 wreck+0.042
Neg logit contributions
ages-0.048
-0.048
's-0.045
aul-0.044
bey-0.043
Tokent
Token ID83
Feature activation+1.80e-01

Pos logit contributions
+0.352
's+0.297
ages+0.274
aul+0.256
cious+0.245
Neg logit contributions
mate-0.353
 them-0.350
 polar-0.335
 wreck-0.331
 ramp-0.329
Token help
Token ID1037
Feature activation+1.26e+00

Pos logit contributions
mate+0.011
 them+0.011
 snowball+0.011
 ramp+0.010
 polar+0.010
Neg logit contributions
-0.014
's-0.011
ages-0.009
 mindful-0.009
cious-0.009
Token it
Token ID340
Feature activation+1.16e+00

Pos logit contributions
mate+0.078
 tow+0.073
 ramp+0.072
 polar+0.072
 wreck+0.072
Neg logit contributions
-0.090
's-0.079
ages-0.065
 decisions-0.064
 pays-0.060
Tokenâ
Token ID22940
Feature activation-1.99e+00

Pos logit contributions
mate+0.072
 polar+0.072
 tow+0.070
 them+0.070
 firefighter+0.068
Neg logit contributions
-0.086
's-0.076
ages-0.060
 pays-0.057
 decisions-0.056
Token
Token ID26391
Feature activation-3.07e+00

Pos logit contributions
+0.099
ages+0.087
's+0.084
cious+0.081
aul+0.080
Neg logit contributions
mate-0.157
 them-0.149
inn-0.144
 wreck-0.138
 ramp-0.136
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.178
 decisions+0.161
aul+0.157
ience+0.154
 List+0.152
Neg logit contributions
 them-0.199
mate-0.197
 ramp-0.187
 wreck-0.178
 tow-0.177
Token
Token ID251
Feature activation-3.77e-01

Pos logit contributions
+1.103
's+0.985
ages+0.971
aul+0.920
cious+0.917
Neg logit contributions
mate-0.651
 them-0.637
 wreck-0.559
 ramp-0.551
 tow-0.550
Tokenhe
Token ID258
Feature activation+5.88e+00

Pos logit contributions
+0.027
's+0.023
ages+0.023
aul+0.022
cious+0.021
Neg logit contributions
 them-0.023
mate-0.023
 polar-0.020
 wreck-0.020
 tow-0.020
Token reached
Token ID4251
Feature activation+2.74e-01

Pos logit contributions
mate+0.354
 them+0.346
 tow+0.331
 wreck+0.329
 polar+0.326
Neg logit contributions
-0.418
's-0.369
ages-0.348
aul-0.318
cious-0.313
Token out
Token ID503
Feature activation-1.72e+00

Pos logit contributions
mate+0.018
 wreck+0.016
 them+0.016
 polar+0.015
 ramp+0.015
Neg logit contributions
-0.019
's-0.017
ages-0.015
 pays-0.014
 decisions-0.014
Token and
Token ID290
Feature activation-8.61e-01

Pos logit contributions
+0.148
's+0.128
ages+0.108
 pays+0.107
 Louise+0.106
Neg logit contributions
mate-0.086
 wreck-0.084
 ramp-0.083
 spoiler-0.074
 puck-0.074
Token those
Token ID883
Feature activation+7.47e-01

Pos logit contributions
+0.008
ages+0.007
cious+0.007
ience+0.007
bey+0.007
Neg logit contributions
 them-0.004
mate-0.004
 tow-0.004
 polar-0.004
 wreck-0.004
Token in
Token ID287
Feature activation+6.80e-02

Pos logit contributions
 them+0.045
mate+0.043
 wreck+0.039
 polar+0.038
 tow+0.038
Neg logit contributions
-0.054
ages-0.047
's-0.047
aul-0.044
cious-0.043
Token need
Token ID761
Feature activation+1.12e+00

Pos logit contributions
mate+0.004
 them+0.004
 polar+0.003
 wreck+0.003
 tow+0.003
Neg logit contributions
-0.005
's-0.005
ages-0.004
aul-0.004
 decisions-0.004
Tokenâ
Token ID22940
Feature activation-1.88e+00

Pos logit contributions
mate+0.064
 them+0.064
 wreck+0.057
 polar+0.056
 tow+0.056
Neg logit contributions
-0.084
's-0.074
ages-0.072
aul-0.068
cious-0.066
Token
Token ID26391
Feature activation-2.86e+00

Pos logit contributions
ages+0.102
+0.101
cious+0.099
's+0.094
aul+0.089
Neg logit contributions
mate-0.124
 them-0.123
inn-0.117
 wreck-0.111
 load-0.103
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.156
aul+0.155
 decisions+0.151
 pays+0.150
ience+0.149
Neg logit contributions
 them-0.178
mate-0.170
 tow-0.153
 ramp-0.152
 wreck-0.150
Token
Token ID251
Feature activation-4.20e-01

Pos logit contributions
+0.835
ages+0.757
's+0.749
cious+0.709
 decisions+0.699
Neg logit contributions
mate-0.851
 them-0.836
 wreck-0.788
 ramp-0.775
 tow-0.755
Tokeneven
Token ID10197
Feature activation-2.96e+00

Pos logit contributions
+0.029
ages+0.026
's+0.026
aul+0.025
cious+0.024
Neg logit contributions
 them-0.026
mate-0.025
 polar-0.022
 tow-0.022
 wreck-0.021
Token<|endoftext|>
Token ID50256
Feature activation-1.03e+00

Pos logit contributions
+0.197
ages+0.184
aul+0.171
's+0.170
cious+0.168
Neg logit contributions
 them-0.186
mate-0.182
 polar-0.159
 tant-0.159
inn-0.155
TokenOne
Token ID3198
Feature activation+1.89e+00

Pos logit contributions
+0.071
ages+0.065
's+0.062
aul+0.059
cious+0.059
Neg logit contributions
 them-0.063
mate-0.061
 polar-0.054
 tow-0.054
 wreck-0.054
Token day
Token ID1110
Feature activation-2.00e+00

Pos logit contributions
 them+0.110
mate+0.104
 wreck+0.100
 polar+0.098
 tow+0.097
Neg logit contributions
-0.130
ages-0.129
cious-0.117
's-0.115
aul-0.115
Token anxious
Token ID18116
Feature activation-4.85e-01

Pos logit contributions
mate+0.332
 them+0.322
 tow+0.300
 ramp+0.299
 wreck+0.295
Neg logit contributions
-0.254
's-0.213
ages-0.203
aul-0.185
cious-0.180
Token anymore
Token ID7471
Feature activation+4.71e+00

Pos logit contributions
+0.044
's+0.040
ages+0.039
aul+0.037
cious+0.036
Neg logit contributions
mate-0.020
 them-0.020
 polar-0.017
 wreck-0.017
 tow-0.017
Token
Token ID6184
Feature activation-3.33e-01

Pos logit contributions
mate+0.270
 them+0.269
 wreck+0.238
 polar+0.237
 tow+0.234
Neg logit contributions
-0.353
's-0.307
ages-0.301
aul-0.288
cious-0.280
Token
Token ID95
Feature activation-1.31e-01

Pos logit contributions
+0.023
's+0.021
ages+0.020
aul+0.019
cious+0.018
Neg logit contributions
mate-0.021
 them-0.020
 wreck-0.018
 tow-0.018
 ramp-0.018
Token
Token ID26391
Feature activation-3.04e+00

Pos logit contributions
+0.007
ages+0.007
aul+0.006
's+0.006
cious+0.006
Neg logit contributions
mate-0.010
 them-0.009
 wreck-0.009
 ramp-0.009
 tow-0.008
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.197
 decisions+0.183
aul+0.180
 persever+0.174
ience+0.173
Neg logit contributions
 them-0.172
mate-0.164
 ramp-0.153
 wreck-0.150
 racer-0.149
Token
Token ID251
Feature activation-4.49e-01

Pos logit contributions
+1.063
's+0.948
ages+0.945
 decisions+0.899
cious+0.883
Neg logit contributions
mate-0.674
 them-0.656
 wreck-0.592
 ramp-0.589
 tow-0.569
Token he
Token ID339
Feature activation-9.23e-01

Pos logit contributions
+0.033
ages+0.030
's+0.029
aul+0.029
cious+0.028
Neg logit contributions
 them-0.026
mate-0.025
 polar-0.022
 tow-0.022
 wreck-0.021
Token knew
Token ID2993
Feature activation-5.57e-01

Pos logit contributions
+0.061
ages+0.054
aul+0.052
's+0.052
cious+0.050
Neg logit contributions
 them-0.059
mate-0.057
 polar-0.052
 wreck-0.052
 tow-0.051
Token he
Token ID339
Feature activation-8.65e-01

Pos logit contributions
+0.043
's+0.037
ages+0.036
aul+0.034
cious+0.033
Neg logit contributions
mate-0.031
 them-0.031
 wreck-0.027
 polar-0.027
 tow-0.027
Token was
Token ID373
Feature activation+2.50e-01

Pos logit contributions
+0.060
aul+0.057
ages+0.056
cious+0.053
 decisions+0.053
Neg logit contributions
 them-0.048
mate-0.047
 wreck-0.042
 tow-0.040
 polar-0.040
Token and
Token ID290
Feature activation-1.91e-01

Pos logit contributions
+0.037
's+0.033
ages+0.031
aul+0.028
cious+0.028
Neg logit contributions
mate-0.023
 wreck-0.022
 tow-0.022
 ramp-0.021
 polar-0.021
Token rocked
Token ID36872
Feature activation-4.40e-01

Pos logit contributions
+0.015
aul+0.013
ages+0.013
 decisions+0.013
's+0.012
Neg logit contributions
 them-0.011
mate-0.010
 polar-0.009
 snowball-0.009
 puck-0.009
Token
Token ID6184
Feature activation-1.30e-01

Pos logit contributions
+0.032
's+0.028
ages+0.025
aul+0.023
cious+0.022
Neg logit contributions
 wreck-0.026
mate-0.026
 polar-0.025
 tow-0.025
 ramp-0.025
Token
Token ID95
Feature activation-5.35e-03

Pos logit contributions
+0.009
's+0.008
ages+0.008
aul+0.008
cious+0.007
Neg logit contributions
mate-0.008
 them-0.008
 wreck-0.007
 polar-0.007
 tow-0.007
Token
Token ID26391
Feature activation-2.92e+00

Pos logit contributions
+0.000
ages+0.000
's+0.000
aul+0.000
bey+0.000
Neg logit contributions
mate-0.000
 them-0.000
 ramp-0.000
 tow-0.000
inn-0.000
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.189
 decisions+0.179
aul+0.173
 List+0.168
 Michelle+0.166
Neg logit contributions
 them-0.165
mate-0.158
 ramp-0.155
 snowball-0.147
 tow-0.144
Token
Token ID250
Feature activation+1.01e-01

Pos logit contributions
+0.992
's+0.886
ages+0.874
 decisions+0.818
cious+0.812
Neg logit contributions
mate-0.745
 them-0.732
 wreck-0.656
 ramp-0.651
 tow-0.646
Token higher
Token ID2440
Feature activation-2.02e+00

Pos logit contributions
mate+0.006
 them+0.006
 tow+0.006
 polar+0.006
inn+0.006
Neg logit contributions
-0.007
's-0.006
ages-0.006
aul-0.006
 decisions-0.005
Token and
Token ID290
Feature activation-1.04e+00

Pos logit contributions
+0.163
's+0.144
ages+0.142
aul+0.136
cious+0.133
Neg logit contributions
mate-0.102
 them-0.102
 wreck-0.088
 polar-0.088
 tow-0.086
Token higher
Token ID2440
Feature activation-2.06e+00

Pos logit contributions
ages+0.080
+0.078
cious+0.076
aul+0.075
 Michelle+0.073
Neg logit contributions
 them-0.053
 puck-0.046
 hon-0.046
mate-0.046
 wreck-0.045
Token.
Token ID13
Feature activation-7.28e-01

Pos logit contributions
+0.170
's+0.151
ages+0.148
aul+0.142
cious+0.138
Neg logit contributions
mate-0.102
 them-0.101
 wreck-0.087
 polar-0.087
 tow-0.086
Token,
Token ID11
Feature activation-8.18e-01

Pos logit contributions
+0.056
ages+0.054
 List+0.051
 decisions+0.051
aul+0.051
Neg logit contributions
 them-0.033
mate-0.031
 polar-0.029
 wreck-0.029
 tow-0.028
Token look
Token ID804
Feature activation-3.08e-01

Pos logit contributions
ages+0.057
+0.057
aul+0.052
aut+0.052
's+0.052
Neg logit contributions
 them-0.047
mate-0.043
 polar-0.042
 wreck-0.040
 tow-0.040
Token
Token ID6184
Feature activation-4.01e-01

Pos logit contributions
+0.022
ages+0.019
's+0.019
aul+0.018
cious+0.018
Neg logit contributions
 them-0.019
mate-0.018
 polar-0.016
 wreck-0.016
 tow-0.016
Token
Token ID95
Feature activation-1.56e-01

Pos logit contributions
ages+0.030
+0.029
's+0.028
ups+0.027
 decisions+0.027
Neg logit contributions
mate-0.020
 them-0.018
inn-0.018
 wreck-0.017
 splash-0.017
Token
Token ID26391
Feature activation-3.11e+00

Pos logit contributions
ages+0.009
+0.009
 decisions+0.008
's+0.008
bey+0.008
Neg logit contributions
mate-0.010
inn-0.009
 ramp-0.009
 them-0.009
 tow-0.009
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
 decisions+0.205
 persever+0.192
 mindful+0.189
 List+0.188
+0.187
Neg logit contributions
 them-0.158
room-0.151
 ramp-0.149
mate-0.147
 tow-0.142
Token
Token ID250
Feature activation+2.21e-01

Pos logit contributions
+0.931
ages+0.908
 decisions+0.859
's+0.846
cious+0.817
Neg logit contributions
 them-0.725
mate-0.694
 wreck-0.685
 ramp-0.670
 snowball-0.658
Token it
Token ID340
Feature activation+1.06e+00

Pos logit contributions
mate+0.014
 them+0.014
 wreck+0.013
 polar+0.013
 ramp+0.013
Neg logit contributions
-0.015
's-0.013
ages-0.012
aul-0.012
cious-0.011
Tokenâ
Token ID22940
Feature activation-2.08e+00

Pos logit contributions
 them+0.086
 match+0.081
mate+0.079
 wreck+0.077
 splash+0.076
Neg logit contributions
ages-0.041
aul-0.040
 List-0.038
cious-0.037
assy-0.036
Token
Token ID26391
Feature activation-3.10e+00

Pos logit contributions
ages+0.115
+0.115
cious+0.107
 decisions+0.107
ups+0.106
Neg logit contributions
mate-0.139
inn-0.126
 them-0.125
 tow-0.118
 match-0.115
Token
Token ID8151
Feature activation-5.32e+00

Pos logit contributions
 decisions+0.180
aul+0.173
+0.172
 List+0.171
 mindful+0.169
Neg logit contributions
mate-0.172
 them-0.169
 tow-0.165
room-0.159
 ramp-0.158
Token it
Token ID340
Feature activation+1.96e+00

Pos logit contributions
 them+0.113
mate+0.099
 wreck+0.089
 polar+0.088
 snowball+0.084
Neg logit contributions
-0.156
ages-0.138
's-0.135
aul-0.133
cious-0.132
Token forever
Token ID8097
Feature activation+4.85e+00

Pos logit contributions
 them+0.107
mate+0.101
 wreck+0.090
 captain+0.087
 polar+0.086
Neg logit contributions
-0.151
ages-0.133
cious-0.130
aul-0.130
's-0.130
Token
Token ID6184
Feature activation+4.66e-01

Pos logit contributions
 them+0.209
mate+0.175
 wreck+0.167
 control+0.148
 rock+0.146
Neg logit contributions
-0.421
ages-0.390
cious-0.377
aul-0.374
 List-0.373
Token
Token ID95
Feature activation+6.61e-01

Pos logit contributions
mate+0.029
 them+0.028
 tow+0.025
 wreck+0.025
inn+0.025
Neg logit contributions
-0.033
's-0.030
ages-0.030
aul-0.027
cious-0.027
Token
Token ID26391
Feature activation-2.53e+00

Pos logit contributions
mate+0.048
 them+0.046
 tow+0.043
 ramp+0.042
inn+0.042
Neg logit contributions
-0.038
ages-0.034
's-0.033
aul-0.032
bey-0.030
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.180
 decisions+0.172
aul+0.170
ience+0.164
 persever+0.163
Neg logit contributions
 them-0.123
mate-0.120
 ramp-0.108
 racer-0.107
 tow-0.104
Token
Token ID250
Feature activation+3.33e-01

Pos logit contributions
+0.858
's+0.754
ages+0.746
cious+0.686
aul+0.680
Neg logit contributions
mate-0.884
 them-0.857
 wreck-0.791
 tow-0.782
 ramp-0.782
Token things
Token ID1243
Feature activation-3.56e+00

Pos logit contributions
mate+0.020
 them+0.020
 tow+0.018
inn+0.017
 wreck+0.017
Neg logit contributions
-0.023
's-0.021
ages-0.021
aul-0.019
cious-0.019
Token are
Token ID389
Feature activation-1.67e-01

Pos logit contributions
+0.277
ages+0.252
's+0.246
aul+0.239
cious+0.238
Neg logit contributions
 them-0.190
mate-0.184
 wreck-0.162
 tow-0.155
 ramp-0.151
Token only
Token ID691
Feature activation+2.17e+00

Pos logit contributions
+0.012
ages+0.010
's+0.010
aul+0.010
cious+0.010
Neg logit contributions
 them-0.010
mate-0.010
 wreck-0.009
 tow-0.009
 polar-0.008
Token available
Token ID1695
Feature activation+3.43e+00

Pos logit contributions
 them+0.117
mate+0.105
 wreck+0.094
 polar+0.091
 match+0.091
Neg logit contributions
-0.166
ages-0.148
aul-0.144
's-0.144
cious-0.141
Token special
Token ID2041
Feature activation-2.67e+00

Pos logit contributions
mate+0.170
 them+0.163
 polar+0.145
 ramp+0.145
 wreck+0.144
Neg logit contributions
-0.166
's-0.141
ages-0.135
cious-0.125
aul-0.125
Token taxi
Token ID17536
Feature activation+3.70e+00

Pos logit contributions
+0.214
's+0.190
ages+0.176
 decisions+0.169
aul+0.164
Neg logit contributions
mate-0.141
 them-0.138
inn-0.123
 puck-0.114
 polar-0.113
Token
Token ID6184
Feature activation-4.67e-01

Pos logit contributions
mate+0.185
 them+0.179
 wreck+0.160
 tow+0.159
 polar+0.156
Neg logit contributions
-0.296
ages-0.262
aul-0.259
's-0.256
 List-0.247
Token
Token ID95
Feature activation-2.56e-01

Pos logit contributions
+0.032
's+0.028
ages+0.027
aul+0.026
cious+0.025
Neg logit contributions
mate-0.030
 them-0.029
 wreck-0.026
 tow-0.026
 polar-0.026
Token
Token ID26391
Feature activation-3.22e+00

Pos logit contributions
+0.015
's+0.013
ages+0.013
aul+0.012
cious+0.011
Neg logit contributions
mate-0.018
 them-0.018
 tow-0.017
 wreck-0.017
 ramp-0.016
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.208
 decisions+0.190
aul+0.186
ience+0.178
 persever+0.178
Neg logit contributions
 them-0.192
mate-0.182
 tow-0.179
 ramp-0.175
 wreck-0.168
Token
Token ID250
Feature activation+8.30e-02

Pos logit contributions
+0.997
's+0.881
ages+0.875
aul+0.815
 decisions+0.814
Neg logit contributions
mate-0.743
 them-0.738
 wreck-0.664
 tow-0.655
 ramp-0.651
Token it
Token ID340
Feature activation+9.49e-01

Pos logit contributions
mate+0.005
 them+0.005
 wreck+0.005
 polar+0.005
 tow+0.005
Neg logit contributions
-0.006
's-0.005
ages-0.005
aul-0.004
cious-0.004
Token fit
Token ID4197
Feature activation+2.84e+00

Pos logit contributions
 them+0.083
mate+0.080
 wreck+0.077
 match+0.077
 tow+0.076
Neg logit contributions
aul-0.030
ages-0.030
cious-0.028
 List-0.025
 decisions-0.025
Token three
Token ID1115
Feature activation+2.95e+00

Pos logit contributions
 them+0.157
mate+0.156
 wreck+0.133
 polar+0.132
 tow+0.130
Neg logit contributions
-0.217
's-0.191
ages-0.190
aul-0.182
cious-0.176
Token people
Token ID661
Feature activation-4.18e+00

Pos logit contributions
mate+0.165
 them+0.156
 wreck+0.143
 polar+0.142
 ramp+0.141
Neg logit contributions
-0.232
's-0.204
ages-0.198
aul-0.184
cious-0.182
Token my
Token ID616
Feature activation+2.06e+00

Pos logit contributions
+0.055
's+0.048
ages+0.045
aul+0.043
cious+0.042
Neg logit contributions
mate-0.040
 them-0.038
 wreck-0.035
 ramp-0.035
 polar-0.034
Token planet
Token ID5440
Feature activation-6.44e-01

Pos logit contributions
mate+0.120
 them+0.119
 wreck+0.106
 polar+0.105
 tow+0.105
Neg logit contributions
-0.154
's-0.134
ages-0.130
aul-0.124
cious-0.121
Token
Token ID6184
Feature activation-4.17e-01

Pos logit contributions
+0.050
's+0.043
ages+0.042
aul+0.040
cious+0.039
Neg logit contributions
mate-0.036
 them-0.035
 wreck-0.031
 polar-0.031
 tow-0.031
Token
Token ID95
Feature activation-2.17e-01

Pos logit contributions
+0.026
ages+0.024
's+0.023
aul+0.021
 decisions+0.021
Neg logit contributions
mate-0.028
 them-0.027
 wreck-0.025
 tow-0.025
 polar-0.025
Token
Token ID26391
Feature activation-3.14e+00

Pos logit contributions
+0.012
ages+0.011
's+0.011
 decisions+0.011
bey+0.010
Neg logit contributions
mate-0.015
 them-0.014
 tow-0.014
 wreck-0.014
 ramp-0.013
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
 decisions+0.218
+0.218
aul+0.210
 persever+0.208
ience+0.206
Neg logit contributions
 them-0.149
mate-0.147
 ramp-0.139
 tow-0.137
 racer-0.133
Token
Token ID250
Feature activation+2.14e-01

Pos logit contributions
+0.830
ages+0.766
's+0.743
 decisions+0.709
cious+0.692
Neg logit contributions
mate-0.858
 them-0.851
 wreck-0.789
 ramp-0.784
 tow-0.779
Token let
Token ID1309
Feature activation-1.64e+00

Pos logit contributions
mate+0.014
 them+0.013
 wreck+0.012
 polar+0.012
 tow+0.012
Neg logit contributions
-0.015
's-0.013
ages-0.012
aul-0.012
cious-0.011
Tokenâ
Token ID22940
Feature activation-2.10e+00

Pos logit contributions
ages+0.030
aul+0.026
 List+0.022
cious+0.021
+0.021
Neg logit contributions
 them-0.185
mate-0.175
 polar-0.159
 tow-0.159
 his-0.158
Token
Token ID26391
Feature activation-3.15e+00

Pos logit contributions
+0.113
ages+0.109
's+0.104
aul+0.102
cious+0.100
Neg logit contributions
mate-0.151
 them-0.137
inn-0.134
 tow-0.131
 wreck-0.131
Token
Token ID8151
Feature activation-5.29e+00

Pos logit contributions
aul+0.196
 decisions+0.187
 mindful+0.185
+0.184
ience+0.183
Neg logit contributions
 them-0.173
mate-0.172
 tow-0.166
 racer-0.161
 ramp-0.156
Token lovely
Token ID14081
Feature activation-8.12e-02

Pos logit contributions
mate+0.166
 them+0.153
inn+0.144
 ramp+0.141
 tow+0.141
Neg logit contributions
-0.185
's-0.160
ages-0.149
aul-0.143
 decisions-0.142
Token things
Token ID1243
Feature activation-3.69e+00

Pos logit contributions
+0.006
's+0.005
ages+0.005
aul+0.005
cious+0.005
Neg logit contributions
 them-0.005
mate-0.005
 polar-0.004
 wreck-0.004
 tow-0.004
Token
Token ID6184
Feature activation-2.53e-01

Pos logit contributions
+0.287
ages+0.260
's+0.252
aul+0.249
cious+0.239
Neg logit contributions
 them-0.203
mate-0.185
 wreck-0.165
 tow-0.161
 polar-0.160
Token
Token ID95
Feature activation-8.00e-02

Pos logit contributions
+0.018
ages+0.017
's+0.017
 decisions+0.016
aul+0.015
Neg logit contributions
mate-0.014
 them-0.014
 ramp-0.013
 tow-0.013
inn-0.012
Token
Token ID26391
Feature activation-3.04e+00

Pos logit contributions
+0.005
ages+0.005
 decisions+0.004
bey+0.004
aul+0.004
Neg logit contributions
mate-0.005
 them-0.005
 tow-0.005
 ramp-0.005
room-0.005
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
 decisions+0.178
+0.174
 persever+0.170
aul+0.167
 dedication+0.162
Neg logit contributions
 them-0.187
mate-0.171
room-0.163
 ramp-0.161
 tow-0.157
Token
Token ID251
Feature activation-4.60e-01

Pos logit contributions
+1.144
ages+1.048
's+1.036
 decisions+1.015
 pays+0.967
Neg logit contributions
 them-0.565
mate-0.553
 wreck-0.489
 ramp-0.482
 tow-0.473
Token a
Token ID257
Feature activation-1.52e+00

Pos logit contributions
+0.033
ages+0.033
ience+0.031
aul+0.031
 decisions+0.030
Neg logit contributions
 them-0.026
mate-0.021
 his-0.020
 polar-0.019
 tow-0.019
Token big
Token ID1263
Feature activation+9.05e-01

Pos logit contributions
+0.110
's+0.094
ages+0.090
aul+0.086
cious+0.085
Neg logit contributions
 them-0.094
mate-0.093
 wreck-0.081
inn-0.081
 ramp-0.079
Token slide
Token ID10649
Feature activation+1.22e-01

Pos logit contributions
mate+0.054
 them+0.052
inn+0.046
 wreck+0.045
 ramp+0.045
Neg logit contributions
-0.068
's-0.059
ages-0.052
aul-0.052
ience-0.052
Token,
Token ID11
Feature activation-6.58e-01

Pos logit contributions
mate+0.007
 them+0.007
 polar+0.006
 wreck+0.006
 tow+0.006
Neg logit contributions
-0.009
's-0.008
ages-0.008
aul-0.007
cious-0.007
Token They
Token ID1119
Feature activation-8.40e-02

Pos logit contributions
+0.040
's+0.035
ages+0.035
aul+0.033
cious+0.032
Neg logit contributions
mate-0.030
 them-0.030
 wreck-0.027
 polar-0.027
 tow-0.026
Token forgot
Token ID16453
Feature activation-3.25e+00

Pos logit contributions
+0.006
's+0.005
ages+0.005
aul+0.005
cious+0.005
Neg logit contributions
mate-0.005
 them-0.005
 ramp-0.005
 snowball-0.005
 polar-0.005
Token
Token ID6184
Feature activation-3.74e-01

Pos logit contributions
+0.273
ages+0.246
's+0.239
aul+0.236
cious+0.231
Neg logit contributions
 them-0.163
mate-0.150
 wreck-0.134
 polar-0.130
 tow-0.129
Token
Token ID95
Feature activation-1.30e-01

Pos logit contributions
+0.025
's+0.022
ages+0.022
aul+0.020
 decisions+0.019
Neg logit contributions
mate-0.024
 them-0.024
 wreck-0.022
 tow-0.021
 ramp-0.021
Token
Token ID26391
Feature activation-3.07e+00

Pos logit contributions
+0.008
ages+0.007
bey+0.007
aul+0.007
 decisions+0.007
Neg logit contributions
mate-0.008
 them-0.008
 wreck-0.007
 tow-0.007
 ramp-0.007
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.167
 decisions+0.162
aul+0.159
 persever+0.158
 List+0.153
Neg logit contributions
 them-0.194
 ramp-0.177
mate-0.175
 wreck-0.174
room-0.173
Token
Token ID250
Feature activation+2.04e-01

Pos logit contributions
+1.049
ages+0.959
's+0.945
 decisions+0.927
cious+0.891
Neg logit contributions
mate-0.650
 them-0.647
 wreck-0.592
 ramp-0.576
 tow-0.563
Token they
Token ID484
Feature activation-2.26e+00

Pos logit contributions
mate+0.014
 them+0.014
 polar+0.012
 wreck+0.012
 tow+0.012
Neg logit contributions
-0.014
's-0.011
ages-0.011
aul-0.010
cious-0.010
Token were
Token ID547
Feature activation+2.45e+00

Pos logit contributions
+0.159
ages+0.154
aul+0.150
cious+0.146
 List+0.143
Neg logit contributions
 them-0.123
mate-0.119
 wreck-0.110
 match-0.103
 tow-0.100
Token supposed
Token ID4385
Feature activation-2.35e+00

Pos logit contributions
 them+0.141
mate+0.128
 wreck+0.122
 polar+0.117
 tow+0.115
Neg logit contributions
-0.181
ages-0.167
aul-0.161
's-0.158
bey-0.155
Token to
Token ID284
Feature activation-6.09e-01

Pos logit contributions
+0.188
ages+0.169
aul+0.165
's+0.164
cious+0.159
Neg logit contributions
 them-0.124
mate-0.116
 wreck-0.106
 tow-0.099
 polar-0.098
Token was
Token ID373
Feature activation+5.28e-01

Pos logit contributions
 them+0.059
mate+0.057
 wreck+0.053
 polar+0.051
 snowball+0.051
Neg logit contributions
-0.088
aul-0.086
ages-0.085
cious-0.082
 decisions-0.080
Token too
Token ID1165
Feature activation+3.63e+00

Pos logit contributions
mate+0.030
 them+0.028
 ramp+0.026
 wreck+0.026
 polar+0.026
Neg logit contributions
-0.042
's-0.036
ages-0.034
aul-0.032
 pays-0.032
Token late
Token ID2739
Feature activation-4.87e+00

Pos logit contributions
 them+0.240
 snowball+0.231
 wreck+0.228
 polar+0.224
 tow+0.216
Neg logit contributions
-0.220
's-0.201
ages-0.200
cious-0.194
aul-0.188
Tokenâ
Token ID22940
Feature activation-1.94e+00

Pos logit contributions
+0.418
ages+0.381
's+0.371
aul+0.369
cious+0.358
Neg logit contributions
 them-0.232
mate-0.210
 wreck-0.173
 polar-0.167
 tow-0.165
Token
Token ID26391
Feature activation-2.94e+00

Pos logit contributions
+0.110
ages+0.102
's+0.101
ups+0.099
 decisions+0.098
Neg logit contributions
mate-0.134
inn-0.127
 them-0.120
 wreck-0.118
 ramp-0.118
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.171
 decisions+0.159
aul+0.156
ience+0.155
 persever+0.155
Neg logit contributions
 them-0.180
mate-0.173
 ramp-0.169
 puck-0.163
 tow-0.162
Token
Token ID251
Feature activation-3.71e-01

Pos logit contributions
+1.177
's+1.078
ages+1.071
 decisions+1.030
cious+1.028
Neg logit contributions
mate-0.531
 them-0.526
 wreck-0.472
 ramp-0.463
 tow-0.444
Token the
Token ID262
Feature activation-7.99e-01

Pos logit contributions
+0.027
ages+0.025
's+0.024
aul+0.024
cious+0.023
Neg logit contributions
 them-0.021
mate-0.020
 polar-0.017
 tow-0.017
 wreck-0.017
Token ice
Token ID4771
Feature activation+9.41e-01

Pos logit contributions
+0.064
's+0.057
ages+0.057
aul+0.054
cious+0.052
Neg logit contributions
mate-0.041
 them-0.040
 polar-0.037
 wreck-0.037
 tow-0.036
Token melted
Token ID24178
Feature activation-1.26e-01

Pos logit contributions
mate+0.050
 them+0.050
 wreck+0.045
 polar+0.044
 tow+0.043
Neg logit contributions
-0.075
's-0.065
ages-0.063
aul-0.061
cious-0.060
Token and
Token ID290
Feature activation-9.12e-01

Pos logit contributions
+0.010
's+0.009
ages+0.008
aul+0.008
 decisions+0.008
Neg logit contributions
mate-0.007
 them-0.006
 tow-0.006
 wreck-0.006
 polar-0.006
Token something
Token ID1223
Feature activation-4.14e+00

Pos logit contributions
mate+0.234
 them+0.233
 wreck+0.208
 polar+0.208
 tow+0.207
Neg logit contributions
-0.263
's-0.227
ages-0.222
aul-0.210
cious-0.204
Token incredible
Token ID8082
Feature activation-1.19e-02

Pos logit contributions
+0.302
's+0.261
ages+0.242
aul+0.230
cious+0.226
Neg logit contributions
mate-0.256
 them-0.246
 polar-0.227
 wreck-0.224
 tow-0.224
Token
Token ID6184
Feature activation-4.74e-01

Pos logit contributions
+0.001
ages+0.001
's+0.001
aul+0.001
cious+0.001
Neg logit contributions
 them-0.001
mate-0.001
 wreck-0.001
 polar-0.001
 tow-0.001
Token
Token ID95
Feature activation-2.34e-01

Pos logit contributions
+0.034
ages+0.033
's+0.031
 decisions+0.030
bey+0.029
Neg logit contributions
mate-0.027
 them-0.025
 ramp-0.024
 wreck-0.024
 tow-0.024
Token
Token ID26391
Feature activation-3.06e+00

Pos logit contributions
+0.013
ages+0.013
bey+0.012
 decisions+0.012
aul+0.012
Neg logit contributions
mate-0.016
 them-0.014
 ramp-0.014
 tow-0.014
inn-0.013
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
 decisions+0.196
 persever+0.184
aul+0.184
+0.183
ience+0.180
Neg logit contributions
 them-0.169
mate-0.152
 ramp-0.148
room-0.148
 tow-0.142
Token
Token ID250
Feature activation+2.52e-01

Pos logit contributions
ages+1.109
 decisions+1.104
+1.094
's+1.029
 mindful+1.018
Neg logit contributions
 them-0.513
mate-0.496
 ramp-0.451
 tow-0.430
 snowball-0.426
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
mate+0.016
 them+0.016
 tow+0.014
 polar+0.014
 wreck+0.014
Neg logit contributions
-0.017
's-0.015
ages-0.015
aul-0.014
 decisions-0.013
Token magical
Token ID10883
Feature activation-2.71e+00

Pos logit contributions
+0.111
's+0.095
ages+0.090
cious+0.087
aul+0.087
Neg logit contributions
 them-0.079
mate-0.078
inn-0.067
 tow-0.067
 wreck-0.066
Token plant
Token ID4618
Feature activation-5.08e+00

Pos logit contributions
+0.214
's+0.188
ages+0.179
aul+0.172
cious+0.168
Neg logit contributions
 them-0.145
mate-0.144
 wreck-0.125
 polar-0.124
 tow-0.124
Token!
Token ID0
Feature activation+8.29e-01

Pos logit contributions
+0.370
ages+0.357
 List+0.336
aul+0.332
's+0.328
Neg logit contributions
mate-0.269
 them-0.269
 wreck-0.226
 tow-0.221
 polar-0.219
Token her
Token ID607
Feature activation+1.61e+00

Pos logit contributions
 them+0.019
mate+0.018
 wreck+0.016
 tow+0.016
 polar+0.016
Neg logit contributions
-0.018
aul-0.016
ages-0.016
's-0.015
cious-0.015
Token peace
Token ID4167
Feature activation-4.53e+00

Pos logit contributions
mate+0.078
 them+0.077
 wreck+0.067
 polar+0.067
 tow+0.066
Neg logit contributions
-0.135
's-0.120
ages-0.117
aul-0.112
cious-0.109
Token
Token ID6184
Feature activation-1.69e-01

Pos logit contributions
+0.349
's+0.305
ages+0.299
aul+0.286
cious+0.278
Neg logit contributions
mate-0.250
 them-0.248
 wreck-0.218
 polar-0.217
 tow-0.215
Token
Token ID95
Feature activation+5.43e-02

Pos logit contributions
+0.011
ages+0.010
's+0.010
 decisions+0.009
aul+0.009
Neg logit contributions
mate-0.012
 them-0.011
inn-0.010
 tow-0.010
 wreck-0.010
Token
Token ID26391
Feature activation-2.81e+00

Pos logit contributions
mate+0.004
 them+0.004
 tow+0.003
inn+0.003
 ramp+0.003
Neg logit contributions
-0.003
ages-0.003
's-0.003
aul-0.003
 decisions-0.003
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.200
 decisions+0.190
aul+0.184
ages+0.180
 pays+0.177
Neg logit contributions
 them-0.146
mate-0.141
 tow-0.126
 ramp-0.124
 racer-0.120
Token
Token ID250
Feature activation+2.91e-01

Pos logit contributions
+0.819
's+0.718
ages+0.714
 decisions+0.652
cious+0.649
Neg logit contributions
mate-0.910
 them-0.891
 wreck-0.817
 tow-0.811
 ramp-0.811
Token she
Token ID673
Feature activation-3.81e+00

Pos logit contributions
mate+0.019
 them+0.019
 tow+0.017
inn+0.016
 wreck+0.016
Neg logit contributions
-0.019
's-0.017
ages-0.017
aul-0.016
cious-0.015
Token just
Token ID655
Feature activation+6.42e-01

Pos logit contributions
aul+0.230
+0.226
ages+0.223
cious+0.222
 Michelle+0.217
Neg logit contributions
 them-0.223
mate-0.219
 wreck-0.199
 match-0.195
 tow-0.192
Token needs
Token ID2476
Feature activation-3.23e+00

Pos logit contributions
 them+0.034
mate+0.032
 wreck+0.030
 polar+0.028
 tow+0.028
Neg logit contributions
-0.047
ages-0.045
aul-0.044
cious-0.043
's-0.042
Token to
Token ID284
Feature activation-5.72e-01

Pos logit contributions
+0.239
's+0.208
ages+0.202
aul+0.192
cious+0.187
Neg logit contributions
mate-0.189
 them-0.186
 wreck-0.167
 polar-0.167
 tow-0.165
Token a
Token ID257
Feature activation-1.39e+00

Pos logit contributions
 them+0.040
mate+0.037
 wreck+0.034
 polar+0.033
 tow+0.032
Neg logit contributions
-0.060
ages-0.054
's-0.053
cious-0.051
aul-0.050
Token normal
Token ID3487
Feature activation+1.66e+00

Pos logit contributions
+0.091
's+0.079
aul+0.066
cious+0.065
ages+0.062
Neg logit contributions
 them-0.096
mate-0.092
inn-0.088
room-0.085
 ramp-0.083
Token penny
Token ID26369
Feature activation-3.70e-01

Pos logit contributions
mate+0.103
 them+0.103
 polar+0.091
 tow+0.090
 ramp+0.090
Neg logit contributions
-0.118
's-0.103
ages-0.096
aul-0.093
 decisions-0.090
Tokenâ
Token ID22940
Feature activation-1.99e+00

Pos logit contributions
+0.031
ages+0.027
aul+0.026
's+0.026
 List+0.026
Neg logit contributions
mate-0.018
 them-0.018
 wreck-0.016
 polar-0.015
 ramp-0.015
Token
Token ID26391
Feature activation-3.06e+00

Pos logit contributions
+0.117
ages+0.109
ience+0.105
 decisions+0.104
ups+0.102
Neg logit contributions
mate-0.134
inn-0.126
 them-0.119
room-0.115
 match-0.115
Token
Token ID447
Feature activation-1.33e+01

Pos logit contributions
+0.176
 decisions+0.149
 List+0.143
 mindful+0.141
ience+0.141
Neg logit contributions
 them-0.211
mate-0.211
 tow-0.196
 ramp-0.191
 wreck-0.190
Token
Token ID251
Feature activation-4.37e-01

Pos logit contributions
+1.140
's+1.010
ages+0.999
 decisions+0.952
cious+0.938
Neg logit contributions
mate-0.607
 them-0.601
 wreck-0.527
 ramp-0.517
 tow-0.509
Tokenit
Token ID270
Feature activation-9.31e-01

Pos logit contributions
+0.035
ages+0.031
's+0.030
aul+0.029
 pays+0.029
Neg logit contributions
 them-0.023
mate-0.021
 polar-0.019
 tow-0.019
 wreck-0.019
Token was
Token ID373
Feature activation+2.92e-01

Pos logit contributions
+0.066
's+0.056
ages+0.055
aul+0.053
cious+0.051
Neg logit contributions
mate-0.057
 them-0.057
 wreck-0.051
 polar-0.051
 tow-0.050
Token special
Token ID2041
Feature activation-2.50e+00

Pos logit contributions
mate+0.020
 them+0.019
 wreck+0.017
 ramp+0.017
 tow+0.017
Neg logit contributions
-0.020
's-0.017
ages-0.016
aul-0.015
cious-0.015
Token.
Token ID13
Feature activation-5.96e-01

Pos logit contributions
+0.186
's+0.161
ages+0.158
aul+0.150
cious+0.146
Neg logit contributions
mate-0.147
 them-0.146
 wreck-0.130
 polar-0.130
 tow-0.128
Token set
Token ID900
Feature activation+2.48e+00

Pos logit contributions
+0.041
's+0.036
ages+0.035
aul+0.033
cious+0.032
Neg logit contributions
mate-0.033
 them-0.032
 wreck-0.030
 polar-0.029
 snowball-0.029
Token with
Token ID351
Feature activation-1.15e+00

Pos logit contributions
mate+0.140
 them+0.138
 wreck+0.123
 polar+0.123
 tow+0.121
Neg logit contributions
-0.189
's-0.165
ages-0.161
aul-0.153
cious-0.149
Token colorful
Token ID20239
Feature activation+1.53e+00

Pos logit contributions
+0.091
's+0.080
ages+0.075
aul+0.071
 decisions+0.070
Neg logit contributions
mate-0.065
 ramp-0.057
 wreck-0.056
 polar-0.055
 them-0.055
Token patterns
Token ID7572
Feature activation-5.48e-01

Pos logit contributions
mate+0.095
 them+0.094
 wreck+0.084
 polar+0.084
 tow+0.083
Neg logit contributions
-0.107
's-0.093
ages-0.090
aul-0.086
cious-0.083
Token on
Token ID319
Feature activation+8.09e-01

Pos logit contributions
+0.040
's+0.035
ages+0.033
aul+0.031
cious+0.031
Neg logit contributions
mate-0.033
 them-0.031
 polar-0.030
 wreck-0.030
 tow-0.029
Token them
Token ID606
Feature activation+6.84e+00

Pos logit contributions
mate+0.049
 polar+0.048
 wreck+0.045
 ramp+0.044
 snowball+0.043
Neg logit contributions
-0.060
's-0.052
aul-0.043
 Michelle-0.043
 pays-0.041
Token.
Token ID13
Feature activation-4.35e-01

Pos logit contributions
 them+0.339
mate+0.321
 wreck+0.268
 tow+0.265
 ramp+0.256
Neg logit contributions
-0.561
ages-0.496
's-0.486
aul-0.486
 List-0.475
Token
Token ID220
Feature activation-1.11e+00

Pos logit contributions
+0.030
ages+0.027
's+0.025
aul+0.025
ience+0.024
Neg logit contributions
 them-0.028
mate-0.025
 tow-0.024
inn-0.023
 polar-0.023
Token
Token ID198
Feature activation-5.30e-01

Pos logit contributions
+0.083
's+0.072
ages+0.072
ience+0.069
aul+0.069
Neg logit contributions
 them-0.065
mate-0.061
 tow-0.054
inn-0.053
 ramp-0.052
Token
Token ID198
Feature activation-5.37e-01

Pos logit contributions
+0.034
's+0.029
ages+0.025
aul+0.025
 List+0.024
Neg logit contributions
mate-0.039
 wreck-0.036
 polar-0.036
 them-0.036
 ramp-0.034
TokenAt
Token ID2953
Feature activation+5.62e-01

Pos logit contributions
+0.037
's+0.031
ages+0.031
aul+0.029
cious+0.028
Neg logit contributions
mate-0.035
 them-0.034
 wreck-0.031
 polar-0.031
 tow-0.031
Token Jake
Token ID14757
Feature activation+8.17e-01

Pos logit contributions
mate+0.177
 them+0.176
 polar+0.157
 wreck+0.156
 tow+0.156
Neg logit contributions
-0.201
's-0.174
ages-0.171
aul-0.161
cious-0.157
Token said
Token ID531
Feature activation-8.38e-02

Pos logit contributions
 them+0.049
mate+0.047
inn+0.042
 wreck+0.041
 polar+0.040
Neg logit contributions
-0.055
ages-0.050
 decisions-0.048
aul-0.047
cious-0.046
Token,
Token ID11
Feature activation-5.61e-01

Pos logit contributions
+0.007
's+0.006
ages+0.006
aul+0.005
 decisions+0.005
Neg logit contributions
mate-0.005
 them-0.004
 tow-0.004
 polar-0.004
 wreck-0.004
Token "
Token ID366
Feature activation+1.64e+00

Pos logit contributions
+0.045
's+0.040
ages+0.039
aul+0.038
cious+0.037
Neg logit contributions
 them-0.029
mate-0.029
 polar-0.025
 wreck-0.025
 tow-0.024
TokenYes
Token ID5297
Feature activation+2.19e+00

Pos logit contributions
mate+0.097
 them+0.097
 wreck+0.092
 polar+0.091
 ramp+0.088
Neg logit contributions
-0.125
's-0.103
ages-0.100
aul-0.095
cious-0.094
Token please
Token ID3387
Feature activation+6.62e+00

Pos logit contributions
 wreck+0.128
mate+0.128
 polar+0.125
 them+0.122
 ramp+0.120
Neg logit contributions
-0.165
's-0.142
ages-0.119
ience-0.118
aul-0.118
Token!
Token ID0
Feature activation+1.07e+00

Pos logit contributions
mate+0.318
 them+0.313
 wreck+0.268
 polar+0.267
 tow+0.266
Neg logit contributions
-0.559
's-0.495
ages-0.485
aul-0.466
cious-0.456
Token But
Token ID887
Feature activation-7.21e-01

Pos logit contributions
mate+0.077
 them+0.075
 tow+0.070
 polar+0.068
 ramp+0.067
Neg logit contributions
-0.059
ages-0.053
's-0.053
aul-0.051
cious-0.049
Token I
Token ID314
Feature activation-2.92e+00

Pos logit contributions
+0.056
ages+0.051
's+0.049
aul+0.047
cious+0.047
Neg logit contributions
 them-0.039
mate-0.039
 wreck-0.034
 polar-0.033
 tow-0.033
Token'd
Token ID1549
Feature activation+2.75e+00

Pos logit contributions
+0.209
ages+0.184
's+0.183
aul+0.175
cious+0.172
Neg logit contributions
 them-0.169
mate-0.168
 wreck-0.151
 polar-0.148
 tow-0.148
Token like
Token ID588
Feature activation+7.68e-01

Pos logit contributions
mate+0.149
 them+0.143
 polar+0.129
 tow+0.128
 wreck+0.128
Neg logit contributions
-0.220
's-0.194
ages-0.185
aul-0.176
cious-0.172
Token play
Token ID711
Feature activation+3.20e+00

Pos logit contributions
+0.034
's+0.030
ages+0.028
aul+0.027
cious+0.027
Neg logit contributions
mate-0.016
 them-0.015
inn-0.013
 polar-0.013
 wreck-0.013
Token with
Token ID351
Feature activation-1.02e+00

Pos logit contributions
 tow+0.230
 polar+0.226
 spoiler+0.212
 wreck+0.210
mate+0.207
Neg logit contributions
's-0.194
-0.177
ages-0.141
aut-0.132
aul-0.131
Token toy
Token ID13373
Feature activation+3.17e+00

Pos logit contributions
+0.086
's+0.081
ages+0.075
aul+0.073
cious+0.070
Neg logit contributions
mate-0.051
 them-0.041
inn-0.041
 tow-0.040
 ramp-0.039
Token soldiers
Token ID5795
Feature activation+2.79e+00

Pos logit contributions
mate+0.143
 tow+0.137
inn+0.132
 polar+0.127
 them+0.121
Neg logit contributions
-0.264
's-0.264
ages-0.235
aul-0.221
ups-0.217
Token and
Token ID290
Feature activation-4.04e-01

Pos logit contributions
mate+0.176
 them+0.166
 polar+0.165
 tow+0.162
 wreck+0.161
Neg logit contributions
-0.193
's-0.177
ages-0.159
aul-0.147
cious-0.142
Token pretend
Token ID16614
Feature activation+5.91e+00

Pos logit contributions
+0.035
's+0.032
ages+0.029
 pays+0.028
cious+0.027
Neg logit contributions
mate-0.020
inn-0.018
 them-0.017
 polar-0.016
 snowball-0.016
Token they
Token ID484
Feature activation-1.49e+00

Pos logit contributions
mate+0.404
 them+0.380
 polar+0.362
inn+0.360
 tow+0.359
Neg logit contributions
-0.384
's-0.338
ages-0.319
aul-0.291
cious-0.285
Token were
Token ID547
Feature activation+3.09e+00

Pos logit contributions
+0.104
's+0.096
ages+0.080
 pays+0.077
cious+0.074
Neg logit contributions
mate-0.098
inn-0.090
 snowball-0.089
 them-0.087
 ramp-0.086
Token in
Token ID287
Feature activation-3.51e-01

Pos logit contributions
mate+0.147
 them+0.132
inn+0.129
 ramp+0.124
 tow+0.123
Neg logit contributions
-0.260
's-0.242
ages-0.227
aul-0.209
cious-0.208
Token a
Token ID257
Feature activation-1.05e+00

Pos logit contributions
+0.022
's+0.019
 decisions+0.015
 List+0.015
 pays+0.015
Neg logit contributions
mate-0.026
inn-0.024
 polar-0.022
 wreck-0.022
 ramp-0.022
Token war
Token ID1175
Feature activation-2.09e+00

Pos logit contributions
+0.080
's+0.078
cious+0.056
ience+0.056
ages+0.053
Neg logit contributions
mate-0.062
icle-0.061
inn-0.060
 them-0.058
uit-0.054
Token and
Token ID290
Feature activation-5.10e-02

Pos logit contributions
 them+0.088
mate+0.085
 wreck+0.074
 tow+0.072
 polar+0.072
Neg logit contributions
-0.130
ages-0.113
's-0.113
aul-0.109
cious-0.106
Token pe
Token ID613
Feature activation-4.97e-02

Pos logit contributions
+0.004
aul+0.003
's+0.003
ages+0.003
 decisions+0.003
Neg logit contributions
 them-0.003
mate-0.003
 polar-0.002
 wreck-0.002
 tow-0.002
Tokenck
Token ID694
Feature activation+8.83e-01

Pos logit contributions
+0.004
ages+0.003
's+0.003
bey+0.003
cious+0.003
Neg logit contributions
mate-0.003
 them-0.003
 tow-0.003
 wreck-0.003
 ramp-0.003
Tokened
Token ID276
Feature activation-3.19e+00

Pos logit contributions
 them+0.073
mate+0.073
 polar+0.067
 wreck+0.067
 tow+0.066
Neg logit contributions
-0.044
's-0.035
ages-0.034
aul-0.032
cious-0.030
Token at
Token ID379
Feature activation-1.30e+00

Pos logit contributions
+0.255
's+0.228
ages+0.212
aul+0.202
cious+0.198
Neg logit contributions
mate-0.169
 them-0.152
 wreck-0.151
 ramp-0.150
 polar-0.149
Token them
Token ID606
Feature activation+7.22e+00

Pos logit contributions
+0.112
's+0.103
 Michelle+0.096
aul+0.092
 pays+0.090
Neg logit contributions
mate-0.052
 ramp-0.049
inn-0.046
 polar-0.045
 puck-0.045
Token.
Token ID13
Feature activation+4.62e-01

Pos logit contributions
 them+0.360
mate+0.346
 wreck+0.296
 tow+0.288
 ramp+0.284
Neg logit contributions
-0.588
ages-0.527
aul-0.512
's-0.509
cious-0.495
Token Tim
Token ID5045
Feature activation+1.76e+00

Pos logit contributions
mate+0.031
 them+0.030
 wreck+0.028
 polar+0.028
 ramp+0.027
Neg logit contributions
-0.031
's-0.026
ages-0.025
aul-0.024
 List-0.023
Token and
Token ID290
Feature activation-3.37e-02

Pos logit contributions
 them+0.085
mate+0.082
 wreck+0.073
 polar+0.073
 snowball+0.072
Neg logit contributions
-0.144
ages-0.127
aul-0.124
 decisions-0.123
's-0.122
Token Mia
Token ID32189
Feature activation+1.34e+00

Pos logit contributions
+0.002
's+0.002
ages+0.002
cious+0.002
aul+0.002
Neg logit contributions
mate-0.002
 them-0.002
 wreck-0.002
 tow-0.002
 ramp-0.002
Token screamed
Token ID25421
Feature activation+4.42e-01

Pos logit contributions
 them+0.076
mate+0.076
 wreck+0.067
 polar+0.067
 tow+0.066
Neg logit contributions
-0.101
's-0.087
ages-0.087
aul-0.083
cious-0.080
Token can
Token ID460
Feature activation+9.20e-01

Pos logit contributions
+0.259
's+0.221
ages+0.195
aul+0.183
bey+0.180
Neg logit contributions
mate-0.237
 them-0.220
 polar-0.217
 ramp-0.209
 tow-0.209
Token smell
Token ID8508
Feature activation+3.06e-01

Pos logit contributions
mate+0.056
 polar+0.054
 snowball+0.051
 tant+0.049
 ramp+0.049
Neg logit contributions
-0.073
's-0.063
ages-0.050
aul-0.050
bey-0.049
Token them
Token ID606
Feature activation+7.28e+00

Pos logit contributions
mate+0.015
 ramp+0.012
 tow+0.012
inn+0.011
 racer+0.011
Neg logit contributions
-0.027
's-0.025
aul-0.023
 decisions-0.023
ages-0.022
Token and
Token ID290
Feature activation+1.77e-02

Pos logit contributions
 them+0.366
mate+0.314
 wreck+0.269
 polar+0.262
 captain+0.262
Neg logit contributions
-0.609
ages-0.552
aul-0.523
's-0.519
cious-0.518
Token touch
Token ID3638
Feature activation-1.89e+00

Pos logit contributions
mate+0.001
 them+0.001
 wreck+0.001
 polar+0.001
 tow+0.001
Neg logit contributions
-0.001
's-0.001
ages-0.001
aul-0.001
cious-0.001
Token them
Token ID606
Feature activation+7.29e+00

Pos logit contributions
+0.225
's+0.210
ages+0.197
aul+0.195
 decisions+0.192
Neg logit contributions
mate-0.031
 ramp-0.017
 tow-0.016
 wreck-0.015
inn-0.015
Token,
Token ID11
Feature activation+3.76e-02

Pos logit contributions
 them+0.352
mate+0.318
 wreck+0.269
 polar+0.261
 ramp+0.260
Neg logit contributions
-0.614
ages-0.551
's-0.530
aul-0.526
cious-0.520
Token but
Token ID475
Feature activation+2.52e+00

Pos logit contributions
mate+0.002
 them+0.002
 tow+0.002
 polar+0.002
 wreck+0.002
Neg logit contributions
-0.003
's-0.003
ages-0.002
aul-0.002
cious-0.002
Token we
Token ID356
Feature activation-3.41e+00

Pos logit contributions
 them+0.178
mate+0.171
 wreck+0.156
 polar+0.155
 tow+0.153
Neg logit contributions
-0.158
ages-0.136
's-0.132
aul-0.127
cious-0.123
Token can
Token ID460
Feature activation+9.37e-01

Pos logit contributions
+0.253
's+0.220
ages+0.212
aul+0.202
cious+0.196
Neg logit contributions
mate-0.202
 them-0.198
 polar-0.178
 wreck-0.177
 tow-0.177
Token't
Token ID470
Feature activation+4.42e+00

Pos logit contributions
mate+0.059
 polar+0.053
 snowball+0.051
 ramp+0.051
 them+0.051
Neg logit contributions
-0.071
's-0.061
ages-0.053
aul-0.052
cious-0.050
Token us
Token ID514
Feature activation+2.36e+00

Pos logit contributions
+0.116
's+0.106
ages+0.105
aul+0.102
cious+0.101
Neg logit contributions
 them-0.018
mate-0.015
 polar-0.009
 wreck-0.009
 tow-0.008
Token our
Token ID674
Feature activation+1.71e+00

Pos logit contributions
 them+0.142
mate+0.133
 polar+0.119
 wreck+0.119
 snowball+0.115
Neg logit contributions
-0.174
ages-0.150
's-0.149
aul-0.143
cious-0.142
Token coins
Token ID10796
Feature activation+5.29e-01

Pos logit contributions
mate+0.110
 them+0.099
inn+0.098
 ramp+0.093
 polar+0.093
Neg logit contributions
-0.118
's-0.107
ages-0.101
aul-0.095
 decisions-0.094
Token back
Token ID736
Feature activation+5.30e-01

Pos logit contributions
mate+0.028
 them+0.028
 polar+0.025
 wreck+0.025
 tow+0.025
Neg logit contributions
-0.042
's-0.037
ages-0.036
aul-0.034
cious-0.033
Token."
Token ID526
Feature activation+2.73e+00

Pos logit contributions
mate+0.028
 them+0.027
 wreck+0.024
 polar+0.024
 tow+0.024
Neg logit contributions
-0.042
's-0.037
ages-0.036
aul-0.035
cious-0.034
Token Tom
Token ID4186
Feature activation-7.68e-03

Pos logit contributions
 them+0.151
mate+0.119
 tow+0.118
 polar+0.115
 his+0.112
Neg logit contributions
-0.214
ages-0.207
's-0.190
ience-0.190
cious-0.189
Token says
Token ID1139
Feature activation-1.09e+00

Pos logit contributions
+0.000
ages+0.000
cious+0.000
aul+0.000
's+0.000
Neg logit contributions
 them-0.001
mate-0.001
 snowball-0.001
 polar-0.001
 wreck-0.001
Token.
Token ID13
Feature activation+9.80e-01

Pos logit contributions
+0.094
ages+0.083
aul+0.082
's+0.081
cious+0.079
Neg logit contributions
 them-0.052
mate-0.048
 tow-0.039
 polar-0.038
 wreck-0.038
Token
Token ID198
Feature activation+2.36e-01

Pos logit contributions
mate+0.085
 wreck+0.080
 polar+0.075
 them+0.074
 ramp+0.074
Neg logit contributions
-0.051
's-0.041
ages-0.035
 List-0.032
aul-0.030
Token
Token ID198
Feature activation+2.22e-01

Pos logit contributions
mate+0.020
 wreck+0.018
 captain+0.017
 polar+0.017
 racer+0.017
Neg logit contributions
-0.013
's-0.011
ages-0.009
aul-0.009
 List-0.009
TokenThey
Token ID2990
Feature activation+1.39e+00

Pos logit contributions
mate+0.014
 them+0.014
 wreck+0.013
 polar+0.013
 tow+0.012
Neg logit contributions
-0.016
's-0.014
ages-0.013
aul-0.012
cious-0.012
Token back
Token ID736
Feature activation+7.62e-01

Pos logit contributions
+0.003
's+0.003
ages+0.003
aul+0.002
cious+0.002
Neg logit contributions
mate-0.003
 them-0.002
 wreck-0.002
 ramp-0.002
 tow-0.002
Token soon
Token ID2582
Feature activation+1.07e+00

Pos logit contributions
 them+0.043
mate+0.042
 polar+0.037
 wreck+0.037
 tow+0.036
Neg logit contributions
-0.058
ages-0.050
's-0.050
aul-0.048
cious-0.047
Token.
Token ID13
Feature activation+8.17e-01

Pos logit contributions
 them+0.053
mate+0.050
 wreck+0.043
 tow+0.042
 polar+0.042
Neg logit contributions
-0.089
ages-0.079
's-0.078
aul-0.076
cious-0.075
Token<|endoftext|>
Token ID50256
Feature activation-5.41e-01

Pos logit contributions
 them+0.042
mate+0.037
 tow+0.035
 ramp+0.031
 polar+0.030
Neg logit contributions
ages-0.063
ience-0.060
-0.058
 decisions-0.058
aul-0.057
TokenL
Token ID43
Feature activation+7.54e-01

Pos logit contributions
+0.038
ages+0.034
's+0.033
cious+0.032
ience+0.031
Neg logit contributions
 them-0.033
mate-0.032
 tow-0.028
 wreck-0.028
 polar-0.028
Tokenily
Token ID813
Feature activation+1.40e+00

Pos logit contributions
mate+0.053
 ramp+0.049
 wreck+0.049
 tow+0.047
 polar+0.047
Neg logit contributions
-0.048
's-0.043
aul-0.039
ages-0.037
bey-0.036
Token liked
Token ID8288
Feature activation+1.65e+00

Pos logit contributions
 them+0.060
 his+0.049
 polar+0.048
 rock+0.047
 wreck+0.046
Neg logit contributions
-0.114
 decisions-0.113
ages-0.113
cious-0.108
 List-0.106
Token to
Token ID284
Feature activation-4.26e-01

Pos logit contributions
 them+0.094
mate+0.092
 wreck+0.082
 polar+0.082
 tow+0.081
Neg logit contributions
-0.126
's-0.110
ages-0.108
aul-0.102
cious-0.100
Token play
Token ID711
Feature activation+3.19e+00

Pos logit contributions
+0.035
's+0.030
ages+0.027
aul+0.026
cious+0.026
Neg logit contributions
mate-0.023
 them-0.021
inn-0.020
 polar-0.020
 wreck-0.019
Token with
Token ID351
Feature activation-9.76e-01

Pos logit contributions
 tow+0.224
 polar+0.221
 crashing+0.211
 spoiler+0.209
 wreck+0.205
Neg logit contributions
's-0.187
-0.183
aul-0.135
ages-0.126
rawling-0.117
Token her
Token ID607
Feature activation+1.08e+00

Pos logit contributions
+0.057
's+0.053
ages+0.046
aul+0.045
 Michelle+0.043
Neg logit contributions
mate-0.072
 ramp-0.063
 wreck-0.062
inn-0.062
 captain-0.062
Token smiled
Token ID13541
Feature activation-2.15e+00

Pos logit contributions
+0.013
ages+0.012
 decisions+0.012
aul+0.011
 List+0.011
Neg logit contributions
 them-0.011
mate-0.010
 polar-0.009
 wreck-0.009
 captain-0.009
Token and
Token ID290
Feature activation-8.83e-01

Pos logit contributions
+0.171
ages+0.151
's+0.149
aul+0.145
cious+0.142
Neg logit contributions
 them-0.113
mate-0.111
 polar-0.097
 wreck-0.095
 tow-0.095
Token said
Token ID531
Feature activation-8.89e-02

Pos logit contributions
+0.064
aul+0.062
 decisions+0.061
ages+0.058
lette+0.057
Neg logit contributions
 them-0.047
 his-0.045
 polar-0.042
 hon-0.042
mate-0.041
Token,
Token ID11
Feature activation-6.66e-01

Pos logit contributions
+0.007
's+0.006
ages+0.006
aul+0.006
cious+0.006
Neg logit contributions
mate-0.005
 them-0.005
 wreck-0.004
 polar-0.004
 tow-0.004
Token "
Token ID366
Feature activation+1.62e+00

Pos logit contributions
+0.055
's+0.048
ages+0.048
aul+0.046
cious+0.044
Neg logit contributions
 them-0.033
mate-0.033
 tow-0.028
 polar-0.028
 wreck-0.028
TokenIt
Token ID1026
Feature activation+6.14e-01

Pos logit contributions
mate+0.109
 them+0.105
 tow+0.094
inn+0.093
 racer+0.091
Neg logit contributions
-0.098
's-0.093
ages-0.093
 decisions-0.087
aul-0.085
Token's
Token ID338
Feature activation-9.08e+00

Pos logit contributions
 them+0.046
 match+0.043
mate+0.043
 bear+0.041
 zoom+0.040
Neg logit contributions
cious-0.029
aul-0.029
oney-0.026
assy-0.026
enna-0.026
Token OK
Token ID7477
Feature activation-4.55e+00

Pos logit contributions
+0.446
ages+0.436
cious+0.423
aul+0.389
's+0.387
Neg logit contributions
 them-0.738
mate-0.703
 snowball-0.647
 polar-0.645
 tow-0.640
Token.
Token ID13
Feature activation-5.32e-01

Pos logit contributions
+0.355
's+0.311
ages+0.307
aul+0.292
cious+0.285
Neg logit contributions
mate-0.250
 them-0.248
 polar-0.218
 wreck-0.217
 tow-0.215
Token That
Token ID1320
Feature activation-3.96e+00

Pos logit contributions
ages+0.032
cious+0.031
+0.031
aul+0.029
's+0.029
Neg logit contributions
mate-0.034
 tow-0.032
 them-0.032
 polar-0.030
 ramp-0.029
Token's
Token ID338
Feature activation-9.10e+00

Pos logit contributions
oney+0.248
cious+0.246
aul+0.231
riet+0.230
enna+0.229
Neg logit contributions
 snowball-0.236
 wreck-0.228
 rock-0.227
mate-0.222
 lot-0.222
Token was
Token ID373
Feature activation+6.25e-01

Pos logit contributions
mate+0.000
 them+0.000
 captain+0.000
 ramp+0.000
 polar+0.000
Neg logit contributions
-0.000
's-0.000
aul-0.000
ages-0.000
bey-0.000
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
 them+0.038
mate+0.037
 polar+0.034
 tow+0.033
 wreck+0.033
Neg logit contributions
-0.045
ages-0.039
's-0.039
aul-0.037
cious-0.036
Token little
Token ID1310
Feature activation+5.05e-01

Pos logit contributions
+0.073
's+0.064
aul+0.058
ages+0.056
cious+0.055
Neg logit contributions
mate-0.070
 them-0.070
inn-0.061
 tow-0.058
 wreck-0.058
Token girl
Token ID2576
Feature activation+1.48e+00

Pos logit contributions
mate+0.030
 them+0.030
 tow+0.026
 wreck+0.026
 polar+0.025
Neg logit contributions
-0.037
's-0.033
ages-0.031
aul-0.030
cious-0.029
Token named
Token ID3706
Feature activation+3.65e+00

Pos logit contributions
 them+0.053
mate+0.053
 polar+0.044
 tow+0.043
 wreck+0.043
Neg logit contributions
-0.141
ages-0.127
's-0.125
aul-0.122
 decisions-0.119
Token Mia
Token ID32189
Feature activation+9.73e-01

Pos logit contributions
 them+0.116
mate+0.100
 tow+0.075
inn+0.072
 polar+0.066
Neg logit contributions
-0.367
ages-0.354
 decisions-0.340
aul-0.334
ience-0.331
Token.
Token ID13
Feature activation-2.42e-02

Pos logit contributions
 them+0.047
mate+0.045
 polar+0.040
 wreck+0.039
 tow+0.038
Neg logit contributions
-0.082
ages-0.074
's-0.070
 decisions-0.069
aul-0.069
Token She
Token ID1375
Feature activation-7.35e-01

Pos logit contributions
+0.002
's+0.001
ages+0.001
aul+0.001
cious+0.001
Neg logit contributions
mate-0.002
 them-0.002
 wreck-0.001
 polar-0.001
 tow-0.001
Token loved
Token ID6151
Feature activation-1.01e+00

Pos logit contributions
+0.054
 decisions+0.050
ages+0.046
aul+0.045
ience+0.045
Neg logit contributions
 them-0.041
mate-0.039
 polar-0.038
 wreck-0.036
 snowball-0.035
Token to
Token ID284
Feature activation-3.11e-01

Pos logit contributions
+0.081
's+0.069
ages+0.068
aul+0.065
cious+0.064
Neg logit contributions
 them-0.056
mate-0.053
 polar-0.048
 wreck-0.048
 tow-0.046
Token spend
Token ID4341
Feature activation+5.06e+00

Pos logit contributions
+0.027
's+0.024
ages+0.023
aul+0.023
cious+0.022
Neg logit contributions
mate-0.015
 them-0.014
 wreck-0.012
inn-0.012
 polar-0.012
Token noise
Token ID7838
Feature activation-1.19e+00

Pos logit contributions
mate+0.258
 them+0.255
 polar+0.231
 tow+0.231
inn+0.229
Neg logit contributions
-0.324
's-0.289
ages-0.256
aul-0.238
 pays-0.235
Token coming
Token ID2406
Feature activation+8.41e-01

Pos logit contributions
+0.086
's+0.076
ages+0.068
aul+0.064
 pays+0.063
Neg logit contributions
mate-0.073
 them-0.069
 tow-0.065
 polar-0.065
 ramp-0.065
Token from
Token ID422
Feature activation-4.18e+00

Pos logit contributions
mate+0.067
 them+0.063
 puck+0.062
 tow+0.062
 ramp+0.062
Neg logit contributions
-0.048
's-0.039
ages-0.030
 pays-0.029
 decisions-0.029
Token her
Token ID607
Feature activation+1.07e+00

Pos logit contributions
+0.245
's+0.196
 Michelle+0.175
 Louise+0.171
 pays+0.162
Neg logit contributions
mate-0.298
inn-0.277
 puck-0.272
 polar-0.269
 tow-0.267
Token bedroom
Token ID14043
Feature activation+1.78e+00

Pos logit contributions
mate+0.060
 them+0.060
inn+0.052
 tow+0.052
 polar+0.052
Neg logit contributions
-0.082
's-0.074
ages-0.069
aul-0.066
cious-0.064
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
mate+0.093
 them+0.092
 polar+0.081
 wreck+0.080
 tow+0.080
Neg logit contributions
-0.143
's-0.126
ages-0.123
aul-0.117
cious-0.114
Token She
Token ID1375
Feature activation-8.37e-01

Pos logit contributions
+0.020
bey+0.020
ages+0.020
ience+0.020
 decisions+0.019
Neg logit contributions
 them-0.013
mate-0.012
 tow-0.011
 his-0.010
 ramp-0.010
Token stopped
Token ID5025
Feature activation-3.90e+00

Pos logit contributions
+0.058
's+0.050
ages+0.048
aul+0.046
cious+0.044
Neg logit contributions
mate-0.054
 them-0.053
 wreck-0.048
 polar-0.047
 tow-0.047
Token and
Token ID290
Feature activation-6.62e-01

Pos logit contributions
+0.282
's+0.247
ages+0.222
aul+0.212
 pays+0.209
Neg logit contributions
mate-0.243
 them-0.226
 tow-0.220
 ramp-0.214
 polar-0.214
Token listened
Token ID16399
Feature activation-6.90e+00

Pos logit contributions
+0.052
ages+0.050
 decisions+0.049
aul+0.048
cious+0.045
Neg logit contributions
 them-0.037
mate-0.030
 wreck-0.029
 hon-0.029
 his-0.028
Token,
Token ID11
Feature activation-4.32e-01

Pos logit contributions
+0.540
ages+0.480
's+0.473
aul+0.463
 decisions+0.443
Neg logit contributions
 them-0.372
mate-0.356
 wreck-0.308
 tow-0.304
 polar-0.302
Token Lily
Token ID20037
Feature activation+2.80e+00

Pos logit contributions
+0.023
's+0.020
ages+0.020
aul+0.019
cious+0.018
Neg logit contributions
mate-0.020
 them-0.020
 polar-0.018
 wreck-0.018
 tow-0.018
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
 them+0.117
mate+0.116
 ramp+0.091
 snowball+0.091
 wreck+0.090
Neg logit contributions
-0.235
ages-0.221
 List-0.217
aul-0.216
cious-0.216
Token You
Token ID921
Feature activation-2.57e+00

Pos logit contributions
mate+0.007
 tow+0.007
 them+0.007
 ramp+0.006
 polar+0.006
Neg logit contributions
ages-0.006
-0.006
aul-0.005
ience-0.005
cious-0.005
Token can
Token ID460
Feature activation+9.75e-01

Pos logit contributions
+0.199
ages+0.185
aul+0.176
's+0.175
cious+0.175
Neg logit contributions
 them-0.132
mate-0.128
 wreck-0.119
 tow-0.115
 polar-0.113
Token play
Token ID711
Feature activation+3.19e+00

Pos logit contributions
mate+0.060
 tant+0.057
 polar+0.054
 snowball+0.052
 them+0.051
Neg logit contributions
-0.082
's-0.069
ages-0.051
bey-0.051
ama-0.050
Token with
Token ID351
Feature activation-1.21e+00

Pos logit contributions
 tow+0.260
 polar+0.249
 crashing+0.233
inn+0.228
 detector+0.227
Neg logit contributions
-0.191
's-0.182
ages-0.110
 you-0.101
 doesn-0.100
Token my
Token ID616
Feature activation+2.12e+00

Pos logit contributions
+0.078
's+0.071
aul+0.058
ages+0.057
 Michelle+0.056
Neg logit contributions
mate-0.083
 tow-0.077
inn-0.077
 polar-0.076
 ramp-0.074
Token car
Token ID1097
Feature activation+4.43e+00

Pos logit contributions
mate+0.106
 them+0.102
inn+0.100
 tow+0.092
 polar+0.083
Neg logit contributions
-0.172
's-0.162
ages-0.144
 decisions-0.136
aul-0.136
Token.
Token ID13
Feature activation+2.48e-01

Pos logit contributions
mate+0.276
 them+0.273
 tow+0.271
 polar+0.270
inn+0.251
Neg logit contributions
-0.310
's-0.288
ages-0.250
aul-0.225
 pays-0.222
Token And
Token ID843
Feature activation-3.12e+00

Pos logit contributions
mate+0.018
 them+0.017
 tow+0.016
 polar+0.016
 wreck+0.016
Neg logit contributions
-0.015
's-0.013
ages-0.013
aul-0.012
cious-0.011
Token I
Token ID314
Feature activation-3.04e+00

Pos logit contributions
+0.180
ages+0.152
's+0.151
aul+0.143
cious+0.136
Neg logit contributions
 them-0.231
mate-0.230
 wreck-0.207
 tow-0.206
 polar-0.206
Token off
Token ID572
Feature activation-9.25e-01

Pos logit contributions
+0.237
's+0.207
ages+0.181
 pays+0.176
aul+0.169
Neg logit contributions
mate-0.224
 them-0.216
 polar-0.209
 tow-0.204
 wreck-0.204
Token she
Token ID673
Feature activation-3.61e+00

Pos logit contributions
+0.060
's+0.052
ages+0.046
 pays+0.043
aul+0.043
Neg logit contributions
mate-0.062
 them-0.058
 wreck-0.057
 polar-0.057
 snowball-0.056
Token would
Token ID561
Feature activation+1.36e+00

Pos logit contributions
+0.258
ages+0.232
aul+0.225
 decisions+0.221
cious+0.219
Neg logit contributions
 them-0.207
mate-0.197
 wreck-0.189
 polar-0.180
 tow-0.176
Token look
Token ID804
Feature activation-1.13e-01

Pos logit contributions
mate+0.081
inn+0.075
 them+0.074
 polar+0.073
 snowball+0.071
Neg logit contributions
-0.107
's-0.090
adow-0.073
 listens-0.073
 pays-0.073
Token up
Token ID510
Feature activation-4.62e+00

Pos logit contributions
+0.008
's+0.007
ages+0.006
aul+0.006
 pays+0.006
Neg logit contributions
mate-0.007
 them-0.007
 polar-0.007
 wreck-0.007
 tow-0.007
Token at
Token ID379
Feature activation-1.23e+00

Pos logit contributions
+0.357
ages+0.319
's+0.308
aul+0.296
cious+0.294
Neg logit contributions
 them-0.264
mate-0.250
 wreck-0.219
 tow-0.217
 polar-0.216
Token her
Token ID607
Feature activation+1.03e+00

Pos logit contributions
+0.087
's+0.076
ages+0.070
aul+0.068
 decisions+0.067
Neg logit contributions
mate-0.076
 them-0.069
 polar-0.069
 wreck-0.067
 ramp-0.067
Token mom
Token ID1995
Feature activation-3.46e-01

Pos logit contributions
mate+0.054
 them+0.054
 wreck+0.047
 polar+0.047
 tow+0.047
Neg logit contributions
-0.082
's-0.071
ages-0.071
aul-0.068
cious-0.066
Token and
Token ID290
Feature activation-6.89e-01

Pos logit contributions
+0.027
ages+0.025
aul+0.023
cious+0.023
ience+0.023
Neg logit contributions
 them-0.018
mate-0.017
 polar-0.015
 wreck-0.015
 tow-0.015
Token say
Token ID910
Feature activation+3.02e-01

Pos logit contributions
+0.053
ages+0.047
aul+0.045
cious+0.045
ience+0.045
Neg logit contributions
 them-0.039
mate-0.036
 wreck-0.033
 polar-0.032
 tow-0.032
Token
Token ID6184
Feature activation-2.92e-01

Pos logit contributions
 them+0.016
mate+0.015
 tow+0.013
 wreck+0.012
 polar+0.012
Neg logit contributions
-0.024
ages-0.022
's-0.021
aul-0.021
aut-0.020
TokenOne
Token ID3198
Feature activation+1.99e+00

Pos logit contributions
+0.082
's+0.070
ages+0.070
aul+0.066
cious+0.064
Neg logit contributions
 them-0.078
mate-0.078
 polar-0.069
 wreck-0.069
 tow-0.069
Token day
Token ID1110
Feature activation-2.21e+00

Pos logit contributions
 them+0.106
mate+0.098
 wreck+0.095
 polar+0.094
 tow+0.094
Neg logit contributions
ages-0.146
-0.141
aul-0.133
cious-0.131
ience-0.128
Token,
Token ID11
Feature activation-5.37e-01

Pos logit contributions
+0.181
ages+0.170
aul+0.166
 decisions+0.164
's+0.160
Neg logit contributions
 them-0.109
mate-0.100
inn-0.086
 polar-0.085
 his-0.081
Token there
Token ID612
Feature activation-3.43e-01

Pos logit contributions
+0.037
's+0.030
ages+0.027
cious+0.026
aul+0.025
Neg logit contributions
mate-0.037
 them-0.034
 ramp-0.034
 wreck-0.033
 tow-0.033
Token was
Token ID373
Feature activation+3.85e-01

Pos logit contributions
+0.024
's+0.021
ages+0.019
aul+0.018
cious+0.017
Neg logit contributions
mate-0.023
 them-0.022
 polar-0.020
 wreck-0.020
 ramp-0.020
Token a
Token ID257
Feature activation-1.37e+00

Pos logit contributions
mate+0.025
 them+0.025
 wreck+0.022
 polar+0.022
 tow+0.022
Neg logit contributions
-0.026
's-0.023
ages-0.022
aul-0.021
cious-0.020
Token long
Token ID890
Feature activation+1.02e-01

Pos logit contributions
+0.098
's+0.085
aul+0.076
ages+0.075
cious+0.074
Neg logit contributions
 them-0.087
mate-0.086
inn-0.075
 tow-0.072
 wreck-0.072
Token circle
Token ID9197
Feature activation+3.17e+00

Pos logit contributions
 them+0.006
mate+0.006
 tow+0.005
 wreck+0.005
 polar+0.005
Neg logit contributions
-0.008
's-0.007
ages-0.007
aul-0.006
cious-0.006
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
 them+0.173
mate+0.173
 polar+0.153
 wreck+0.152
 tow+0.151
Neg logit contributions
-0.247
's-0.221
ages-0.210
aul-0.196
cious-0.194
Token It
Token ID632
Feature activation+8.01e-01

Pos logit contributions
+0.024
ages+0.021
's+0.021
aul+0.019
ience+0.019
Neg logit contributions
 them-0.022
mate-0.022
 tow-0.020
 wreck-0.020
 polar-0.020
Token needed
Token ID2622
Feature activation-2.35e+00

Pos logit contributions
mate+0.056
 them+0.054
 tow+0.049
 polar+0.049
 wreck+0.048
Neg logit contributions
-0.054
's-0.047
ages-0.042
aul-0.039
 pays-0.038
Token said
Token ID531
Feature activation+4.06e-02

Pos logit contributions
+0.029
ages+0.025
aul+0.025
's+0.024
 decisions+0.024
Neg logit contributions
 them-0.029
mate-0.028
 polar-0.026
 captain-0.026
 wreck-0.025
Token.
Token ID13
Feature activation-3.85e-01

Pos logit contributions
 them+0.002
mate+0.002
 tow+0.001
 control+0.001
 wreck+0.001
Neg logit contributions
-0.004
aul-0.003
ages-0.003
 pays-0.003
bey-0.003
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
+0.028
ages+0.025
aul+0.025
 decisions+0.024
's+0.024
Neg logit contributions
 them-0.023
mate-0.021
 tow-0.020
 polar-0.019
 captain-0.019
Token
Token ID198
Feature activation-4.27e-01

Pos logit contributions
+0.027
's+0.023
ages+0.021
aul+0.020
cious+0.019
Neg logit contributions
mate-0.030
 them-0.028
 wreck-0.027
 polar-0.027
 ramp-0.026
TokenSab
Token ID39646
Feature activation-1.55e+00

Pos logit contributions
+0.027
's+0.023
ages+0.022
aul+0.020
cious+0.020
Neg logit contributions
mate-0.030
 them-0.030
 wreck-0.027
 polar-0.027
 tow-0.027
Tokenina
Token ID1437
Feature activation-1.33e+00

Pos logit contributions
+0.092
ages+0.077
's+0.074
aul+0.069
 decisions+0.068
Neg logit contributions
mate-0.113
 them-0.113
 polar-0.102
inn-0.100
 captain-0.099
Token felt
Token ID2936
Feature activation-1.34e+00

Pos logit contributions
 decisions+0.098
ages+0.095
+0.093
 rewarding+0.092
aul+0.089
Neg logit contributions
 them-0.068
 row-0.056
 stuffed-0.056
mate-0.055
 wreck-0.055
Token sad
Token ID6507
Feature activation+8.88e-01

Pos logit contributions
+0.092
ages+0.092
aul+0.087
cious+0.084
bey+0.084
Neg logit contributions
 them-0.078
mate-0.069
 tow-0.065
 wreck-0.064
 his-0.064
Token.
Token ID13
Feature activation-3.61e-01

Pos logit contributions
mate+0.050
 them+0.050
 wreck+0.044
 polar+0.044
 tow+0.043
Neg logit contributions
-0.068
's-0.059
ages-0.058
aul-0.055
cious-0.054
Token She
Token ID1375
Feature activation-7.88e-01

Pos logit contributions
+0.027
ages+0.027
uch+0.025
ience+0.025
bey+0.024
Neg logit contributions
 them-0.019
mate-0.017
 his-0.015
 captain-0.015
 tow-0.014
Token apologised
Token ID46397
Feature activation-4.58e+00

Pos logit contributions
+0.052
ages+0.048
 decisions+0.046
aul+0.045
's+0.044
Neg logit contributions
 them-0.048
mate-0.045
 wreck-0.043
 polar-0.042
 captain-0.041
Token idea
Token ID2126
Feature activation+5.50e+00

Pos logit contributions
+0.033
's+0.029
ages+0.028
aul+0.027
cious+0.026
Neg logit contributions
mate-0.023
 them-0.022
 polar-0.020
 wreck-0.020
 tow-0.019
Token.
Token ID13
Feature activation-1.03e-01

Pos logit contributions
 them+0.289
mate+0.286
 wreck+0.236
 tow+0.236
 polar+0.232
Neg logit contributions
-0.435
ages-0.386
's-0.381
aul-0.377
cious-0.363
Token<|endoftext|>
Token ID50256
Feature activation-9.16e-01

Pos logit contributions
+0.007
ages+0.006
's+0.006
aul+0.006
cious+0.006
Neg logit contributions
 them-0.006
mate-0.006
 tow-0.005
 polar-0.005
 ramp-0.005
TokenOnce
Token ID7454
Feature activation+1.14e+00

Pos logit contributions
+0.063
's+0.054
ages+0.052
aul+0.049
cious+0.048
Neg logit contributions
mate-0.059
 them-0.058
 wreck-0.053
 polar-0.052
 tow-0.052
Token upon
Token ID2402
Feature activation+2.06e+00

Pos logit contributions
mate+0.071
 them+0.065
 polar+0.063
 ramp+0.063
 wreck+0.062
Neg logit contributions
-0.082
's-0.074
aul-0.064
bey-0.063
ages-0.062
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
mate+0.137
 them+0.134
 wreck+0.123
 polar+0.122
 tow+0.122
Neg logit contributions
-0.137
's-0.118
ages-0.113
aul-0.106
cious-0.103
Token time
Token ID640
Feature activation-5.71e-01

Pos logit contributions
+0.099
's+0.087
ages+0.086
aul+0.082
cious+0.080
Neg logit contributions
mate-0.063
 them-0.063
 polar-0.055
 wreck-0.055
 tow-0.054
Token,
Token ID11
Feature activation-3.90e-01

Pos logit contributions
+0.045
ages+0.042
's+0.040
aul+0.040
 decisions+0.038
Neg logit contributions
 them-0.029
mate-0.029
 wreck-0.025
 polar-0.024
 tow-0.024
Token there
Token ID612
Feature activation-2.01e-01

Pos logit contributions
+0.025
's+0.022
ages+0.019
aul+0.018
bey+0.018
Neg logit contributions
mate-0.027
 them-0.026
 tow-0.025
 wreck-0.025
 polar-0.025
Token was
Token ID373
Feature activation+4.29e-01

Pos logit contributions
+0.012
's+0.011
ages+0.008
aul+0.008
bey+0.008
Neg logit contributions
mate-0.015
 them-0.014
 captain-0.014
 ramp-0.014
 polar-0.014
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
 them+0.026
mate+0.024
 polar+0.022
 snowball+0.022
 tow+0.022
Neg logit contributions
-0.031
ages-0.028
's-0.027
aul-0.026
ience-0.026
Token she
Token ID673
Feature activation-3.39e+00

Pos logit contributions
 his+0.115
 them+0.111
 stuffed+0.091
 t+0.087
mate+0.086
Neg logit contributions
aul-0.130
ages-0.126
lette-0.125
-0.125
aut-0.124
Token saw
Token ID2497
Feature activation+3.85e+00

Pos logit contributions
+0.236
's+0.207
ages+0.191
aul+0.179
cious+0.177
Neg logit contributions
mate-0.224
 them-0.215
 wreck-0.197
 tow-0.195
 ramp-0.194
Token the
Token ID262
Feature activation-1.23e-01

Pos logit contributions
 them+0.235
mate+0.230
 wreck+0.204
 polar+0.204
 tow+0.203
Neg logit contributions
-0.281
's-0.243
ages-0.242
aul-0.227
cious-0.224
Token little
Token ID1310
Feature activation+5.47e-01

Pos logit contributions
+0.008
's+0.008
 decisions+0.007
aul+0.007
ages+0.007
Neg logit contributions
mate-0.008
inn-0.007
 them-0.006
room-0.006
 tow-0.006
Token boy
Token ID2933
Feature activation+2.37e+00

Pos logit contributions
mate+0.031
 them+0.030
inn+0.027
 wreck+0.026
 tow+0.026
Neg logit contributions
-0.042
's-0.037
ages-0.035
aul-0.034
cious-0.033
Token's
Token ID338
Feature activation-8.90e+00

Pos logit contributions
 them+0.139
mate+0.130
 wreck+0.122
 polar+0.120
 tow+0.117
Neg logit contributions
-0.171
ages-0.156
aul-0.150
's-0.143
cious-0.143
Token kind
Token ID1611
Feature activation-3.17e+00

Pos logit contributions
+0.616
's+0.551
ages+0.517
 decisions+0.497
cious+0.472
Neg logit contributions
mate-0.580
 them-0.538
inn-0.500
 ramp-0.484
 wreck-0.474
Token eyes
Token ID2951
Feature activation+1.57e+00

Pos logit contributions
+0.235
's+0.211
ages+0.199
aul+0.190
 decisions+0.186
Neg logit contributions
mate-0.186
 them-0.179
 ramp-0.163
 wreck-0.161
inn-0.160
Token.
Token ID13
Feature activation+6.17e-01

Pos logit contributions
 them+0.080
mate+0.076
 wreck+0.067
 tow+0.067
 polar+0.066
Neg logit contributions
-0.126
ages-0.114
's-0.110
aul-0.109
cious-0.106
Token She
Token ID1375
Feature activation-4.82e-01

Pos logit contributions
 them+0.037
mate+0.036
 tow+0.033
 polar+0.032
 wreck+0.032
Neg logit contributions
-0.043
ages-0.039
's-0.037
cious-0.037
bey-0.036
Token felt
Token ID2936
Feature activation-1.09e+00

Pos logit contributions
+0.030
's+0.026
ages+0.024
aul+0.022
cious+0.021
Neg logit contributions
mate-0.036
 them-0.034
 wreck-0.031
 ramp-0.031
 tow-0.031
Token,
Token ID11
Feature activation-3.07e-01

Pos logit contributions
 them+0.004
mate+0.004
 tow+0.003
 wreck+0.003
 polar+0.003
Neg logit contributions
-0.006
ages-0.006
's-0.005
aul-0.005
 decisions-0.005
Token "
Token ID366
Feature activation+1.84e+00

Pos logit contributions
+0.025
's+0.022
ages+0.022
aul+0.021
cious+0.020
Neg logit contributions
 them-0.015
mate-0.015
 wreck-0.013
 polar-0.013
 tow-0.013
TokenSure
Token ID19457
Feature activation+4.75e+00

Pos logit contributions
mate+0.113
 them+0.112
inn+0.096
 tow+0.094
 racer+0.092
Neg logit contributions
-0.126
ages-0.116
's-0.112
 decisions-0.108
aul-0.106
Token,
Token ID11
Feature activation-3.15e-01

Pos logit contributions
mate+0.269
 them+0.266
 wreck+0.235
 polar+0.235
 tow+0.233
Neg logit contributions
-0.364
's-0.318
ages-0.312
aul-0.297
cious-0.289
Token let
Token ID1309
Feature activation-1.16e+00

Pos logit contributions
+0.024
ages+0.022
's+0.021
aul+0.021
cious+0.020
Neg logit contributions
 them-0.018
mate-0.017
 tow-0.015
 polar-0.015
 wreck-0.015
Token's
Token ID338
Feature activation-8.93e+00

Pos logit contributions
ages+0.035
 List+0.035
cious+0.033
 rewarding+0.032
adow+0.031
Neg logit contributions
 them-0.123
mate-0.102
 snowball-0.094
 lot-0.094
 his-0.093
Token print
Token ID3601
Feature activation-5.44e-01

Pos logit contributions
+0.747
's+0.660
ages+0.639
aul+0.613
cious+0.596
Neg logit contributions
mate-0.443
 them-0.434
 polar-0.382
 wreck-0.378
 tow-0.375
Token a
Token ID257
Feature activation-1.04e+00

Pos logit contributions
+0.042
ages+0.037
cious+0.036
's+0.036
aul+0.035
Neg logit contributions
 them-0.031
mate-0.029
 wreck-0.025
 tow-0.024
 snowball-0.024
Token picture
Token ID4286
Feature activation-3.78e-01

Pos logit contributions
+0.077
's+0.067
ages+0.063
aul+0.061
cious+0.058
Neg logit contributions
mate-0.063
 them-0.062
 polar-0.056
 wreck-0.055
 tow-0.055
Token of
Token ID286
Feature activation+3.03e+00

Pos logit contributions
+0.032
's+0.028
ages+0.028
aul+0.027
cious+0.026
Neg logit contributions
mate-0.018
 them-0.018
 wreck-0.015
 tow-0.015
 polar-0.015
Token the
Token ID262
Feature activation-2.39e-01

Pos logit contributions
 them+0.177
mate+0.160
 wreck+0.142
 tow+0.139
 polar+0.135
Neg logit contributions
-0.234
ages-0.210
's-0.201
cious-0.196
aul-0.193
TokenAnd
Token ID1870
Feature activation+1.38e+00

Pos logit contributions
+0.038
's+0.032
ages+0.031
aul+0.029
cious+0.028
Neg logit contributions
mate-0.039
 them-0.039
 wreck-0.036
 polar-0.036
 tow-0.035
Token he
Token ID339
Feature activation-4.94e-01

Pos logit contributions
 them+0.071
mate+0.066
 his+0.059
 captain+0.055
 polar+0.053
Neg logit contributions
ages-0.105
-0.103
aul-0.101
aut-0.096
cious-0.095
Token did
Token ID750
Feature activation+1.97e+00

Pos logit contributions
+0.033
ages+0.030
aul+0.029
's+0.028
 decisions+0.028
Neg logit contributions
mate-0.031
 them-0.030
 wreck-0.026
 polar-0.026
 tow-0.026
Token!
Token ID0
Feature activation+1.10e+00

Pos logit contributions
 them+0.102
mate+0.099
 wreck+0.084
 tow+0.084
 ramp+0.082
Neg logit contributions
-0.157
ages-0.140
's-0.139
aul-0.138
cious-0.133
Token Pete
Token ID17542
Feature activation-3.64e+00

Pos logit contributions
mate+0.050
 them+0.049
inn+0.044
 tow+0.043
 puck+0.040
Neg logit contributions
-0.087
ages-0.085
cious-0.083
's-0.082
ience-0.079
Token's
Token ID338
Feature activation-9.09e+00

Pos logit contributions
+0.238
ages+0.218
aul+0.215
 decisions+0.209
cious+0.206
Neg logit contributions
 them-0.216
mate-0.216
 wreck-0.192
 polar-0.187
 tow-0.185
Token speech
Token ID4046
Feature activation-1.92e+00

Pos logit contributions
+0.636
ages+0.560
cious+0.545
aul+0.545
's+0.526
Neg logit contributions
mate-0.571
 them-0.530
 wreck-0.494
 tow-0.473
 control-0.470
Token was
Token ID373
Feature activation+5.10e-01

Pos logit contributions
+0.107
's+0.089
ages+0.088
aul+0.084
cious+0.079
Neg logit contributions
mate-0.146
 them-0.144
 wreck-0.131
 tow-0.131
 polar-0.131
Token one
Token ID530
Feature activation-4.31e-01

Pos logit contributions
mate+0.031
 them+0.031
 wreck+0.028
 tow+0.028
 polar+0.027
Neg logit contributions
-0.036
's-0.031
ages-0.031
aul-0.030
cious-0.029
Token of
Token ID286
Feature activation+2.70e+00

Pos logit contributions
+0.035
ages+0.033
aul+0.032
cious+0.031
's+0.031
Neg logit contributions
mate-0.021
 them-0.018
 wreck-0.017
 tow-0.017
 racer-0.016
Token the
Token ID262
Feature activation-4.44e-01

Pos logit contributions
mate+0.148
 ramp+0.143
 them+0.139
 polar+0.139
 wreck+0.135
Neg logit contributions
-0.208
's-0.171
 pays-0.161
ages-0.159
 decisions-0.157
Token Mom
Token ID11254
Feature activation-2.80e+00

Pos logit contributions
+0.028
ages+0.026
ience+0.025
aul+0.025
cious+0.024
Neg logit contributions
 them-0.021
mate-0.018
 tow-0.018
 wreck-0.018
 ramp-0.017
Token said
Token ID531
Feature activation-1.17e-01

Pos logit contributions
+0.168
's+0.141
ages+0.137
aul+0.129
cious+0.124
Neg logit contributions
mate-0.202
 them-0.202
 wreck-0.183
 polar-0.183
 tow-0.182
Token,
Token ID11
Feature activation-4.69e-01

Pos logit contributions
+0.009
ages+0.009
's+0.008
aul+0.008
 decisions+0.008
Neg logit contributions
 them-0.006
mate-0.006
 polar-0.005
 tow-0.005
 wreck-0.005
Token "
Token ID366
Feature activation+1.63e+00

Pos logit contributions
+0.039
ages+0.035
's+0.035
aul+0.034
 decisions+0.033
Neg logit contributions
 them-0.023
mate-0.021
 tow-0.018
 polar-0.018
 wreck-0.018
TokenIt
Token ID1026
Feature activation+5.35e-01

Pos logit contributions
 them+0.114
mate+0.107
 wreck+0.098
 tow+0.097
 snowball+0.096
Neg logit contributions
-0.100
ages-0.090
's-0.087
aul-0.086
cious-0.082
Token's
Token ID338
Feature activation-9.08e+00

Pos logit contributions
 them+0.046
 snowball+0.043
 wreck+0.043
 hon+0.043
 match+0.042
Neg logit contributions
aul-0.021
cious-0.019
assy-0.018
ages-0.017
enna-0.017
Token OK
Token ID7477
Feature activation-4.58e+00

Pos logit contributions
+0.481
ages+0.415
aul+0.413
's+0.392
cious+0.391
Neg logit contributions
 them-0.717
mate-0.693
 polar-0.651
 snowball-0.639
 wreck-0.633
Token,
Token ID11
Feature activation-4.77e-01

Pos logit contributions
+0.358
's+0.312
ages+0.310
aul+0.298
cious+0.290
Neg logit contributions
mate-0.249
 them-0.249
 polar-0.218
 wreck-0.214
 tow-0.212
Token Tommy
Token ID19919
Feature activation-1.96e-01

Pos logit contributions
+0.040
ages+0.038
aul+0.036
cious+0.036
's+0.036
Neg logit contributions
 them-0.023
mate-0.021
 tow-0.018
 wreck-0.018
 polar-0.018
Token.
Token ID13
Feature activation-3.87e-01

Pos logit contributions
+0.017
ages+0.015
 List+0.015
aul+0.014
cious+0.014
Neg logit contributions
 them-0.009
mate-0.008
 polar-0.007
 wreck-0.007
 tow-0.007
Token That
Token ID1320
Feature activation-3.97e+00

Pos logit contributions
ages+0.024
+0.023
cious+0.022
aul+0.021
's+0.021
Neg logit contributions
 them-0.024
mate-0.024
 tow-0.023
 polar-0.023
 wreck-0.022
Token kids
Token ID3988
Feature activation+1.15e+00

Pos logit contributions
+0.001
's+0.000
ages+0.000
 pays+0.000
aul+0.000
Neg logit contributions
mate-0.000
 them-0.000
 wreck-0.000
 polar-0.000
 tow-0.000
Token.
Token ID13
Feature activation+8.04e-01

Pos logit contributions
mate+0.061
 them+0.061
 wreck+0.053
 polar+0.053
 tow+0.053
Neg logit contributions
-0.091
's-0.080
ages-0.078
aul-0.074
cious-0.073
Token Now
Token ID2735
Feature activation+7.17e-01

Pos logit contributions
mate+0.048
 them+0.044
 tow+0.043
 racer+0.039
 ramp+0.038
Neg logit contributions
ages-0.054
-0.051
ups-0.050
ience-0.049
's-0.049
Token,
Token ID11
Feature activation-4.30e-02

Pos logit contributions
 them+0.038
mate+0.032
 captain+0.027
 tow+0.026
 match+0.026
Neg logit contributions
ages-0.058
-0.057
aul-0.054
cious-0.053
aut-0.052
Token let
Token ID1309
Feature activation-1.12e+00

Pos logit contributions
+0.003
ages+0.003
aul+0.003
cious+0.003
's+0.003
Neg logit contributions
 them-0.002
mate-0.002
 tow-0.002
 polar-0.002
 captain-0.002
Token's
Token ID338
Feature activation-8.98e+00

Pos logit contributions
ages+0.031
cious+0.029
 mindful+0.028
aul+0.026
 List+0.026
Neg logit contributions
 them-0.122
mate-0.104
 snowball-0.099
 polar-0.098
 tow-0.097
Token go
Token ID467
Feature activation-1.41e+00

Pos logit contributions
+0.743
's+0.653
ages+0.624
aul+0.599
cious+0.578
Neg logit contributions
mate-0.459
 them-0.446
 polar-0.395
 wreck-0.392
 tow-0.388
Token inside
Token ID2641
Feature activation-2.08e+00

Pos logit contributions
+0.096
's+0.088
ages+0.075
 pays+0.069
bey+0.069
Neg logit contributions
mate-0.096
 tant-0.084
 them-0.084
 wreck-0.083
 polar-0.082
Token and
Token ID290
Feature activation-3.96e-02

Pos logit contributions
+0.153
's+0.134
ages+0.125
aul+0.120
 pays+0.115
Neg logit contributions
mate-0.126
 them-0.120
 polar-0.112
 wreck-0.112
 tow-0.111
Token have
Token ID423
Feature activation+2.58e-01

Pos logit contributions
+0.004
ages+0.004
aul+0.004
ience+0.004
cious+0.003
Neg logit contributions
 them-0.001
mate-0.001
 wreck-0.001
 match-0.001
 tow-0.001
Token some
Token ID617
Feature activation-2.47e+00

Pos logit contributions
 them+0.015
mate+0.012
 snowball+0.012
 polar+0.012
 tow+0.011
Neg logit contributions
-0.020
ages-0.018
cious-0.017
aul-0.017
bey-0.017