TOP ACTIVATIONS
MAX = 0.622

that day on , Fl opsy and Mr . Snow man
orns and never met Fl opsy . He was glad for
happy and grateful to Fl opsy for saving him from melting
patient little bunny named Fl oppy . Fl oppy lived in
to play and asked Fl oppy to join . Fl oppy
named Fl oppy . Fl oppy lived in a modest little
very sad and missed Fl opsy . He wished he had
oppy to join . Fl oppy thought for a moment and
named Fl opsy . Fl opsy loved to hop and play
, whenever Anna took Fl opsy for a walk , she
hurt my ear ." Fl oppy apologized and they continued to
. The car hit Fl opsy and she was gone .
smooth and shiny . Fl oppy was so happy to have
too . H oppy hopped and hopped , but
man back together . Fl opsy was so brave and worked
bush . P oppy cries . She has no
! Be careful , Fl oppy . You hurt my ear
One day , Fl opsy hopped up to the gate
might get hurt ." Fl opsy listened to her friends and
a past el for Fl oppy to eat . The past

MIN ACTIVATIONS
MIN = -0.458

The towns folk searched high and low ,
. He asked the towns folk if they wanted him to
and days and the towns folk looked on .
thing ever . The towns folk cl apped and cheered because
its bouncing , the towns folk thanked the rope for its
was very happy with his sale . He had enough money
his grandma got it on sale ! <|endoftext|> Once upon a
were many beautiful apples for sale . The pirate smiled and
that jewel is not for sale . It is too special
che ap basketball s for sale ". Tim my asked his
put the rake up for sale and waited .
found the monster truck on sale . Tim my was very
that day , the garage sale was over and Lily and
old toys at a garage sale . Lily was scared because
. He is not for sale . Please , put him
T oys and books for sale ! One dollar each !"
these carrots are not for sale . They are for our
. He is not for sale . He is my friend
's yard was not for sale . Tim my was very
old toys at a garage sale . Tim my thought it

INTERVAL 0.352 - 0.622
CONTAINS 0.069%

ens by mistake . Mitt ens was upset and said ,
Spot and a cat named Fl uffy . One
cat named Mitt ens . Mitt ens loved to play with
was a little rabbit named Remy . Remy loved to spring
. She wanted Kitty and Bunny to be friends again .

INTERVAL 0.082 - 0.352
CONTAINS 12.999%

Suddenly he saw the book tucked away in a corner .
tape and go for a walk in the park . One
also made Angel wet and dirty . She could have been
: " Hello Ab ig ail ! I 'm glad you
, Annie was feeling very brave . She decided to escape

INTERVAL -0.188 - 0.082
CONTAINS 84.939%

One day , she found a veil in her sack .
, there was a little boy named John . He loved
a time , there was a girl called Jill . She
feels the wind in his hair . He sees the trees
could help him be free . He was so happy .

INTERVAL -0.458 - -0.188
CONTAINS 1.993%

again . Sarah thanked the bear and gave
He laughed and laughed . The man was
tiny mouse . The mouse asked the bald man if he
s go to the store and get you a battery
bons and shiny stars . When it was
Token that
Token ID326
Feature activation+9.81e-02

Pos logit contributions
oppy+0.429
opsy+0.408
chy+0.402
rig+0.379
 bur+0.378
Neg logit contributions
folk-0.189
 sale-0.186
 letters-0.180
 digits-0.169
 Amen-0.164
Token day
Token ID1110
Feature activation+4.47e-03

Pos logit contributions
opsy+0.238
oppy+0.234
rig+0.216
 Remy+0.212
 bur+0.210
Neg logit contributions
folk-0.109
 digits-0.104
 sale-0.102
 customer-0.098
 Amen-0.097
Token on
Token ID319
Feature activation-5.02e-02

Pos logit contributions
opsy+0.010
oppy+0.010
 Remy+0.009
 bur+0.009
chy+0.009
Neg logit contributions
folk-0.006
 digits-0.006
 sale-0.005
 customer-0.005
 letters-0.005
Token,
Token ID11
Feature activation-2.59e-02

Pos logit contributions
 sale+0.036
folk+0.034
 customer+0.028
 digits+0.026
 letters+0.025
Neg logit contributions
rig-0.143
opsy-0.139
oppy-0.132
chy-0.129
 bur-0.124
Token Fl
Token ID1610
Feature activation+3.94e-01

Pos logit contributions
 sale+0.045
folk+0.044
 customer+0.044
 ones+0.040
 one+0.040
Neg logit contributions
rig-0.045
opsy-0.042
oppy-0.042
 web-0.040
chy-0.040
Tokenopsy
Token ID44522
Feature activation+5.67e-01

Pos logit contributions
chy+0.351
rig+0.325
 web+0.311
 webs+0.299
 rubble+0.271
Neg logit contributions
ams-0.772
be-0.743
 ones-0.743
h-0.734
 customer-0.731
Token and
Token ID290
Feature activation+4.36e-02

Pos logit contributions
opsy+1.306
oppy+1.279
 Remy+1.178
rig+1.172
chy+1.125
Neg logit contributions
folk-0.734
 digits-0.695
 sale-0.627
 letters-0.619
 cheering-0.585
Token Mr
Token ID1770
Feature activation+1.67e-01

Pos logit contributions
rig+0.082
oppy+0.077
opsy+0.076
chy+0.072
 web+0.070
Neg logit contributions
folk-0.070
 sale-0.070
 customer-0.068
 Amen-0.067
 letters-0.065
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
rig+0.402
oppy+0.390
opsy+0.389
 bur+0.369
 web+0.359
Neg logit contributions
folk-0.164
boxes-0.148
 ones-0.148
 sale-0.147
 letters-0.146
Token Snow
Token ID7967
Feature activation+3.41e-01

Pos logit contributions
oppy+0.017
rig+0.017
chy+0.017
opsy+0.016
ches+0.015
Neg logit contributions
 sale-0.023
folk-0.022
 customer-0.021
 digits-0.021
 Amen-0.021
Tokenman
Token ID805
Feature activation-1.93e-01

Pos logit contributions
oppy+0.701
opsy+0.700
rig+0.671
 bur+0.644
 Remy+0.639
Neg logit contributions
folk-0.523
boxes-0.415
 sale-0.396
 winners-0.391
 cheering-0.390
Tokenorns
Token ID19942
Feature activation+1.59e-01

Pos logit contributions
opsy+0.401
oppy+0.388
 Remy+0.359
 bur+0.349
rig+0.349
Neg logit contributions
folk-0.427
 digits-0.418
 sale-0.402
 customer-0.394
bench-0.390
Token and
Token ID290
Feature activation+4.16e-02

Pos logit contributions
opsy+0.371
oppy+0.361
 Remy+0.333
 bur+0.320
uffy+0.318
Neg logit contributions
folk-0.211
 sale-0.201
 digits-0.182
 customer-0.179
epad-0.178
Token never
Token ID1239
Feature activation+5.74e-03

Pos logit contributions
opsy+0.095
oppy+0.093
rig+0.082
 Remy+0.081
uffy+0.081
Neg logit contributions
folk-0.058
 sale-0.055
 digits-0.053
 letters-0.052
epad-0.048
Token met
Token ID1138
Feature activation-8.09e-02

Pos logit contributions
opsy+0.013
oppy+0.013
 Remy+0.012
chy+0.011
uffy+0.011
Neg logit contributions
folk-0.008
 digits-0.008
 sale-0.007
 letters-0.007
epad-0.007
Token Fl
Token ID1610
Feature activation+3.93e-01

Pos logit contributions
folk+0.108
 sale+0.106
 digits+0.103
 letters+0.099
 customer+0.094
Neg logit contributions
oppy-0.182
opsy-0.181
rig-0.161
chy-0.159
uffy-0.156
Tokenopsy
Token ID44522
Feature activation+5.67e-01

Pos logit contributions
chy+0.277
rig+0.261
 Remy+0.196
 web+0.173
ches+0.159
Neg logit contributions
 customer-0.912
 digits-0.909
 sale-0.908
folk-0.878
 ones-0.877
Token.
Token ID13
Feature activation+8.46e-03

Pos logit contributions
opsy+1.376
oppy+1.340
 Remy+1.247
rig+1.222
 bur+1.207
Neg logit contributions
folk-0.649
 sale-0.599
 digits-0.570
 customer-0.555
 letters-0.525
Token He
Token ID679
Feature activation-1.10e-02

Pos logit contributions
opsy+0.019
oppy+0.019
rig+0.017
chy+0.017
 web+0.016
Neg logit contributions
 sale-0.010
 Amen-0.010
folk-0.010
 -0.009
 digits-0.009
Token was
Token ID373
Feature activation+6.28e-02

Pos logit contributions
folk+0.011
 digits+0.010
 sale+0.010
 Amen+0.010
 asked+0.010
Neg logit contributions
opsy-0.028
oppy-0.027
uffy-0.025
rig-0.024
 Remy-0.024
Token glad
Token ID9675
Feature activation-3.22e-03

Pos logit contributions
opsy+0.137
oppy+0.136
 Remy+0.125
chy+0.121
 bur+0.120
Neg logit contributions
folk-0.092
 digits-0.088
 sale-0.084
 customer-0.077
 Amen-0.077
Token for
Token ID329
Feature activation+1.27e-01

Pos logit contributions
 sale+0.003
 one+0.003
 them+0.003
folk+0.003
 cheering+0.003
Neg logit contributions
rig-0.008
oppy-0.008
opsy-0.008
chy-0.008
 web-0.007
Token happy
Token ID3772
Feature activation-6.59e-02

Pos logit contributions
folk+0.148
 digits+0.143
 sale+0.134
 customer+0.123
 prices+0.122
Neg logit contributions
opsy-0.193
oppy-0.191
 Remy-0.177
chy-0.174
 bur-0.169
Token and
Token ID290
Feature activation+3.86e-02

Pos logit contributions
folk+0.084
 sale+0.083
 digits+0.080
 cheering+0.074
 letters+0.073
Neg logit contributions
opsy-0.152
oppy-0.150
chy-0.136
rig-0.132
 bur-0.131
Token grateful
Token ID14066
Feature activation-6.08e-04

Pos logit contributions
opsy+0.091
oppy+0.090
uffy+0.081
chy+0.080
rig+0.080
Neg logit contributions
folk-0.047
 digits-0.044
 sale-0.042
 cheering-0.042
 letters-0.041
Token to
Token ID284
Feature activation+6.54e-03

Pos logit contributions
 sale+0.001
folk+0.001
 letters+0.001
 digits+0.001
 customer+0.001
Neg logit contributions
opsy-0.001
oppy-0.001
 bur-0.001
rig-0.001
chy-0.001
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
opsy+0.013
oppy+0.012
chy+0.011
 Remy+0.011
 bur+0.011
Neg logit contributions
folk-0.011
 digits-0.011
 sale-0.010
 customer-0.010
 Amen-0.010
Tokenopsy
Token ID44522
Feature activation+5.66e-01

Pos logit contributions
chy+0.318
 web+0.293
rig+0.272
 Remy+0.236
 cob+0.235
Neg logit contributions
 sale-0.823
 digits-0.812
 customer-0.811
be-0.801
folk-0.798
Token for
Token ID329
Feature activation+1.25e-01

Pos logit contributions
opsy+1.343
oppy+1.279
 Remy+1.183
 bur+1.163
rig+1.159
Neg logit contributions
folk-0.675
 digits-0.650
 sale-0.641
 letters-0.636
 customer-0.573
Token saving
Token ID8914
Feature activation-1.88e-02

Pos logit contributions
opsy+0.255
oppy+0.251
 Remy+0.250
 bur+0.236
chy+0.227
Neg logit contributions
folk-0.201
 digits-0.195
 sale-0.162
 prices-0.160
epad-0.159
Token him
Token ID683
Feature activation+1.34e-02

Pos logit contributions
 sale+0.025
folk+0.025
 digits+0.025
 customer+0.023
 letters+0.023
Neg logit contributions
opsy-0.042
oppy-0.041
chy-0.038
 Remy-0.037
rig-0.037
Token from
Token ID422
Feature activation+1.98e-01

Pos logit contributions
opsy+0.034
oppy+0.032
 Remy+0.030
uffy+0.029
 bur+0.028
Neg logit contributions
 sale-0.015
folk-0.014
 letters-0.013
 digits-0.013
 prices-0.012
Token melting
Token ID24203
Feature activation+9.15e-02

Pos logit contributions
opsy+0.417
oppy+0.413
 Remy+0.375
chy+0.369
 bur+0.363
Neg logit contributions
folk-0.306
 digits-0.295
 sale-0.287
 customer-0.263
 letters-0.259
Token patient
Token ID5827
Feature activation-6.85e-02

Pos logit contributions
opsy+0.029
oppy+0.029
 Remy+0.027
chy+0.027
 bur+0.026
Neg logit contributions
 digits-0.021
folk-0.021
 customer-0.020
 sale-0.020
 letters-0.018
Token little
Token ID1310
Feature activation+6.79e-02

Pos logit contributions
folk+0.122
 digits+0.121
 sale+0.109
epad+0.104
 letters+0.103
Neg logit contributions
opsy-0.129
oppy-0.127
 Remy-0.116
 bur-0.113
chy-0.112
Token bunny
Token ID44915
Feature activation+2.56e-01

Pos logit contributions
opsy+0.146
oppy+0.144
 Remy+0.134
chy+0.132
 bur+0.130
Neg logit contributions
folk-0.099
 digits-0.096
 sale-0.090
 customer-0.087
 letters-0.084
Token named
Token ID3706
Feature activation+6.21e-04

Pos logit contributions
opsy+0.598
oppy+0.585
chy+0.541
 Remy+0.541
 bur+0.539
Neg logit contributions
folk-0.303
 digits-0.299
 sale-0.291
 Amen-0.270
 customer-0.263
Token Fl
Token ID1610
Feature activation+3.91e-01

Pos logit contributions
opsy+0.001
oppy+0.001
rig+0.001
chy+0.001
 bur+0.001
Neg logit contributions
 sale-0.001
 customer-0.001
 digits-0.001
folk-0.001
 Robert-0.001
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
rig+0.293
chy+0.268
 refreshing+0.260
 Remy+0.204
 web+0.196
Neg logit contributions
 customer-0.932
 digits-0.878
 sale-0.873
 buyer-0.849
 Amen-0.826
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
opsy+1.431
oppy+1.376
 Remy+1.289
 bur+1.276
rig+1.250
Neg logit contributions
 digits-0.571
folk-0.563
 sale-0.551
 letters-0.502
 Amen-0.487
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
opsy+0.012
oppy+0.011
rig+0.010
chy+0.009
uffy+0.009
Neg logit contributions
 sale-0.014
folk-0.014
 digits-0.014
 customer-0.013
 Amen-0.013
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
rig+0.326
chy+0.266
 refreshing+0.261
 Remy+0.235
iqu+0.201
Neg logit contributions
 customer-0.829
 digits-0.807
 ones-0.776
 three-0.771
 Amen-0.764
Token lived
Token ID5615
Feature activation+1.69e-01

Pos logit contributions
opsy+1.364
oppy+1.311
 Remy+1.238
rig+1.228
 bur+1.190
Neg logit contributions
 digits-0.602
folk-0.600
 sale-0.562
 letters-0.552
 Amen-0.517
Token in
Token ID287
Feature activation+3.67e-02

Pos logit contributions
opsy+0.371
oppy+0.371
chy+0.342
 Remy+0.341
rig+0.333
Neg logit contributions
 digits-0.217
folk-0.214
 sale-0.206
 customer-0.200
 letters-0.189
Token to
Token ID284
Feature activation+5.97e-03

Pos logit contributions
folk+0.037
 digits+0.036
 sale+0.035
 letters+0.032
 customer+0.032
Neg logit contributions
opsy-0.056
oppy-0.055
 Remy-0.050
chy-0.049
 bur-0.049
Token play
Token ID711
Feature activation+5.70e-02

Pos logit contributions
opsy+0.013
oppy+0.013
 Remy+0.012
chy+0.012
uffy+0.011
Neg logit contributions
 digits-0.008
folk-0.008
 sale-0.008
 number-0.007
 cheering-0.007
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
opsy+0.129
oppy+0.128
 Remy+0.118
chy+0.116
 bur+0.115
Neg logit contributions
folk-0.080
 digits-0.077
 sale-0.072
 customer-0.066
 letters-0.065
Token asked
Token ID1965
Feature activation-2.37e-01

Pos logit contributions
opsy+0.083
oppy+0.082
 Remy+0.074
chy+0.073
 bur+0.072
Neg logit contributions
folk-0.058
 digits-0.056
 sale-0.053
 letters-0.049
 customer-0.048
Token Fl
Token ID1610
Feature activation+3.93e-01

Pos logit contributions
folk+0.353
 sale+0.352
 digits+0.339
 letters+0.318
 customer+0.311
Neg logit contributions
opsy-0.496
oppy-0.485
rig-0.437
chy-0.437
 bur-0.426
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
chy+0.237
 Remy+0.217
rig+0.186
 refreshing+0.161
 itch+0.127
Neg logit contributions
 digits-0.991
 sale-0.949
gu-0.936
 customer-0.931
 Amen-0.924
Token to
Token ID284
Feature activation+6.07e-03

Pos logit contributions
oppy+1.130
opsy+1.130
 Remy+1.040
chy+1.011
 bur+1.001
Neg logit contributions
folk-0.934
 digits-0.907
 sale-0.842
 customer-0.787
 letters-0.773
Token join
Token ID4654
Feature activation-4.82e-02

Pos logit contributions
opsy+0.013
oppy+0.013
 Remy+0.012
chy+0.012
 bur+0.012
Neg logit contributions
folk-0.009
 digits-0.009
 sale-0.008
 customer-0.007
 letters-0.007
Token.
Token ID13
Feature activation+6.25e-03

Pos logit contributions
folk+0.068
 digits+0.064
 sale+0.062
 letters+0.056
 customer+0.056
Neg logit contributions
opsy-0.108
oppy-0.106
chy-0.099
 Remy-0.096
 bur-0.095
Token Fl
Token ID1610
Feature activation+3.94e-01

Pos logit contributions
opsy+0.011
oppy+0.011
chy+0.009
rig+0.008
uffy+0.008
Neg logit contributions
 sale-0.012
folk-0.012
 digits-0.011
 letters-0.010
 customer-0.010
Tokenoppy
Token ID26696
Feature activation+5.65e-01

Pos logit contributions
chy+0.291
rig+0.279
 Remy+0.259
 refreshing+0.255
 Tig+0.185
Neg logit contributions
 digits-0.859
gu-0.812
 winners-0.809
 sale-0.792
ka-0.788
Token named
Token ID3706
Feature activation+6.21e-04

Pos logit contributions
opsy+0.598
oppy+0.585
chy+0.541
 Remy+0.541
 bur+0.539
Neg logit contributions
folk-0.303
 digits-0.299
 sale-0.291
 Amen-0.270
 customer-0.263
Token Fl
Token ID1610
Feature activation+3.91e-01

Pos logit contributions
opsy+0.001
oppy+0.001
rig+0.001
chy+0.001
 bur+0.001
Neg logit contributions
 sale-0.001
 customer-0.001
 digits-0.001
folk-0.001
 Robert-0.001
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
rig+0.293
chy+0.268
 refreshing+0.260
 Remy+0.204
 web+0.196
Neg logit contributions
 customer-0.932
 digits-0.878
 sale-0.873
 buyer-0.849
 Amen-0.826
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
opsy+1.431
oppy+1.376
 Remy+1.289
 bur+1.276
rig+1.250
Neg logit contributions
 digits-0.571
folk-0.563
 sale-0.551
 letters-0.502
 Amen-0.487
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
opsy+0.012
oppy+0.011
rig+0.010
chy+0.009
uffy+0.009
Neg logit contributions
 sale-0.014
folk-0.014
 digits-0.014
 customer-0.013
 Amen-0.013
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
rig+0.326
chy+0.266
 refreshing+0.261
 Remy+0.235
iqu+0.201
Neg logit contributions
 customer-0.829
 digits-0.807
 ones-0.776
 three-0.771
 Amen-0.764
Token lived
Token ID5615
Feature activation+1.69e-01

Pos logit contributions
opsy+1.364
oppy+1.311
 Remy+1.238
rig+1.228
 bur+1.190
Neg logit contributions
 digits-0.602
folk-0.600
 sale-0.562
 letters-0.552
 Amen-0.517
Token in
Token ID287
Feature activation+3.67e-02

Pos logit contributions
opsy+0.371
oppy+0.371
chy+0.342
 Remy+0.341
rig+0.333
Neg logit contributions
 digits-0.217
folk-0.214
 sale-0.206
 customer-0.200
 letters-0.189
Token a
Token ID257
Feature activation+1.58e-02

Pos logit contributions
opsy+0.099
oppy+0.097
uffy+0.092
rig+0.092
chy+0.088
Neg logit contributions
 sale-0.031
 digits-0.030
 letters-0.029
 customer-0.029
 Amen-0.028
Token modest
Token ID12949
Feature activation-1.13e-02

Pos logit contributions
opsy+0.032
oppy+0.031
rig+0.031
chy+0.030
 Remy+0.029
Neg logit contributions
 digits-0.021
 sale-0.020
 customer-0.020
 shop-0.019
 Amen-0.019
Token little
Token ID1310
Feature activation+6.98e-02

Pos logit contributions
 sale+0.017
folk+0.017
 digits+0.017
 customer+0.016
 letters+0.015
Neg logit contributions
opsy-0.022
oppy-0.022
 Remy-0.021
chy-0.021
rig-0.020
Token very
Token ID845
Feature activation-2.98e-02

Pos logit contributions
opsy+0.140
oppy+0.139
 Remy+0.128
chy+0.121
 bur+0.121
Neg logit contributions
folk-0.082
 digits-0.078
 sale-0.077
 cheering-0.069
 Amen-0.068
Token sad
Token ID6507
Feature activation+1.95e-02

Pos logit contributions
folk+0.034
 digits+0.032
 sale+0.032
 Amen+0.030
 cheering+0.030
Neg logit contributions
opsy-0.071
oppy-0.068
 Remy-0.066
chy-0.062
uffy-0.062
Token and
Token ID290
Feature activation+4.08e-02

Pos logit contributions
opsy+0.049
oppy+0.047
 Remy+0.043
rig+0.042
chy+0.041
Neg logit contributions
 sale-0.021
folk-0.020
 digits-0.019
 cheering-0.018
 customer-0.017
Token missed
Token ID6825
Feature activation+1.01e-01

Pos logit contributions
opsy+0.097
oppy+0.093
rig+0.087
uffy+0.084
 Remy+0.080
Neg logit contributions
folk-0.052
 Amen-0.046
 begged-0.045
 sale-0.045
 asked-0.044
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
opsy+0.249
oppy+0.248
rig+0.233
chy+0.218
uffy+0.217
Neg logit contributions
 sale-0.111
folk-0.103
 digits-0.097
 cheering-0.097
 letters-0.093
Tokenopsy
Token ID44522
Feature activation+5.66e-01

Pos logit contributions
rig+0.319
chy+0.290
 web+0.231
 Remy+0.207
ches+0.190
Neg logit contributions
 digits-0.826
 customer-0.826
 ones-0.813
 sale-0.806
folk-0.802
Token.
Token ID13
Feature activation+8.32e-03

Pos logit contributions
opsy+1.317
oppy+1.265
 Remy+1.176
rig+1.160
 bur+1.145
Neg logit contributions
folk-0.715
 digits-0.645
 sale-0.642
 letters-0.632
 customer-0.587
Token He
Token ID679
Feature activation-1.22e-02

Pos logit contributions
opsy+0.021
oppy+0.020
rig+0.018
 Remy+0.018
chy+0.018
Neg logit contributions
folk-0.009
 sale-0.009
 digits-0.008
 prices-0.007
 customer-0.007
Token wished
Token ID16555
Feature activation+1.37e-02

Pos logit contributions
folk+0.012
 asked+0.012
 digits+0.012
 begged+0.012
 sale+0.011
Neg logit contributions
opsy-0.031
oppy-0.030
uffy-0.028
 Remy-0.027
rig-0.027
Token he
Token ID339
Feature activation+4.36e-02

Pos logit contributions
rig+0.037
opsy+0.036
oppy+0.036
 web+0.032
uffy+0.032
Neg logit contributions
folk-0.011
 sale-0.011
 one-0.010
 them-0.010
 ones-0.009
Token had
Token ID550
Feature activation-1.17e-02

Pos logit contributions
opsy+0.112
oppy+0.109
rig+0.103
 Remy+0.100
 bur+0.100
Neg logit contributions
folk-0.048
 digits-0.041
 sale-0.039
 letters-0.037
 salesman-0.036
Tokenoppy
Token ID26696
Feature activation+5.66e-01

Pos logit contributions
chy+0.237
 Remy+0.217
rig+0.186
 refreshing+0.161
 itch+0.127
Neg logit contributions
 digits-0.991
 sale-0.949
gu-0.936
 customer-0.931
 Amen-0.924
Token to
Token ID284
Feature activation+6.07e-03

Pos logit contributions
oppy+1.130
opsy+1.130
 Remy+1.040
chy+1.011
 bur+1.001
Neg logit contributions
folk-0.934
 digits-0.907
 sale-0.842
 customer-0.787
 letters-0.773
Token join
Token ID4654
Feature activation-4.82e-02

Pos logit contributions
opsy+0.013
oppy+0.013
 Remy+0.012
chy+0.012
 bur+0.012
Neg logit contributions
folk-0.009
 digits-0.009
 sale-0.008
 customer-0.007
 letters-0.007
Token.
Token ID13
Feature activation+6.25e-03

Pos logit contributions
folk+0.068
 digits+0.064
 sale+0.062
 letters+0.056
 customer+0.056
Neg logit contributions
opsy-0.108
oppy-0.106
chy-0.099
 Remy-0.096
 bur-0.095
Token Fl
Token ID1610
Feature activation+3.94e-01

Pos logit contributions
opsy+0.011
oppy+0.011
chy+0.009
rig+0.008
uffy+0.008
Neg logit contributions
 sale-0.012
folk-0.012
 digits-0.011
 letters-0.010
 customer-0.010
Tokenoppy
Token ID26696
Feature activation+5.65e-01

Pos logit contributions
chy+0.291
rig+0.279
 Remy+0.259
 refreshing+0.255
 Tig+0.185
Neg logit contributions
 digits-0.859
gu-0.812
 winners-0.809
 sale-0.792
ka-0.788
Token thought
Token ID1807
Feature activation-1.53e-01

Pos logit contributions
opsy+1.278
oppy+1.261
 Remy+1.170
chy+1.143
 bur+1.126
Neg logit contributions
folk-0.763
 digits-0.747
 sale-0.697
 customer-0.645
 letters-0.640
Token for
Token ID329
Feature activation+1.26e-01

Pos logit contributions
 sale+0.135
 them+0.123
 one+0.110
folk+0.110
 choosing+0.104
Neg logit contributions
opsy-0.415
oppy-0.385
rig-0.360
 bur-0.346
uffy-0.343
Token a
Token ID257
Feature activation+1.72e-02

Pos logit contributions
opsy+0.225
oppy+0.224
 Remy+0.215
 bur+0.205
chy+0.203
Neg logit contributions
folk-0.240
 digits-0.229
 sale-0.204
 jury-0.200
epad-0.198
Token moment
Token ID2589
Feature activation-1.41e-01

Pos logit contributions
opsy+0.039
oppy+0.039
chy+0.036
 Remy+0.036
 bur+0.035
Neg logit contributions
folk-0.025
 digits-0.023
 sale-0.021
 letters-0.020
 prices-0.019
Token and
Token ID290
Feature activation+4.01e-02

Pos logit contributions
folk+0.217
 digits+0.210
 sale+0.200
 customer+0.186
 letters+0.183
Neg logit contributions
opsy-0.297
oppy-0.294
 Remy-0.268
chy-0.263
 bur-0.263
Token named
Token ID3706
Feature activation+5.46e-02

Pos logit contributions
opsy+0.217
oppy+0.215
 Remy+0.201
 bur+0.193
chy+0.189
Neg logit contributions
folk-0.139
 digits-0.136
 sale-0.129
 customer-0.117
 letters-0.116
Token Fl
Token ID1610
Feature activation+4.14e-01

Pos logit contributions
opsy+0.115
oppy+0.111
 bur+0.102
chy+0.100
rig+0.098
Neg logit contributions
folk-0.085
 digits-0.080
 sale-0.080
 letters-0.072
 customer-0.071
Tokenopsy
Token ID44522
Feature activation+5.78e-01

Pos logit contributions
chy+0.403
 bur+0.374
opsy+0.373
 Remy+0.371
rig+0.362
Neg logit contributions
folk-0.962
 sale-0.936
 digits-0.935
 customer-0.928
 Amen-0.895
Token.
Token ID13
Feature activation+4.98e-03

Pos logit contributions
opsy+1.374
oppy+1.327
rig+1.275
 bur+1.243
 Remy+1.227
Neg logit contributions
folk-0.650
 digits-0.593
 sale-0.571
 Amen-0.536
 letters-0.535
Token Fl
Token ID1610
Feature activation+3.95e-01

Pos logit contributions
opsy+0.008
oppy+0.008
chy+0.007
 Remy+0.007
 bur+0.007
Neg logit contributions
folk-0.010
 digits-0.010
 sale-0.009
 customer-0.009
 Amen-0.009
Tokenopsy
Token ID44522
Feature activation+5.65e-01

Pos logit contributions
chy+0.228
rig+0.165
 Remy+0.137
ches+0.136
 bur+0.127
Neg logit contributions
folk-1.030
 digits-1.024
 customer-1.002
 winners-0.999
 sale-0.998
Token loved
Token ID6151
Feature activation+2.92e-02

Pos logit contributions
opsy+1.256
oppy+1.231
rig+1.124
 Remy+1.121
chy+1.087
Neg logit contributions
folk-0.751
 digits-0.697
 sale-0.659
 letters-0.624
 Amen-0.608
Token to
Token ID284
Feature activation-4.62e-03

Pos logit contributions
oppy+0.068
opsy+0.068
chy+0.061
uffy+0.059
 Remy+0.059
Neg logit contributions
 sale-0.036
 digits-0.036
folk-0.035
 letters-0.033
 customer-0.032
Token hop
Token ID1725
Feature activation+2.92e-01

Pos logit contributions
 digits+0.007
folk+0.007
 sale+0.007
 letters+0.006
 Amen+0.006
Neg logit contributions
opsy-0.009
oppy-0.009
 Remy-0.008
uffy-0.008
chy-0.008
Token and
Token ID290
Feature activation+2.50e-02

Pos logit contributions
opsy+0.802
oppy+0.762
uffy+0.696
iqu+0.681
 Remy+0.663
Neg logit contributions
 sale-0.250
folk-0.217
 one-0.216
 letters-0.199
 ones-0.199
Token play
Token ID711
Feature activation+3.95e-02

Pos logit contributions
opsy+0.049
oppy+0.048
uffy+0.044
rig+0.044
chy+0.042
Neg logit contributions
folk-0.037
 digits-0.036
 Amen-0.035
 sale-0.035
 number-0.033
Token,
Token ID11
Feature activation-3.14e-02

Pos logit contributions
folk+0.052
 sale+0.050
 digits+0.046
 customer+0.045
 Amen+0.039
Neg logit contributions
opsy-0.133
oppy-0.128
rig-0.126
 bur-0.124
chy-0.121
Token whenever
Token ID8797
Feature activation+1.16e-01

Pos logit contributions
folk+0.039
 customer+0.035
 digits+0.035
 sale+0.035
 cheering+0.031
Neg logit contributions
opsy-0.073
oppy-0.071
 bur-0.068
rig-0.067
chy-0.066
Token Anna
Token ID11735
Feature activation-1.35e-02

Pos logit contributions
opsy+0.269
oppy+0.261
rig+0.245
chy+0.244
 bur+0.244
Neg logit contributions
folk-0.148
 digits-0.140
 sale-0.137
 customer-0.131
 Amen-0.123
Token took
Token ID1718
Feature activation-1.46e-02

Pos logit contributions
folk+0.016
 digits+0.015
 sale+0.014
 customer+0.014
 number+0.013
Neg logit contributions
opsy-0.031
oppy-0.031
 Remy-0.029
chy-0.028
rig-0.027
Token Fl
Token ID1610
Feature activation+3.91e-01

Pos logit contributions
folk+0.023
 digits+0.023
 sale+0.021
 customer+0.020
 letters+0.020
Neg logit contributions
opsy-0.030
oppy-0.029
 Remy-0.027
chy-0.026
 bur-0.026
Tokenopsy
Token ID44522
Feature activation+5.65e-01

Pos logit contributions
chy+0.286
rig+0.204
 Remy+0.183
 web+0.152
 refreshing+0.126
Neg logit contributions
 customer-0.966
 digits-0.959
 sale-0.949
 ones-0.919
folk-0.916
Token for
Token ID329
Feature activation+1.25e-01

Pos logit contributions
opsy+1.349
oppy+1.270
chy+1.182
 Remy+1.179
rig+1.173
Neg logit contributions
folk-0.672
 sale-0.658
 letters-0.642
 digits-0.623
 customer-0.607
Token a
Token ID257
Feature activation+1.50e-02

Pos logit contributions
opsy+0.240
oppy+0.239
 Remy+0.225
 bur+0.216
chy+0.215
Neg logit contributions
folk-0.217
 digits-0.209
 sale-0.189
 customer-0.180
epad-0.179
Token walk
Token ID2513
Feature activation+2.02e-01

Pos logit contributions
opsy+0.028
oppy+0.027
 Remy+0.025
chy+0.024
 bur+0.024
Neg logit contributions
 digits-0.026
folk-0.026
 sale-0.025
 customer-0.024
epad-0.022
Token,
Token ID11
Feature activation-3.04e-02

Pos logit contributions
opsy+0.437
oppy+0.432
 Remy+0.401
chy+0.391
 bur+0.389
Neg logit contributions
folk-0.302
 digits-0.293
 sale-0.273
 customer-0.252
 letters-0.249
Token she
Token ID673
Feature activation+8.58e-02

Pos logit contributions
folk+0.045
 digits+0.042
 sale+0.041
 customer+0.040
 cheering+0.040
Neg logit contributions
opsy-0.064
oppy-0.063
rig-0.057
chy-0.056
 bur-0.055
Token hurt
Token ID5938
Feature activation+1.27e-01

Pos logit contributions
folk+0.076
 digits+0.072
 sale+0.069
 letters+0.066
 winners+0.065
Neg logit contributions
opsy-0.110
oppy-0.105
 Remy-0.098
 bur-0.094
rig-0.092
Token my
Token ID616
Feature activation+1.61e-02

Pos logit contributions
opsy+0.250
oppy+0.247
 Remy+0.233
 bur+0.223
chy+0.221
Neg logit contributions
folk-0.214
 digits-0.210
 sale-0.193
 customer-0.183
epad-0.181
Token ear
Token ID1027
Feature activation-1.15e-01

Pos logit contributions
oppy+0.033
opsy+0.033
 Remy+0.031
chy+0.030
rig+0.029
Neg logit contributions
 digits-0.022
 sale-0.022
folk-0.021
 letters-0.021
 customer-0.021
Token."
Token ID526
Feature activation-1.21e-01

Pos logit contributions
folk+0.154
 digits+0.150
 sale+0.139
 customer+0.127
 letters+0.126
Neg logit contributions
opsy-0.264
oppy-0.261
 Remy-0.245
 bur-0.238
chy-0.236
Token Fl
Token ID1610
Feature activation+3.93e-01

Pos logit contributions
folk+0.177
 +0.168
 sale+0.165
 digits+0.163
 Amen+0.157
Neg logit contributions
opsy-0.235
oppy-0.224
rig-0.221
chy-0.221
iqu-0.195
Tokenoppy
Token ID26696
Feature activation+5.65e-01

Pos logit contributions
chy+0.324
rig+0.289
 refreshing+0.222
 cob+0.209
 web+0.181
Neg logit contributions
 customer-0.842
 digits-0.838
folk-0.829
 ones-0.818
 buyer-0.816
Token apologized
Token ID22893
Feature activation-5.73e-03

Pos logit contributions
opsy+1.227
oppy+1.216
 Remy+1.122
chy+1.091
 bur+1.083
Neg logit contributions
folk-0.811
 digits-0.791
 sale-0.737
 letters-0.688
 customer-0.677
Token and
Token ID290
Feature activation+4.18e-02

Pos logit contributions
folk+0.007
 sale+0.007
 digits+0.007
 letters+0.007
 customer+0.006
Neg logit contributions
opsy-0.013
oppy-0.013
chy-0.012
 Remy-0.012
 bur-0.012
Token they
Token ID484
Feature activation+4.48e-02

Pos logit contributions
opsy+0.097
oppy+0.097
rig+0.095
chy+0.094
uffy+0.089
Neg logit contributions
folk-0.044
 begged-0.041
 sale-0.040
 salesman-0.040
 asked-0.040
Token continued
Token ID3767
Feature activation+1.71e-01

Pos logit contributions
opsy+0.103
oppy+0.103
rig+0.101
 Remy+0.094
chy+0.093
Neg logit contributions
folk-0.049
 digits-0.045
 sale-0.044
 numbered-0.041
 letters-0.040
Token to
Token ID284
Feature activation+8.80e-03

Pos logit contributions
opsy+0.374
oppy+0.370
 Remy+0.339
chy+0.335
 bur+0.329
Neg logit contributions
folk-0.246
 digits-0.243
 sale-0.230
 customer-0.210
 letters-0.210
Token.
Token ID13
Feature activation+6.37e-03

Pos logit contributions
opsy+0.227
oppy+0.219
 bur+0.200
 Remy+0.198
rig+0.192
Neg logit contributions
 sale-0.098
folk-0.097
 digits-0.090
 letters-0.083
epad-0.083
Token The
Token ID383
Feature activation+1.04e-01

Pos logit contributions
opsy+0.013
oppy+0.012
 Remy+0.011
chy+0.011
 bur+0.011
Neg logit contributions
folk-0.011
 digits-0.010
 sale-0.010
 customer-0.009
 letters-0.009
Token car
Token ID1097
Feature activation-7.85e-02

Pos logit contributions
opsy+0.206
oppy+0.204
 Remy+0.187
chy+0.182
 bur+0.180
Neg logit contributions
folk-0.178
 digits-0.173
 sale-0.164
 customer-0.153
 letters-0.151
Token hit
Token ID2277
Feature activation+1.58e-02

Pos logit contributions
folk+0.124
 digits+0.117
 sale+0.114
 letters+0.104
 customer+0.101
Neg logit contributions
opsy-0.169
oppy-0.166
 Remy-0.152
 bur-0.143
chy-0.141
Token Fl
Token ID1610
Feature activation+3.91e-01

Pos logit contributions
oppy+0.030
rig+0.029
opsy+0.028
uffy+0.024
chy+0.024
Neg logit contributions
 sale-0.025
 them-0.025
 one-0.025
folk-0.025
 letters-0.024
Tokenopsy
Token ID44522
Feature activation+5.65e-01

Pos logit contributions
chy+0.321
rig+0.294
 Remy+0.205
 refreshing+0.193
othe+0.174
Neg logit contributions
 ones-0.834
 digits-0.805
 customer-0.798
gu-0.784
be-0.779
Token and
Token ID290
Feature activation+3.99e-02

Pos logit contributions
opsy+1.375
oppy+1.329
 Remy+1.238
uffy+1.140
rig+1.136
Neg logit contributions
folk-0.664
 sale-0.647
 digits-0.643
 letters-0.591
 number-0.564
Token she
Token ID673
Feature activation+8.56e-02

Pos logit contributions
oppy+0.076
opsy+0.076
rig+0.074
uffy+0.063
chy+0.062
Neg logit contributions
folk-0.068
 sale-0.066
 letters-0.060
 digits-0.060
 begged-0.058
Token was
Token ID373
Feature activation+6.10e-02

Pos logit contributions
opsy+0.156
oppy+0.145
rig+0.137
 Remy+0.136
uffy+0.116
Neg logit contributions
folk-0.156
 digits-0.150
 sale-0.143
 letters-0.135
 cheering-0.133
Token gone
Token ID3750
Feature activation+5.71e-02

Pos logit contributions
opsy+0.127
oppy+0.124
 Remy+0.114
 bur+0.105
uffy+0.104
Neg logit contributions
folk-0.097
 digits-0.093
 sale-0.091
 cheering-0.084
 letters-0.082
Token.
Token ID13
Feature activation+7.49e-03

Pos logit contributions
opsy+0.136
oppy+0.131
 Remy+0.124
rig+0.114
uffy+0.111
Neg logit contributions
folk-0.069
 sale-0.069
 digits-0.066
epad-0.060
 cheering-0.059
Token smooth
Token ID7209
Feature activation+9.63e-02

Pos logit contributions
 digits+0.145
folk+0.145
 sale+0.136
 letters+0.131
 customer+0.125
Neg logit contributions
opsy-0.215
oppy-0.214
 Remy-0.192
 bur-0.187
uffy-0.186
Token and
Token ID290
Feature activation+3.89e-02

Pos logit contributions
opsy+0.196
oppy+0.194
 Remy+0.178
 bur+0.172
chy+0.171
Neg logit contributions
folk-0.155
 digits-0.151
 sale-0.142
 letters-0.132
 customer-0.131
Token shiny
Token ID22441
Feature activation+1.21e-02

Pos logit contributions
opsy+0.073
oppy+0.072
 Remy+0.065
 bur+0.063
chy+0.063
Neg logit contributions
folk-0.068
 digits-0.067
 sale-0.063
 letters-0.059
 customer-0.059
Token.
Token ID13
Feature activation+4.37e-03

Pos logit contributions
opsy+0.022
oppy+0.022
chy+0.020
 Remy+0.020
 bur+0.020
Neg logit contributions
folk-0.022
 digits-0.021
 sale-0.020
 customer-0.019
 jury-0.019
Token Fl
Token ID1610
Feature activation+3.94e-01

Pos logit contributions
opsy+0.009
oppy+0.009
chy+0.008
rig+0.008
 bur+0.008
Neg logit contributions
folk-0.006
 digits-0.006
 sale-0.006
 Amen-0.006
 -0.005
Tokenoppy
Token ID26696
Feature activation+5.64e-01

Pos logit contributions
rig+0.325
chy+0.290
 Remy+0.279
 refreshing+0.259
ches+0.209
Neg logit contributions
 digits-0.834
 customer-0.792
 winners-0.785
ka-0.781
 ones-0.775
Token was
Token ID373
Feature activation+6.18e-02

Pos logit contributions
opsy+1.244
oppy+1.231
 Remy+1.140
chy+1.100
 bur+1.082
Neg logit contributions
folk-0.779
 digits-0.770
 sale-0.723
 letters-0.668
 customer-0.657
Token so
Token ID523
Feature activation-9.14e-02

Pos logit contributions
opsy+0.123
oppy+0.115
 Remy+0.114
chy+0.112
 bur+0.108
Neg logit contributions
folk-0.110
 digits-0.104
 sale-0.096
 jury-0.091
bench-0.090
Token happy
Token ID3772
Feature activation-6.12e-02

Pos logit contributions
 digits+0.097
folk+0.097
 sale+0.085
 cheering+0.079
 letters+0.079
Neg logit contributions
oppy-0.229
opsy-0.228
 Remy-0.213
 bur-0.211
chy-0.209
Token to
Token ID284
Feature activation+7.19e-03

Pos logit contributions
 sale+0.071
 digits+0.070
folk+0.069
 cheering+0.063
 letters+0.063
Neg logit contributions
opsy-0.146
oppy-0.144
chy-0.133
rig-0.128
 bur-0.126
Token have
Token ID423
Feature activation-7.49e-02

Pos logit contributions
opsy+0.015
oppy+0.015
 Remy+0.014
chy+0.014
 bur+0.014
Neg logit contributions
folk-0.012
 digits-0.011
 sale-0.010
 prices-0.010
 letters-0.010
Token too
Token ID1165
Feature activation-8.54e-02

Pos logit contributions
folk+0.184
 digits+0.182
 sale+0.169
 letters+0.156
 customer+0.155
Neg logit contributions
opsy-0.263
oppy-0.260
 Remy-0.239
 bur-0.232
chy-0.232
Token.
Token ID13
Feature activation+5.59e-03

Pos logit contributions
 digits+0.100
 sale+0.096
folk+0.094
 letters+0.083
 customer+0.081
Neg logit contributions
opsy-0.203
oppy-0.200
 Remy-0.184
 bur-0.179
chy-0.178
Token
Token ID198
Feature activation+3.30e-02

Pos logit contributions
opsy+0.014
oppy+0.014
chy+0.014
rig+0.013
uffy+0.013
Neg logit contributions
 digits-0.005
folk-0.005
 sale-0.005
 letters-0.004
 Amen-0.004
Token
Token ID198
Feature activation+3.27e-02

Pos logit contributions
opsy+0.075
oppy+0.073
chy+0.068
 bur+0.068
 Remy+0.067
Neg logit contributions
 digits-0.043
folk-0.042
 sale-0.040
 customer-0.036
 Amen-0.036
TokenH
Token ID39
Feature activation+1.34e-01

Pos logit contributions
opsy+0.069
oppy+0.067
chy+0.062
uffy+0.062
 bur+0.061
Neg logit contributions
 digits-0.045
 sale-0.042
folk-0.042
 customer-0.039
 salesman-0.038
Tokenoppy
Token ID26696
Feature activation+5.64e-01

Pos logit contributions
 bur+0.074
rig+0.072
 Remy+0.066
opsy+0.063
 refreshing+0.054
Neg logit contributions
 digits-0.325
epad-0.320
bench-0.317
 sale-0.314
 customer-0.301
Token hopped
Token ID45230
Feature activation+2.20e-01

Pos logit contributions
opsy+1.272
oppy+1.257
 Remy+1.162
chy+1.135
 bur+1.103
Neg logit contributions
folk-0.766
 digits-0.754
 sale-0.694
 letters-0.650
 customer-0.629
Token and
Token ID290
Feature activation+3.85e-02

Pos logit contributions
opsy+0.516
oppy+0.516
uffy+0.458
chy+0.456
 Remy+0.444
Neg logit contributions
 digits-0.271
folk-0.271
 sale-0.260
 customer-0.244
 salesman-0.238
Token hopped
Token ID45230
Feature activation+2.20e-01

Pos logit contributions
opsy+0.077
oppy+0.075
chy+0.067
uffy+0.066
rig+0.065
Neg logit contributions
folk-0.062
 digits-0.062
 sale-0.057
 letters-0.054
 cheering-0.054
Token,
Token ID11
Feature activation-2.83e-02

Pos logit contributions
opsy+0.520
oppy+0.514
uffy+0.459
chy+0.448
 bur+0.446
Neg logit contributions
folk-0.275
 digits-0.274
 sale-0.265
 customer-0.237
 cheering-0.235
Token but
Token ID475
Feature activation-5.82e-03

Pos logit contributions
folk+0.036
 digits+0.035
 sale+0.032
 cheering+0.031
 letters+0.029
Neg logit contributions
oppy-0.068
opsy-0.067
uffy-0.059
 Remy-0.059
chy-0.057
Tokenman
Token ID805
Feature activation-1.98e-01

Pos logit contributions
oppy+0.489
opsy+0.487
 bur+0.449
 Remy+0.439
rig+0.433
Neg logit contributions
folk-0.661
boxes-0.601
 sale-0.592
 digits-0.584
 customer-0.579
Token back
Token ID736
Feature activation+1.45e-02

Pos logit contributions
folk+0.304
 digits+0.298
 sale+0.279
 letters+0.262
 customer+0.258
Neg logit contributions
opsy-0.417
oppy-0.409
 Remy-0.379
 bur-0.366
chy-0.363
Token together
Token ID1978
Feature activation-1.23e-01

Pos logit contributions
opsy+0.032
oppy+0.031
 Remy+0.029
chy+0.027
 bur+0.027
Neg logit contributions
folk-0.022
 digits-0.021
 sale-0.020
 letters-0.018
 customer-0.018
Token.
Token ID13
Feature activation+4.38e-03

Pos logit contributions
folk+0.183
 digits+0.177
 sale+0.169
 customer+0.154
 letters+0.153
Neg logit contributions
opsy-0.268
oppy-0.265
 Remy-0.243
 bur-0.235
chy-0.235
Token Fl
Token ID1610
Feature activation+3.90e-01

Pos logit contributions
opsy+0.009
oppy+0.009
chy+0.008
rig+0.007
 Remy+0.007
Neg logit contributions
folk-0.007
 sale-0.007
 digits-0.007
 customer-0.006
 Amen-0.006
Tokenopsy
Token ID44522
Feature activation+5.64e-01

Pos logit contributions
chy+0.354
rig+0.309
 web+0.279
 cob+0.241
 rubble+0.236
Neg logit contributions
 ones-0.778
 digits-0.771
ams-0.768
be-0.763
 customer-0.746
Token was
Token ID373
Feature activation+5.87e-02

Pos logit contributions
opsy+1.233
oppy+1.215
 Remy+1.126
chy+1.073
rig+1.063
Neg logit contributions
folk-0.794
 digits-0.779
 sale-0.702
 letters-0.676
 cheering-0.640
Token so
Token ID523
Feature activation-9.47e-02

Pos logit contributions
opsy+0.119
oppy+0.115
chy+0.110
 Remy+0.109
 bur+0.106
Neg logit contributions
folk-0.097
 digits-0.094
 sale-0.086
 jury-0.082
 prices-0.080
Token brave
Token ID14802
Feature activation+1.07e-01

Pos logit contributions
folk+0.120
 digits+0.117
 sale+0.106
 customer+0.098
 letters+0.096
Neg logit contributions
opsy-0.225
oppy-0.223
 Remy-0.209
 bur-0.204
chy-0.203
Token and
Token ID290
Feature activation+3.59e-02

Pos logit contributions
opsy+0.225
oppy+0.220
 Remy+0.196
chy+0.194
 bur+0.193
Neg logit contributions
folk-0.171
 digits-0.164
 sale-0.156
 customer-0.145
 letters-0.145
Token worked
Token ID3111
Feature activation-6.18e-02

Pos logit contributions
oppy+0.077
opsy+0.077
chy+0.067
 Remy+0.067
uffy+0.067
Neg logit contributions
folk-0.052
 digits-0.051
 sale-0.048
 letters-0.046
 customer-0.046
Token bush
Token ID24484
Feature activation+1.99e-01

Pos logit contributions
opsy+0.030
oppy+0.029
 Remy+0.026
uffy+0.025
chy+0.025
Neg logit contributions
 digits-0.026
 sale-0.026
folk-0.026
 customer-0.024
 letters-0.024
Token.
Token ID13
Feature activation+5.12e-03

Pos logit contributions
opsy+0.436
oppy+0.429
 Remy+0.395
chy+0.382
 bur+0.378
Neg logit contributions
folk-0.292
 digits-0.283
 sale-0.276
 customer-0.249
 letters-0.244
Token
Token ID198
Feature activation+3.13e-02

Pos logit contributions
opsy+0.012
oppy+0.012
chy+0.011
rig+0.011
 bur+0.011
Neg logit contributions
 digits-0.006
folk-0.006
 sale-0.005
 customer-0.005
 Amen-0.005
Token
Token ID198
Feature activation+3.09e-02

Pos logit contributions
opsy+0.087
chy+0.084
oppy+0.084
 bur+0.080
rig+0.077
Neg logit contributions
 digits-0.020
 -0.018
 sale-0.017
John-0.016
 Amen-0.016
TokenP
Token ID47
Feature activation+5.98e-02

Pos logit contributions
opsy+0.070
chy+0.068
oppy+0.068
rig+0.066
 bur+0.063
Neg logit contributions
 digits-0.038
 sale-0.033
John-0.033
 customer-0.033
folk-0.032
Tokenoppy
Token ID26696
Feature activation+5.64e-01

Pos logit contributions
chy+0.062
opsy+0.050
 refreshing+0.043
 bur+0.042
rig+0.039
Neg logit contributions
 digits-0.149
 customer-0.139
 sale-0.138
iers-0.137
 jury-0.131
Token cries
Token ID24691
Feature activation+2.05e-01

Pos logit contributions
opsy+1.277
oppy+1.219
 Remy+1.115
chy+1.079
rig+1.053
Neg logit contributions
 digits-0.801
folk-0.792
 sale-0.750
 letters-0.732
 prices-0.685
Token.
Token ID13
Feature activation+5.17e-03

Pos logit contributions
opsy+0.548
oppy+0.521
rig+0.487
uffy+0.458
chy+0.451
Neg logit contributions
 digits-0.199
 letters-0.194
folk-0.192
 sale-0.186
 cheering-0.178
Token She
Token ID1375
Feature activation+3.15e-02

Pos logit contributions
opsy+0.012
oppy+0.012
rig+0.011
chy+0.011
 bur+0.010
Neg logit contributions
 digits-0.006
 sale-0.006
folk-0.006
 customer-0.005
 letters-0.005
Token has
Token ID468
Feature activation+4.19e-02

Pos logit contributions
opsy+0.081
oppy+0.077
rig+0.069
 Remy+0.068
uffy+0.066
Neg logit contributions
 digits-0.033
 letters-0.033
 number-0.030
 begged-0.028
 prices-0.026
Token no
Token ID645
Feature activation-5.67e-02

Pos logit contributions
opsy+0.090
oppy+0.088
 Remy+0.081
chy+0.079
 bur+0.078
Neg logit contributions
folk-0.063
 digits-0.062
 sale-0.059
 letters-0.054
 customer-0.054
Token!
Token ID0
Feature activation+1.05e-01

Pos logit contributions
opsy+0.353
oppy+0.345
 Remy+0.326
 bur+0.324
chy+0.318
Neg logit contributions
folk-0.219
 digits-0.214
 sale-0.199
 letters-0.184
 cheering-0.178
Token Be
Token ID1355
Feature activation-5.23e-02

Pos logit contributions
opsy+0.221
oppy+0.217
 Remy+0.201
chy+0.200
 bur+0.199
Neg logit contributions
folk-0.158
 digits-0.152
 sale-0.144
 customer-0.133
 letters-0.130
Token careful
Token ID8161
Feature activation+4.67e-02

Pos logit contributions
folk+0.098
 digits+0.094
 sale+0.088
 salesman+0.082
 customer+0.082
Neg logit contributions
opsy-0.096
oppy-0.095
 Remy-0.087
chy-0.085
 bur-0.083
Token,
Token ID11
Feature activation-2.86e-02

Pos logit contributions
opsy+0.097
oppy+0.096
 Remy+0.089
chy+0.087
 bur+0.086
Neg logit contributions
folk-0.074
 digits-0.072
 sale-0.067
 customer-0.062
 letters-0.061
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
 sale+0.042
folk+0.041
 letters+0.038
 customer+0.037
 digits+0.037
Neg logit contributions
opsy-0.058
oppy-0.057
rig-0.052
uffy-0.049
chy-0.048
Tokenoppy
Token ID26696
Feature activation+5.64e-01

Pos logit contributions
chy+0.291
rig+0.280
 cob+0.223
 web+0.215
 refreshing+0.209
Neg logit contributions
 customer-0.820
 ones-0.815
 sale-0.813
 digits-0.813
 winners-0.779
Token.
Token ID13
Feature activation+7.48e-03

Pos logit contributions
opsy+1.323
oppy+1.290
 Remy+1.212
 bur+1.187
chy+1.155
Neg logit contributions
folk-0.710
 digits-0.690
 sale-0.653
 letters-0.593
 customer-0.584
Token You
Token ID921
Feature activation-5.12e-02

Pos logit contributions
opsy+0.017
oppy+0.016
chy+0.015
 Remy+0.015
 bur+0.015
Neg logit contributions
folk-0.011
 digits-0.010
 sale-0.009
 Amen-0.009
 customer-0.009
Token hurt
Token ID5938
Feature activation+1.27e-01

Pos logit contributions
folk+0.076
 digits+0.072
 sale+0.069
 letters+0.066
 winners+0.065
Neg logit contributions
opsy-0.110
oppy-0.105
 Remy-0.098
 bur-0.094
rig-0.092
Token my
Token ID616
Feature activation+1.61e-02

Pos logit contributions
opsy+0.250
oppy+0.247
 Remy+0.233
 bur+0.223
chy+0.221
Neg logit contributions
folk-0.214
 digits-0.210
 sale-0.193
 customer-0.183
epad-0.181
Token ear
Token ID1027
Feature activation-1.15e-01

Pos logit contributions
oppy+0.033
opsy+0.033
 Remy+0.031
chy+0.030
rig+0.029
Neg logit contributions
 digits-0.022
 sale-0.022
folk-0.021
 letters-0.021
 customer-0.021
Token
Token ID198
Feature activation+2.88e-02

Pos logit contributions
opsy+0.060
oppy+0.059
 Remy+0.054
chy+0.053
 bur+0.053
Neg logit contributions
folk-0.047
 digits-0.046
 sale-0.043
 customer-0.040
 letters-0.039
TokenOne
Token ID3198
Feature activation-1.28e-01

Pos logit contributions
opsy+0.073
oppy+0.073
 Remy+0.068
chy+0.066
 bur+0.066
Neg logit contributions
folk-0.032
 digits-0.031
 sale-0.028
 customer-0.025
 letters-0.025
Token day
Token ID1110
Feature activation+4.13e-03

Pos logit contributions
 one+0.051
 color+0.040
 three+0.033
 minute+0.029
 3+0.016
Neg logit contributions
oppy-0.378
iqu-0.372
uffy-0.362
opsy-0.357
istered-0.353
Token,
Token ID11
Feature activation-2.97e-02

Pos logit contributions
opsy+0.011
oppy+0.010
rig+0.010
chy+0.010
 bur+0.010
Neg logit contributions
folk-0.004
 digits-0.004
 sale-0.004
 customer-0.003
 letters-0.003
Token Fl
Token ID1610
Feature activation+3.89e-01

Pos logit contributions
 sale+0.056
folk+0.055
 customer+0.054
 digits+0.053
 one+0.052
Neg logit contributions
opsy-0.047
oppy-0.046
rig-0.046
 bur-0.040
chy-0.040
Tokenopsy
Token ID44522
Feature activation+5.63e-01

Pos logit contributions
chy+0.414
rig+0.346
 rubble+0.331
ches+0.307
 webs+0.285
Neg logit contributions
 digits-0.699
 ones-0.686
 customer-0.685
 three-0.673
be-0.665
Token hopped
Token ID45230
Feature activation+2.19e-01

Pos logit contributions
opsy+1.500
oppy+1.460
rig+1.369
chy+1.367
 Remy+1.356
Neg logit contributions
folk-0.487
 digits-0.479
 sale-0.424
 asked-0.417
 letters-0.396
Token up
Token ID510
Feature activation+1.01e-01

Pos logit contributions
opsy+0.549
oppy+0.542
uffy+0.485
 Remy+0.465
 bur+0.452
Neg logit contributions
folk-0.245
 sale-0.243
 digits-0.235
 letters-0.218
 cheering-0.217
Token to
Token ID284
Feature activation+4.92e-03

Pos logit contributions
opsy+0.244
oppy+0.241
 Remy+0.212
uffy+0.206
chy+0.206
Neg logit contributions
 sale-0.129
folk-0.123
 digits-0.121
 customer-0.111
bench-0.110
Token the
Token ID262
Feature activation+4.07e-02

Pos logit contributions
opsy+0.012
oppy+0.012
chy+0.012
uffy+0.012
rig+0.012
Neg logit contributions
 sale-0.005
 digits-0.005
 customer-0.004
 number-0.004
 one-0.004
Token gate
Token ID8946
Feature activation+2.84e-03

Pos logit contributions
oppy+0.088
opsy+0.083
uffy+0.075
rig+0.074
 Remy+0.073
Neg logit contributions
 sale-0.060
 customer-0.057
 number-0.056
 letters-0.055
 digits-0.055
Token might
Token ID1244
Feature activation+1.72e-01

Pos logit contributions
folk+0.072
 digits+0.068
 sale+0.066
 number+0.064
 winners+0.062
Neg logit contributions
opsy-0.121
oppy-0.110
 Remy-0.106
rig-0.103
 bur-0.103
Token get
Token ID651
Feature activation+1.35e-02

Pos logit contributions
opsy+0.420
oppy+0.407
uffy+0.380
rig+0.368
ilo+0.349
Neg logit contributions
 sale-0.191
 number-0.179
 one-0.163
 cheering-0.163
 winners-0.154
Token hurt
Token ID5938
Feature activation+1.24e-01

Pos logit contributions
opsy+0.028
oppy+0.027
 Remy+0.024
rig+0.023
chy+0.023
Neg logit contributions
 digits-0.020
folk-0.020
 letters-0.019
 sale-0.019
 cheering-0.019
Token."
Token ID526
Feature activation-1.23e-01

Pos logit contributions
opsy+0.268
oppy+0.267
 Remy+0.251
chy+0.244
 bur+0.242
Neg logit contributions
folk-0.181
 digits-0.178
 sale-0.162
 customer-0.152
 letters-0.148
Token Fl
Token ID1610
Feature activation+3.90e-01

Pos logit contributions
folk+0.226
 sale+0.225
 digits+0.218
 prices+0.199
 Amen+0.197
Neg logit contributions
opsy-0.214
oppy-0.207
chy-0.182
rig-0.173
 bur-0.167
Tokenopsy
Token ID44522
Feature activation+5.63e-01

Pos logit contributions
chy+0.375
rig+0.296
ches+0.245
 webs+0.217
 web+0.213
Neg logit contributions
 digits-0.835
 customer-0.800
 begged-0.777
"-0.775
 ones-0.769
Token listened
Token ID16399
Feature activation-7.76e-02

Pos logit contributions
opsy+1.247
oppy+1.231
 Remy+1.123
chy+1.102
 bur+1.085
Neg logit contributions
folk-0.743
 digits-0.725
 sale-0.667
 letters-0.638
 begged-0.626
Token to
Token ID284
Feature activation+4.96e-03

Pos logit contributions
folk+0.126
 digits+0.124
 sale+0.116
 customer+0.108
 letters+0.107
Neg logit contributions
opsy-0.157
oppy-0.155
 Remy-0.143
 bur-0.138
chy-0.137
Token her
Token ID607
Feature activation+2.32e-02

Pos logit contributions
oppy+0.013
opsy+0.013
rig+0.013
uffy+0.012
chy+0.012
Neg logit contributions
 them-0.004
 sale-0.004
folk-0.004
 one-0.003
 cheering-0.003
Token friends
Token ID2460
Feature activation-5.31e-02

Pos logit contributions
oppy+0.061
opsy+0.060
chy+0.057
 Remy+0.056
rig+0.054
Neg logit contributions
 digits-0.021
 sale-0.019
 letters-0.019
 customer-0.018
 number-0.017
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
folk+0.075
 digits+0.070
 sale+0.070
 customer+0.062
 cheering+0.062
Neg logit contributions
opsy-0.120
oppy-0.118
 Remy-0.107
chy-0.105
 bur-0.104
Token a
Token ID257
Feature activation+1.39e-02

Pos logit contributions
folk+0.198
 digits+0.195
 sale+0.191
 letters+0.185
 customer+0.180
Neg logit contributions
opsy-0.278
oppy-0.272
chy-0.251
rig-0.249
 Remy-0.238
Token past
Token ID1613
Feature activation-1.27e-01

Pos logit contributions
opsy+0.025
oppy+0.025
 Remy+0.023
chy+0.023
 bur+0.021
Neg logit contributions
 digits-0.023
 sale-0.023
 customer-0.022
folk-0.022
 letters-0.022
Tokenel
Token ID417
Feature activation+6.17e-02

Pos logit contributions
folk+0.192
 digits+0.188
 sale+0.179
 letters+0.173
 customer+0.169
Neg logit contributions
opsy-0.259
oppy-0.258
chy-0.237
 Remy-0.231
rig-0.230
Token for
Token ID329
Feature activation+1.24e-01

Pos logit contributions
oppy+0.122
opsy+0.122
 Remy+0.112
 bur+0.108
chy+0.107
Neg logit contributions
folk-0.097
 digits-0.096
 sale-0.092
 letters-0.088
 customer-0.087
Token Fl
Token ID1610
Feature activation+3.92e-01

Pos logit contributions
opsy+0.232
oppy+0.229
chy+0.209
rig+0.203
 Remy+0.200
Neg logit contributions
folk-0.215
 digits-0.210
 sale-0.208
 customer-0.192
 letters-0.190
Tokenoppy
Token ID26696
Feature activation+5.63e-01

Pos logit contributions
rig+0.331
chy+0.315
 Remy+0.309
 refreshing+0.273
 Roc+0.217
Neg logit contributions
 digits-0.831
 sale-0.827
 customer-0.823
gu-0.782
acher-0.780
Token to
Token ID284
Feature activation+5.28e-03

Pos logit contributions
opsy+1.314
oppy+1.264
 Remy+1.164
uffy+1.122
rig+1.117
Neg logit contributions
 sale-0.730
folk-0.709
 digits-0.691
 letters-0.652
 customer-0.651
Token eat
Token ID4483
Feature activation+1.09e-01

Pos logit contributions
opsy+0.011
oppy+0.011
uffy+0.010
chy+0.010
rig+0.010
Neg logit contributions
 sale-0.008
 digits-0.008
folk-0.007
 customer-0.007
 letters-0.007
Token.
Token ID13
Feature activation+3.28e-03

Pos logit contributions
oppy+0.263
opsy+0.260
uffy+0.235
chy+0.232
rig+0.232
Neg logit contributions
 sale-0.131
 digits-0.116
folk-0.115
 letters-0.112
 customer-0.111
Token The
Token ID383
Feature activation+1.04e-01

Pos logit contributions
opsy+0.008
oppy+0.008
chy+0.007
rig+0.007
 bur+0.007
Neg logit contributions
 digits-0.004
folk-0.003
 sale-0.003
 customer-0.003
 Amen-0.003
Token past
Token ID1613
Feature activation-1.26e-01

Pos logit contributions
oppy+0.162
opsy+0.160
 Remy+0.141
rig+0.137
uffy+0.133
Neg logit contributions
folk-0.209
 digits-0.205
 sale-0.203
 customer-0.199
 letters-0.197
Token
Token ID220
Feature activation-2.26e-01

Pos logit contributions
opsy+0.187
oppy+0.186
 Remy+0.173
 bur+0.166
chy+0.165
Neg logit contributions
folk-0.146
 digits-0.143
 sale-0.132
 customer-0.124
 letters-0.123
Token
Token ID198
Feature activation+1.61e-02

Pos logit contributions
folk+0.308
 digits+0.301
 sale+0.282
 customer+0.252
 letters+0.252
Neg logit contributions
opsy-0.510
oppy-0.494
 bur-0.466
chy-0.462
 Remy-0.457
Token
Token ID198
Feature activation+1.46e-02

Pos logit contributions
opsy+0.032
oppy+0.032
 Remy+0.029
chy+0.028
 bur+0.028
Neg logit contributions
folk-0.027
 digits-0.026
 sale-0.024
 customer-0.023
 letters-0.023
TokenThe
Token ID464
Feature activation+9.07e-02

Pos logit contributions
opsy+0.026
oppy+0.026
 Remy+0.024
chy+0.023
 bur+0.023
Neg logit contributions
folk-0.027
 digits-0.026
 sale-0.025
 letters-0.023
 customer-0.023
Token towns
Token ID11684
Feature activation-2.04e-01

Pos logit contributions
opsy+0.189
oppy+0.187
chy+0.171
 Remy+0.171
 bur+0.168
Neg logit contributions
folk-0.141
 digits-0.136
 sale-0.125
 Amen-0.116
bench-0.114
Tokenfolk
Token ID19956
Feature activation-4.58e-01

Pos logit contributions
 digits+0.175
 Amen+0.173
epad+0.156
 sale+0.141
Gu+0.140
Neg logit contributions
oppy-0.500
opsy-0.497
chy-0.474
 Remy-0.472
 bur-0.450
Token searched
Token ID16499
Feature activation-5.82e-02

Pos logit contributions
 digits+0.742
folk+0.717
 sale+0.677
 customer+0.651
epad+0.638
Neg logit contributions
opsy-0.897
oppy-0.883
 Remy-0.814
 bur-0.812
chy-0.809
Token high
Token ID1029
Feature activation+1.19e-01

Pos logit contributions
folk+0.108
 digits+0.105
 sale+0.099
 customer+0.093
 letters+0.092
Neg logit contributions
opsy-0.105
oppy-0.103
 Remy-0.095
chy-0.092
 bur-0.092
Token and
Token ID290
Feature activation+2.33e-02

Pos logit contributions
opsy+0.241
oppy+0.239
 Remy+0.219
chy+0.211
 bur+0.210
Neg logit contributions
folk-0.195
 digits-0.189
 sale-0.179
 letters-0.166
 customer-0.165
Token low
Token ID1877
Feature activation-2.98e-02

Pos logit contributions
opsy+0.045
oppy+0.044
 Remy+0.042
chy+0.041
 bur+0.040
Neg logit contributions
folk-0.039
 digits-0.039
 sale-0.036
 customer-0.034
 letters-0.033
Token,
Token ID11
Feature activation-4.52e-02

Pos logit contributions
folk+0.047
 digits+0.047
 sale+0.043
 customer+0.041
 Amen+0.040
Neg logit contributions
opsy-0.060
oppy-0.060
 Remy-0.056
chy-0.055
 bur-0.054
Token.
Token ID13
Feature activation-8.06e-03

Pos logit contributions
opsy+0.258
oppy+0.256
chy+0.241
 Remy+0.237
 bur+0.237
Neg logit contributions
 digits-0.266
folk-0.261
 sale-0.237
 customer-0.228
 Amen-0.227
Token He
Token ID679
Feature activation-2.72e-02

Pos logit contributions
folk+0.014
 digits+0.014
 sale+0.013
epad+0.012
 Amen+0.012
Neg logit contributions
oppy-0.015
opsy-0.015
 Remy-0.014
 bur-0.013
chy-0.013
Token asked
Token ID1965
Feature activation-2.53e-01

Pos logit contributions
folk+0.041
 digits+0.039
 sale+0.036
 customer+0.034
epad+0.033
Neg logit contributions
opsy-0.059
oppy-0.058
 Remy-0.054
 bur-0.053
chy-0.053
Token the
Token ID262
Feature activation+2.98e-02

Pos logit contributions
 digits+0.449
folk+0.447
bench+0.402
 Amen+0.402
epad+0.387
Neg logit contributions
 Remy-0.449
oppy-0.434
opsy-0.428
 bur-0.389
chy-0.387
Token towns
Token ID11684
Feature activation-1.99e-01

Pos logit contributions
opsy+0.059
oppy+0.057
 bur+0.055
 Remy+0.054
chy+0.054
Neg logit contributions
folk-0.044
 digits-0.043
 sale-0.039
 Amen-0.039
bench-0.039
Tokenfolk
Token ID19956
Feature activation-4.52e-01

Pos logit contributions
 digits+0.270
 Amen+0.253
Gu+0.244
bench+0.238
 sale+0.236
Neg logit contributions
oppy-0.376
 Remy-0.375
opsy-0.370
chy-0.357
rig-0.343
Token if
Token ID611
Feature activation+2.09e-02

Pos logit contributions
folk+0.802
 digits+0.796
 sale+0.727
bench+0.687
 Amen+0.686
Neg logit contributions
opsy-0.821
oppy-0.818
 Remy-0.767
chy-0.733
 bur-0.720
Token they
Token ID484
Feature activation+3.16e-02

Pos logit contributions
 Remy+0.030
oppy+0.029
opsy+0.028
 bur+0.025
chy+0.025
Neg logit contributions
 digits-0.044
folk-0.042
 channel-0.040
bench-0.039
 Amen-0.039
Token wanted
Token ID2227
Feature activation-1.13e-01

Pos logit contributions
opsy+0.060
oppy+0.059
 Remy+0.054
 bur+0.051
chy+0.051
Neg logit contributions
folk-0.057
 digits-0.054
 sale-0.051
 letters-0.048
 customer-0.048
Token him
Token ID683
Feature activation+1.14e-03

Pos logit contributions
folk+0.219
 digits+0.211
 Amen+0.193
bench+0.189
 sale+0.186
Neg logit contributions
oppy-0.183
opsy-0.181
 Remy-0.179
 bur-0.169
chy-0.168
Token to
Token ID284
Feature activation-6.47e-03

Pos logit contributions
opsy+0.003
oppy+0.003
 Remy+0.002
 bur+0.002
chy+0.002
Neg logit contributions
folk-0.002
 digits-0.002
 sale-0.001
 letters-0.001
 customer-0.001
Token and
Token ID290
Feature activation+3.23e-02

Pos logit contributions
folk+0.118
 digits+0.115
 sale+0.107
 customer+0.101
 Amen+0.099
Neg logit contributions
opsy-0.138
oppy-0.137
 Remy-0.127
chy-0.124
 bur-0.123
Token days
Token ID1528
Feature activation-7.11e-02

Pos logit contributions
oppy+0.059
opsy+0.059
 Remy+0.058
 bur+0.057
chy+0.055
Neg logit contributions
folk-0.054
 digits-0.053
 Amen-0.050
 sale-0.048
 customer-0.047
Token and
Token ID290
Feature activation+3.26e-02

Pos logit contributions
folk+0.115
 digits+0.114
 sale+0.104
 customer+0.099
 Amen+0.098
Neg logit contributions
opsy-0.141
oppy-0.140
 Remy-0.131
chy-0.126
 bur-0.126
Token the
Token ID262
Feature activation+3.63e-02

Pos logit contributions
oppy+0.058
 Remy+0.058
opsy+0.058
 bur+0.056
chy+0.055
Neg logit contributions
folk-0.053
 digits-0.052
 Amen-0.051
 sale-0.048
 customer-0.046
Token towns
Token ID11684
Feature activation-1.95e-01

Pos logit contributions
opsy+0.066
chy+0.065
oppy+0.065
 bur+0.065
 Remy+0.064
Neg logit contributions
folk-0.052
 Amen-0.051
 digits-0.051
 sale-0.048
bench-0.047
Tokenfolk
Token ID19956
Feature activation-4.50e-01

Pos logit contributions
 Amen+0.168
 digits+0.153
Gu+0.135
epad+0.132
 customer+0.126
Neg logit contributions
chy-0.456
opsy-0.455
oppy-0.452
 Remy-0.448
 bur-0.428
Token looked
Token ID3114
Feature activation-1.10e-01

Pos logit contributions
 digits+0.760
folk+0.730
 sale+0.720
 Amen+0.687
 customer+0.684
Neg logit contributions
opsy-0.811
oppy-0.799
chy-0.774
 bur-0.734
 Remy-0.732
Token on
Token ID319
Feature activation-5.79e-02

Pos logit contributions
folk+0.215
 digits+0.208
 sale+0.197
 Amen+0.188
 customer+0.187
Neg logit contributions
oppy-0.180
opsy-0.178
chy-0.168
 Remy-0.165
 bur-0.164
Token.
Token ID13
Feature activation-8.57e-04

Pos logit contributions
folk+0.105
 digits+0.101
 Amen+0.091
 sale+0.091
 customer+0.089
Neg logit contributions
opsy-0.102
oppy-0.101
 Remy-0.096
 bur-0.095
chy-0.094
Token
Token ID198
Feature activation+2.59e-02

Pos logit contributions
 digits+0.001
folk+0.001
 sale+0.001
epad+0.001
 customer+0.001
Neg logit contributions
oppy-0.002
 Remy-0.002
opsy-0.002
 bur-0.002
chy-0.001
Token
Token ID198
Feature activation+2.59e-02

Pos logit contributions
opsy+0.046
oppy+0.046
 Remy+0.043
 bur+0.040
chy+0.039
Neg logit contributions
folk-0.048
 digits-0.047
 sale-0.044
epad-0.042
 letters-0.042
Token thing
Token ID1517
Feature activation-1.43e-01

Pos logit contributions
opsy+0.004
oppy+0.004
 bur+0.004
 Remy+0.004
chy+0.003
Neg logit contributions
folk-0.004
 digits-0.004
 Amen-0.004
 sale-0.004
bench-0.003
Token ever
Token ID1683
Feature activation-2.07e-02

Pos logit contributions
folk+0.232
 digits+0.223
 sale+0.210
 customer+0.196
 letters+0.195
Neg logit contributions
opsy-0.293
oppy-0.290
 Remy-0.265
 bur-0.259
chy-0.256
Token.
Token ID13
Feature activation+2.64e-05

Pos logit contributions
folk+0.035
 digits+0.035
 sale+0.032
 customer+0.030
 letters+0.030
Neg logit contributions
opsy-0.040
oppy-0.040
 Remy-0.037
chy-0.036
 bur-0.036
Token The
Token ID383
Feature activation+1.00e-01

Pos logit contributions
oppy+0.000
opsy+0.000
 Remy+0.000
 bur+0.000
chy+0.000
Neg logit contributions
 digits-0.000
folk-0.000
 sale-0.000
epad-0.000
 customer-0.000
Token towns
Token ID11684
Feature activation-1.94e-01

Pos logit contributions
opsy+0.168
oppy+0.165
 Remy+0.161
chy+0.158
 bur+0.158
Neg logit contributions
 digits-0.151
 Amen-0.150
folk-0.148
 sale-0.144
bench-0.143
Tokenfolk
Token ID19956
Feature activation-4.48e-01

Pos logit contributions
 Amen+0.133
 digits+0.119
Gu+0.113
epad+0.111
 sale+0.096
Neg logit contributions
opsy-0.476
oppy-0.464
 Remy-0.462
chy-0.456
 bur-0.439
Token cl
Token ID537
Feature activation-1.56e-01

Pos logit contributions
 digits+0.786
 sale+0.738
folk+0.727
 customer+0.701
bench+0.698
Neg logit contributions
opsy-0.794
oppy-0.762
chy-0.708
 bur-0.705
 Remy-0.700
Tokenapped
Token ID6320
Feature activation-1.38e-01

Pos logit contributions
 digits+0.206
folk+0.200
 sale+0.197
 customer+0.184
bench+0.176
Neg logit contributions
oppy-0.358
opsy-0.355
 Remy-0.317
 bur-0.315
uffy-0.306
Token and
Token ID290
Feature activation+3.49e-02

Pos logit contributions
folk+0.249
 digits+0.247
 sale+0.228
 customer+0.217
 jury+0.212
Neg logit contributions
opsy-0.248
oppy-0.246
 Remy-0.230
chy-0.224
 bur-0.223
Token cheered
Token ID34767
Feature activation-2.45e-01

Pos logit contributions
opsy+0.078
oppy+0.078
 Remy+0.077
 bur+0.074
chy+0.073
Neg logit contributions
 digits-0.044
folk-0.042
 sale-0.041
 customer-0.039
 Amen-0.037
Token because
Token ID780
Feature activation+1.54e-01

Pos logit contributions
 digits+0.459
folk+0.454
 sale+0.413
 customer+0.402
bench+0.400
Neg logit contributions
opsy-0.410
oppy-0.409
 Remy-0.388
chy-0.380
 bur-0.361
Token its
Token ID663
Feature activation+8.72e-02

Pos logit contributions
opsy+0.007
oppy+0.007
 Remy+0.007
chy+0.006
 bur+0.006
Neg logit contributions
folk-0.005
 digits-0.004
 sale-0.004
 customer-0.004
 letters-0.004
Token bouncing
Token ID30713
Feature activation+8.73e-02

Pos logit contributions
oppy+0.191
opsy+0.189
 Remy+0.175
uffy+0.166
chy+0.164
Neg logit contributions
 sale-0.112
 digits-0.111
 number-0.111
 cheering-0.106
folk-0.106
Token,
Token ID11
Feature activation-3.32e-02

Pos logit contributions
opsy+0.213
oppy+0.209
 Remy+0.190
chy+0.189
 bur+0.182
Neg logit contributions
folk-0.109
 sale-0.100
 digits-0.097
 cheering-0.087
 letters-0.087
Token the
Token ID262
Feature activation+3.46e-02

Pos logit contributions
 digits+0.056
folk+0.055
 sale+0.051
 customer+0.048
bench+0.048
Neg logit contributions
opsy-0.064
oppy-0.063
 Remy-0.060
 bur-0.057
chy-0.056
Token towns
Token ID11684
Feature activation-1.91e-01

Pos logit contributions
oppy+0.066
opsy+0.065
 Remy+0.060
chy+0.058
 bur+0.057
Neg logit contributions
folk-0.062
 digits-0.060
 sale-0.056
 customer-0.054
 letters-0.054
Tokenfolk
Token ID19956
Feature activation-4.44e-01

Pos logit contributions
 digits+0.291
 Amen+0.269
 sale+0.261
epad+0.253
 customer+0.252
Neg logit contributions
opsy-0.372
oppy-0.362
chy-0.344
 Remy-0.342
 bur-0.331
Token thanked
Token ID26280
Feature activation-4.40e-02

Pos logit contributions
folk+0.666
 digits+0.658
 sale+0.610
 customer+0.566
 letters+0.557
Neg logit contributions
opsy-0.948
oppy-0.935
 Remy-0.867
chy-0.849
 bur-0.849
Token the
Token ID262
Feature activation+3.49e-02

Pos logit contributions
 digits+0.078
folk+0.072
bench+0.071
 customer+0.066
 salesman+0.065
Neg logit contributions
opsy-0.079
 Remy-0.079
oppy-0.076
 bur-0.068
 Dee-0.068
Token rope
Token ID17182
Feature activation+1.22e-01

Pos logit contributions
opsy+0.070
oppy+0.068
 Remy+0.064
chy+0.062
 bur+0.061
Neg logit contributions
folk-0.057
 digits-0.056
 sale-0.052
 Amen-0.048
epad-0.048
Token for
Token ID329
Feature activation+1.22e-01

Pos logit contributions
opsy+0.246
oppy+0.243
 Remy+0.220
chy+0.213
 bur+0.211
Neg logit contributions
folk-0.204
 digits-0.194
 sale-0.190
 letters-0.175
 customer-0.174
Token its
Token ID663
Feature activation+8.83e-02

Pos logit contributions
opsy+0.246
 Remy+0.242
oppy+0.238
 bur+0.227
chy+0.217
Neg logit contributions
folk-0.193
 digits-0.191
 sale-0.161
 prices-0.158
 customer-0.157
Token was
Token ID373
Feature activation+4.65e-02

Pos logit contributions
folk+0.194
 digits+0.184
 sale+0.178
 customer+0.162
 letters+0.159
Neg logit contributions
opsy-0.286
oppy-0.286
 Remy-0.263
chy-0.258
 bur-0.245
Token very
Token ID845
Feature activation-4.39e-02

Pos logit contributions
opsy+0.094
oppy+0.091
 Remy+0.086
chy+0.085
 bur+0.084
Neg logit contributions
folk-0.076
 digits-0.075
 sale-0.068
 jury-0.064
 letters-0.064
Token happy
Token ID3772
Feature activation-7.84e-02

Pos logit contributions
folk+0.069
 digits+0.067
 sale+0.062
 letters+0.057
 customer+0.057
Neg logit contributions
opsy-0.093
oppy-0.092
 Remy-0.085
chy-0.083
 bur-0.083
Token with
Token ID351
Feature activation-9.95e-02

Pos logit contributions
folk+0.138
 digits+0.135
 sale+0.124
 customer+0.117
 letters+0.116
Neg logit contributions
opsy-0.149
oppy-0.147
 Remy-0.137
 bur-0.133
chy-0.131
Token his
Token ID465
Feature activation-5.11e-02

Pos logit contributions
folk+0.141
 digits+0.137
 sale+0.127
 customer+0.117
 letters+0.117
Neg logit contributions
opsy-0.224
oppy-0.222
chy-0.202
 Remy-0.201
 bur-0.199
Token sale
Token ID5466
Feature activation-4.25e-01

Pos logit contributions
 sale+0.074
 digits+0.072
 letters+0.071
folk+0.068
 prices+0.066
Neg logit contributions
opsy-0.105
oppy-0.100
 Remy-0.100
chy-0.094
rig-0.089
Token.
Token ID13
Feature activation-6.30e-03

Pos logit contributions
folk+0.727
 digits+0.726
 sale+0.658
 Amen+0.637
 customer+0.625
Neg logit contributions
opsy-0.796
oppy-0.792
 Remy-0.729
chy-0.720
 bur-0.707
Token He
Token ID679
Feature activation-2.64e-02

Pos logit contributions
folk+0.009
 digits+0.009
 sale+0.008
 customer+0.007
 letters+0.007
Neg logit contributions
opsy-0.014
oppy-0.014
chy-0.013
 Remy-0.013
 bur-0.013
Token had
Token ID550
Feature activation-2.61e-02

Pos logit contributions
folk+0.037
 digits+0.036
 sale+0.034
 customer+0.031
 letters+0.031
Neg logit contributions
opsy-0.058
oppy-0.058
 Remy-0.053
chy-0.052
uffy-0.050
Token enough
Token ID1576
Feature activation-9.50e-02

Pos logit contributions
folk+0.044
 digits+0.042
 Amen+0.040
 jury+0.036
 sale+0.036
Neg logit contributions
opsy-0.048
 Remy-0.047
oppy-0.047
 bur-0.047
chy-0.045
Token money
Token ID1637
Feature activation-1.28e-01

Pos logit contributions
folk+0.148
 digits+0.142
 sale+0.126
 Amen+0.124
epad+0.120
Neg logit contributions
opsy-0.199
oppy-0.198
 Remy-0.184
 bur-0.183
chy-0.178
Token his
Token ID465
Feature activation-4.75e-02

Pos logit contributions
opsy+0.298
oppy+0.297
 Remy+0.287
chy+0.275
 bur+0.274
Neg logit contributions
 digits-0.232
folk-0.230
 sale-0.202
 Amen-0.197
bench-0.196
Token grandma
Token ID49890
Feature activation-5.03e-02

Pos logit contributions
folk+0.085
 digits+0.083
 sale+0.076
 customer+0.073
epad+0.072
Neg logit contributions
opsy-0.088
oppy-0.087
 Remy-0.080
 bur-0.079
chy-0.078
Token got
Token ID1392
Feature activation-4.10e-02

Pos logit contributions
folk+0.090
 digits+0.089
 sale+0.083
 customer+0.078
 Amen+0.077
Neg logit contributions
opsy-0.092
oppy-0.092
chy-0.084
 Remy-0.083
 bur-0.080
Token it
Token ID340
Feature activation-1.29e-01

Pos logit contributions
folk+0.075
 digits+0.074
 Amen+0.066
 sale+0.066
 customer+0.064
Neg logit contributions
oppy-0.073
opsy-0.073
chy-0.068
 Remy-0.066
 bur-0.065
Token on
Token ID319
Feature activation-6.18e-02

Pos logit contributions
folk+0.188
 digits+0.179
 sale+0.179
 letters+0.160
epad+0.160
Neg logit contributions
opsy-0.283
oppy-0.277
 Remy-0.260
 bur-0.246
chy-0.236
Token sale
Token ID5466
Feature activation-4.23e-01

Pos logit contributions
folk+0.111
 digits+0.109
 Amen+0.093
 sale+0.092
 jury+0.092
Neg logit contributions
opsy-0.111
oppy-0.109
 Remy-0.105
 bur-0.102
chy-0.101
Token!
Token ID0
Feature activation+9.97e-02

Pos logit contributions
 digits+0.857
folk+0.855
 Amen+0.823
 jury+0.754
 customer+0.745
Neg logit contributions
oppy-0.612
chy-0.599
opsy-0.596
 bur-0.543
 Remy-0.539
Token<|endoftext|>
Token ID50256
Feature activation+1.77e-01

Pos logit contributions
opsy+0.187
oppy+0.187
 Remy+0.178
 bur+0.166
chy+0.162
Neg logit contributions
folk-0.171
 digits-0.170
 sale-0.156
epad-0.149
 letters-0.149
TokenOnce
Token ID7454
Feature activation-1.05e-01

Pos logit contributions
opsy+0.340
oppy+0.337
 Remy+0.311
chy+0.300
 bur+0.300
Neg logit contributions
folk-0.304
 digits-0.297
 sale-0.278
 customer-0.261
 letters-0.258
Token upon
Token ID2402
Feature activation+1.62e-01

Pos logit contributions
folk+0.197
 digits+0.192
 sale+0.182
 customer+0.174
 cheering+0.168
Neg logit contributions
opsy-0.178
oppy-0.168
 Remy-0.160
 bur-0.160
chy-0.156
Token a
Token ID257
Feature activation-2.15e-03

Pos logit contributions
opsy+0.347
oppy+0.344
 Remy+0.316
 bur+0.309
chy+0.308
Neg logit contributions
folk-0.240
 digits-0.236
 sale-0.220
 customer-0.205
 letters-0.202
Token were
Token ID547
Feature activation-3.96e-02

Pos logit contributions
folk+0.030
 digits+0.028
 sale+0.027
 letters+0.025
 customer+0.024
Neg logit contributions
opsy-0.046
oppy-0.045
 Remy-0.042
chy-0.041
 bur-0.041
Token many
Token ID867
Feature activation-6.26e-02

Pos logit contributions
folk+0.062
 digits+0.060
 sale+0.054
 Amen+0.053
bench+0.051
Neg logit contributions
opsy-0.079
oppy-0.078
 Remy-0.076
chy-0.074
 bur-0.073
Token beautiful
Token ID4950
Feature activation+4.80e-02

Pos logit contributions
folk+0.094
 digits+0.091
 sale+0.085
 Amen+0.081
 customer+0.079
Neg logit contributions
opsy-0.129
oppy-0.128
 bur-0.121
 Remy-0.121
chy-0.118
Token apples
Token ID22514
Feature activation-1.54e-02

Pos logit contributions
opsy+0.101
oppy+0.100
 bur+0.096
 Remy+0.094
chy+0.091
Neg logit contributions
folk-0.070
 digits-0.068
 sale-0.064
 customer-0.061
bench-0.061
Token for
Token ID329
Feature activation+1.10e-01

Pos logit contributions
folk+0.025
 digits+0.024
 sale+0.023
 customer+0.021
 letters+0.021
Neg logit contributions
opsy-0.031
oppy-0.031
 Remy-0.029
 bur-0.028
chy-0.028
Token sale
Token ID5466
Feature activation-4.23e-01

Pos logit contributions
opsy+0.212
oppy+0.211
 Remy+0.208
 bur+0.192
chy+0.183
Neg logit contributions
folk-0.181
 digits-0.181
bench-0.160
 Amen-0.159
epad-0.157
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
 digits+0.833
folk+0.824
 Amen+0.821
Gu+0.732
 customer+0.730
Neg logit contributions
oppy-0.637
opsy-0.619
chy-0.606
 Remy-0.574
 bur-0.564
Token The
Token ID383
Feature activation+8.79e-02

Pos logit contributions
folk+0.022
 digits+0.022
 sale+0.020
epad+0.019
 letters+0.019
Neg logit contributions
oppy-0.025
opsy-0.025
 Remy-0.024
 bur-0.022
chy-0.021
Token pirate
Token ID25868
Feature activation-3.53e-02

Pos logit contributions
opsy+0.178
oppy+0.175
 Remy+0.163
 bur+0.159
chy+0.159
Neg logit contributions
folk-0.142
 digits-0.139
 sale-0.127
epad-0.118
 customer-0.118
Token smiled
Token ID13541
Feature activation-1.35e-01

Pos logit contributions
folk+0.060
 digits+0.059
 sale+0.054
 Amen+0.052
epad+0.052
Neg logit contributions
opsy-0.067
oppy-0.067
 Remy-0.062
chy-0.060
 bur-0.060
Token and
Token ID290
Feature activation+1.97e-02

Pos logit contributions
folk+0.230
 digits+0.224
 sale+0.210
 customer+0.197
 letters+0.195
Neg logit contributions
opsy-0.265
oppy-0.262
 Remy-0.241
chy-0.234
 bur-0.233
Token that
Token ID326
Feature activation+8.10e-02

Pos logit contributions
folk+0.042
 digits+0.041
 sale+0.038
 customer+0.036
bench+0.036
Neg logit contributions
opsy-0.047
oppy-0.046
 Remy-0.043
 bur-0.041
chy-0.041
Token jewel
Token ID16927
Feature activation+7.66e-02

Pos logit contributions
opsy+0.146
oppy+0.145
 Remy+0.134
chy+0.131
 bur+0.129
Neg logit contributions
folk-0.148
 digits-0.145
 sale-0.136
 customer-0.127
 Amen-0.125
Token is
Token ID318
Feature activation+3.75e-02

Pos logit contributions
opsy+0.163
oppy+0.156
 Remy+0.146
 bur+0.141
chy+0.133
Neg logit contributions
folk-0.115
 digits-0.109
 sale-0.107
 letters-0.103
 number-0.098
Token not
Token ID407
Feature activation+1.45e-02

Pos logit contributions
opsy+0.077
oppy+0.076
 Remy+0.070
 bur+0.067
chy+0.067
Neg logit contributions
folk-0.060
 digits-0.059
 sale-0.055
 customer-0.051
 letters-0.051
Token for
Token ID329
Feature activation+1.13e-01

Pos logit contributions
opsy+0.028
oppy+0.028
 Remy+0.026
chy+0.025
 bur+0.025
Neg logit contributions
folk-0.025
 digits-0.024
 sale-0.022
 customer-0.021
 Amen-0.021
Token sale
Token ID5466
Feature activation-4.22e-01

Pos logit contributions
oppy+0.215
opsy+0.214
 Remy+0.204
 bur+0.193
chy+0.186
Neg logit contributions
folk-0.193
 digits-0.187
 Amen-0.168
bench-0.163
 sale-0.162
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
folk+0.768
 digits+0.760
 Amen+0.689
 sale+0.688
 customer+0.665
Neg logit contributions
oppy-0.748
opsy-0.738
chy-0.684
 Remy-0.682
 bur-0.647
Token It
Token ID632
Feature activation-8.40e-02

Pos logit contributions
folk+0.019
 digits+0.018
 sale+0.017
epad+0.016
bench+0.016
Neg logit contributions
oppy-0.021
opsy-0.021
 Remy-0.020
 bur-0.019
chy-0.018
Token is
Token ID318
Feature activation+3.84e-02

Pos logit contributions
folk+0.134
 digits+0.129
 sale+0.123
 letters+0.119
 prices+0.114
Neg logit contributions
opsy-0.175
oppy-0.170
 Remy-0.155
 bur-0.145
uffy-0.139
Token too
Token ID1165
Feature activation-9.79e-02

Pos logit contributions
opsy+0.078
oppy+0.077
 Remy+0.071
 bur+0.069
chy+0.069
Neg logit contributions
folk-0.062
 digits-0.061
 sale-0.057
 customer-0.053
 letters-0.053
Token special
Token ID2041
Feature activation+7.31e-02

Pos logit contributions
folk+0.150
 digits+0.149
 sale+0.144
 letters+0.135
 customer+0.132
Neg logit contributions
opsy-0.204
oppy-0.200
 Remy-0.186
 bur-0.179
chy-0.175
Tokenche
Token ID2395
Feature activation-3.05e-02

Pos logit contributions
 digits+0.205
folk+0.203
 sale+0.183
 Amen+0.182
 customer+0.176
Neg logit contributions
opsy-0.272
oppy-0.263
 Remy-0.250
chy-0.245
 bur-0.237
Tokenap
Token ID499
Feature activation-2.79e-02

Pos logit contributions
folk+0.061
 digits+0.056
epad+0.055
 sale+0.055
 cheering+0.054
Neg logit contributions
oppy-0.052
opsy-0.051
 Remy-0.044
uffy-0.042
chy-0.038
Token basketball
Token ID9669
Feature activation-1.22e-02

Pos logit contributions
folk+0.048
 digits+0.047
 sale+0.042
 customer+0.040
 Amen+0.040
Neg logit contributions
oppy-0.054
opsy-0.053
 Remy-0.050
chy-0.048
 bur-0.046
Tokens
Token ID82
Feature activation+2.01e-01

Pos logit contributions
folk+0.018
 digits+0.018
 sale+0.016
 customer+0.015
 Amen+0.015
Neg logit contributions
opsy-0.026
oppy-0.026
 Remy-0.024
chy-0.023
 bur-0.023
Token for
Token ID329
Feature activation+1.12e-01

Pos logit contributions
opsy+0.393
oppy+0.391
 Remy+0.366
chy+0.359
 bur+0.354
Neg logit contributions
folk-0.328
 digits-0.321
 sale-0.281
 Amen-0.279
 customer-0.275
Token sale
Token ID5466
Feature activation-4.21e-01

Pos logit contributions
oppy+0.211
 Remy+0.211
opsy+0.207
 bur+0.194
 Lucky+0.183
Neg logit contributions
folk-0.194
 digits-0.183
 Amen-0.163
bench-0.162
 salesman-0.157
Token".
Token ID1911
Feature activation-1.07e-01

Pos logit contributions
folk+0.659
 digits+0.653
 Amen+0.589
 cheering+0.557
 jury+0.533
Neg logit contributions
oppy-0.847
opsy-0.825
 Remy-0.790
chy-0.770
 bur-0.734
Token Tim
Token ID5045
Feature activation+6.67e-02

Pos logit contributions
folk+0.214
 digits+0.210
epad+0.203
 winners+0.190
 customer+0.190
Neg logit contributions
 Remy-0.169
opsy-0.168
oppy-0.166
 bur-0.152
chy-0.143
Tokenmy
Token ID1820
Feature activation-1.37e-01

Pos logit contributions
opsy+0.165
oppy+0.164
 Remy+0.153
chy+0.150
 bur+0.149
Neg logit contributions
folk-0.081
 digits-0.077
 sale-0.071
 customer-0.063
 letters-0.062
Token asked
Token ID1965
Feature activation-2.49e-01

Pos logit contributions
folk+0.252
 digits+0.243
 sale+0.226
epad+0.219
 customer+0.217
Neg logit contributions
opsy-0.250
oppy-0.246
 Remy-0.226
chy-0.221
 bur-0.220
Token his
Token ID465
Feature activation-5.28e-02

Pos logit contributions
 digits+0.561
folk+0.551
 winners+0.492
epad+0.491
bench+0.491
Neg logit contributions
 Remy-0.361
oppy-0.300
 Lucky-0.294
opsy-0.289
 Mitt-0.284
Token put
Token ID1234
Feature activation-5.19e-02

Pos logit contributions
folk+0.335
 digits+0.325
 sale+0.302
 customer+0.279
 letters+0.276
Neg logit contributions
opsy-0.468
oppy-0.463
 Remy-0.429
 bur-0.418
chy-0.418
Token the
Token ID262
Feature activation+3.30e-02

Pos logit contributions
folk+0.095
 digits+0.093
 Amen+0.087
 sale+0.086
epad+0.085
Neg logit contributions
opsy-0.089
oppy-0.087
 Remy-0.085
 Lucky-0.079
 bur-0.078
Token rake
Token ID47885
Feature activation+1.83e-01

Pos logit contributions
opsy+0.049
oppy+0.049
 Remy+0.043
chy+0.040
 bur+0.040
Neg logit contributions
 digits-0.070
folk-0.070
 sale-0.067
 customer-0.064
 letters-0.064
Token up
Token ID510
Feature activation+9.12e-02

Pos logit contributions
opsy+0.386
oppy+0.382
 Remy+0.354
chy+0.336
 bur+0.335
Neg logit contributions
folk-0.284
 digits-0.274
 sale-0.261
 letters-0.242
 customer-0.241
Token for
Token ID329
Feature activation+1.15e-01

Pos logit contributions
opsy+0.186
oppy+0.184
 Remy+0.171
chy+0.166
 bur+0.166
Neg logit contributions
folk-0.146
 digits-0.143
 sale-0.132
 customer-0.124
 letters-0.122
Token sale
Token ID5466
Feature activation-4.20e-01

Pos logit contributions
opsy+0.209
oppy+0.205
 Remy+0.203
 bur+0.187
 Lucky+0.186
Neg logit contributions
folk-0.197
 digits-0.193
 Amen-0.177
bench-0.165
 salesman-0.161
Token and
Token ID290
Feature activation+2.71e-02

Pos logit contributions
folk+0.873
 digits+0.865
 Amen+0.859
 jury+0.776
 president+0.775
Neg logit contributions
oppy-0.549
opsy-0.543
chy-0.543
 bur-0.500
 Remy-0.486
Token waited
Token ID13488
Feature activation-1.32e-01

Pos logit contributions
opsy+0.053
oppy+0.053
 Remy+0.050
 bur+0.049
chy+0.048
Neg logit contributions
folk-0.044
 digits-0.043
 sale-0.038
 Amen-0.037
 customer-0.036
Token.
Token ID13
Feature activation-7.01e-03

Pos logit contributions
folk+0.272
 digits+0.261
 sale+0.235
 jury+0.234
 Amen+0.230
Neg logit contributions
opsy-0.211
oppy-0.208
chy-0.191
 bur-0.186
 Remy-0.185
Token
Token ID198
Feature activation+1.80e-02

Pos logit contributions
folk+0.013
 digits+0.013
 Amen+0.011
 winners+0.011
 sale+0.011
Neg logit contributions
opsy-0.012
oppy-0.012
 Remy-0.011
 bur-0.010
uffy-0.010
Token
Token ID198
Feature activation+1.72e-02

Pos logit contributions
opsy+0.036
oppy+0.036
 Remy+0.033
chy+0.032
 bur+0.032
Neg logit contributions
folk-0.030
 digits-0.029
 sale-0.027
 customer-0.025
 letters-0.025
Token found
Token ID1043
Feature activation-5.87e-02

Pos logit contributions
folk+0.167
 Amen+0.163
 digits+0.163
 channel+0.150
 cheering+0.143
Neg logit contributions
oppy-0.185
opsy-0.179
 Remy-0.170
chy-0.159
 bur-0.158
Token the
Token ID262
Feature activation+2.73e-02

Pos logit contributions
folk+0.099
 digits+0.096
 sale+0.088
 Amen+0.085
epad+0.084
Neg logit contributions
opsy-0.114
oppy-0.113
 Remy-0.107
 bur-0.101
chy-0.101
Token monster
Token ID9234
Feature activation+4.57e-02

Pos logit contributions
opsy+0.053
oppy+0.052
chy+0.050
 bur+0.049
 Remy+0.049
Neg logit contributions
folk-0.045
 digits-0.044
 sale-0.038
 Amen-0.038
bench-0.037
Token truck
Token ID7779
Feature activation-1.24e-01

Pos logit contributions
opsy+0.095
oppy+0.094
 Remy+0.086
 bur+0.083
chy+0.083
Neg logit contributions
folk-0.072
 digits-0.070
 sale-0.067
 customer-0.062
 letters-0.061
Token on
Token ID319
Feature activation-6.36e-02

Pos logit contributions
folk+0.212
 digits+0.211
 Amen+0.188
 sale+0.186
 customer+0.182
Neg logit contributions
opsy-0.228
oppy-0.227
chy-0.212
 Remy-0.211
 bur-0.205
Token sale
Token ID5466
Feature activation-4.20e-01

Pos logit contributions
folk+0.114
 digits+0.112
 Amen+0.098
 sale+0.096
epad+0.095
Neg logit contributions
opsy-0.114
oppy-0.113
 Remy-0.108
 bur-0.104
chy-0.102
Token.
Token ID13
Feature activation-4.44e-03

Pos logit contributions
 Amen+0.896
folk+0.847
 digits+0.845
Gu+0.754
 president+0.751
Neg logit contributions
oppy-0.549
opsy-0.539
chy-0.531
 bur-0.497
 Remy-0.494
Token Tim
Token ID5045
Feature activation+6.70e-02

Pos logit contributions
folk+0.008
 digits+0.008
 sale+0.007
 customer+0.007
epad+0.007
Neg logit contributions
opsy-0.008
oppy-0.008
 Remy-0.007
 bur-0.007
chy-0.007
Tokenmy
Token ID1820
Feature activation-1.34e-01

Pos logit contributions
opsy+0.159
oppy+0.158
 Remy+0.145
chy+0.144
 bur+0.144
Neg logit contributions
folk-0.089
 digits-0.085
 sale-0.079
 customer-0.070
 jury-0.070
Token was
Token ID373
Feature activation+5.06e-02

Pos logit contributions
folk+0.236
 digits+0.230
 sale+0.216
 customer+0.203
 letters+0.201
Neg logit contributions
opsy-0.252
oppy-0.249
 Remy-0.228
chy-0.221
 bur-0.221
Token very
Token ID845
Feature activation-4.15e-02

Pos logit contributions
opsy+0.084
oppy+0.080
chy+0.079
 bur+0.078
 Remy+0.077
Neg logit contributions
folk-0.095
 digits-0.093
 occasions-0.084
 sale-0.082
boxes-0.082
Token that
Token ID326
Feature activation+8.50e-02

Pos logit contributions
opsy+0.249
oppy+0.245
 Remy+0.224
 bur+0.214
chy+0.212
Neg logit contributions
folk-0.292
 digits-0.287
 sale-0.266
epad-0.253
 customer-0.253
Token day
Token ID1110
Feature activation-5.65e-03

Pos logit contributions
opsy+0.176
oppy+0.175
 Remy+0.161
chy+0.157
 bur+0.157
Neg logit contributions
folk-0.135
 digits-0.132
 sale-0.123
 customer-0.115
 letters-0.113
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
folk+0.008
 digits+0.008
 sale+0.007
 customer+0.007
 letters+0.007
Neg logit contributions
opsy-0.012
oppy-0.012
 Remy-0.011
chy-0.011
 bur-0.011
Token the
Token ID262
Feature activation+2.54e-02

Pos logit contributions
folk+0.056
 digits+0.054
 sale+0.053
 customer+0.048
 letters+0.047
Neg logit contributions
opsy-0.084
oppy-0.082
 Remy-0.076
 bur-0.075
chy-0.074
Token garage
Token ID15591
Feature activation-3.02e-02

Pos logit contributions
opsy+0.055
oppy+0.053
chy+0.049
 Remy+0.049
 bur+0.049
Neg logit contributions
folk-0.039
 digits-0.037
 sale-0.033
bench-0.031
epad-0.031
Token sale
Token ID5466
Feature activation-4.20e-01

Pos logit contributions
 digits+0.063
folk+0.062
 Amen+0.059
epad+0.057
 winners+0.057
Neg logit contributions
chy-0.041
oppy-0.039
opsy-0.039
 bur-0.037
uffy-0.036
Token was
Token ID373
Feature activation+5.06e-02

Pos logit contributions
 Amen+0.789
 digits+0.768
folk+0.757
 customer+0.674
 president+0.663
Neg logit contributions
oppy-0.682
opsy-0.654
chy-0.641
uffy-0.606
 bur-0.601
Token over
Token ID625
Feature activation-9.58e-02

Pos logit contributions
chy+0.075
 bur+0.067
oppy+0.064
opsy+0.063
 poisonous+0.060
Neg logit contributions
folk-0.107
 digits-0.099
 Amen-0.091
 combinations-0.085
cles-0.084
Token and
Token ID290
Feature activation+2.94e-02

Pos logit contributions
folk+0.182
 digits+0.175
 Amen+0.159
 sale+0.154
 salesman+0.151
Neg logit contributions
oppy-0.171
opsy-0.171
 Remy-0.154
 bur-0.154
chy-0.148
Token Lily
Token ID20037
Feature activation+1.41e-02

Pos logit contributions
oppy+0.051
opsy+0.050
chy+0.047
 Remy+0.047
 bur+0.047
Neg logit contributions
folk-0.055
 digits-0.055
 Amen-0.048
 customer-0.047
 sale-0.047
Token and
Token ID290
Feature activation+3.03e-02

Pos logit contributions
opsy+0.027
oppy+0.027
 Remy+0.024
 bur+0.024
chy+0.024
Neg logit contributions
folk-0.025
 digits-0.024
 sale-0.022
 customer-0.021
 letters-0.021
Token old
Token ID1468
Feature activation+4.55e-03

Pos logit contributions
opsy+0.032
oppy+0.032
 Remy+0.029
 bur+0.029
chy+0.029
Neg logit contributions
folk-0.018
 digits-0.017
 sale-0.015
epad-0.014
 Amen-0.014
Token toys
Token ID14958
Feature activation-1.48e-01

Pos logit contributions
oppy+0.009
 bur+0.009
opsy+0.009
 Remy+0.008
chy+0.008
Neg logit contributions
folk-0.007
 digits-0.007
 Amen-0.006
epad-0.006
Adam-0.006
Token at
Token ID379
Feature activation+6.49e-02

Pos logit contributions
folk+0.259
 digits+0.257
 sale+0.229
 Amen+0.222
 customer+0.218
Neg logit contributions
opsy-0.275
oppy-0.274
 Remy-0.251
chy-0.248
 bur-0.244
Token a
Token ID257
Feature activation+7.13e-03

Pos logit contributions
oppy+0.114
opsy+0.113
 Remy+0.105
 bur+0.103
chy+0.097
Neg logit contributions
folk-0.124
 digits-0.119
epad-0.103
 Amen-0.102
 sale-0.101
Token garage
Token ID15591
Feature activation-2.90e-02

Pos logit contributions
opsy+0.014
oppy+0.014
 Remy+0.013
 bur+0.012
chy+0.012
Neg logit contributions
folk-0.012
 digits-0.012
 sale-0.011
 letters-0.010
epad-0.010
Token sale
Token ID5466
Feature activation-4.19e-01

Pos logit contributions
 digits+0.060
folk+0.059
 Amen+0.055
 cheering+0.051
 letters+0.051
Neg logit contributions
chy-0.039
 bur-0.038
oppy-0.038
opsy-0.037
 Remy-0.034
Token.
Token ID13
Feature activation-2.16e-03

Pos logit contributions
folk+0.857
 digits+0.834
 Amen+0.780
 cheering+0.731
 winners+0.724
Neg logit contributions
oppy-0.625
opsy-0.616
chy-0.586
 bur-0.565
 Remy-0.552
Token Lily
Token ID20037
Feature activation+1.78e-02

Pos logit contributions
folk+0.004
 digits+0.004
 sale+0.004
epad+0.004
 customer+0.003
Neg logit contributions
opsy-0.004
oppy-0.004
 Remy-0.004
 bur-0.004
chy-0.003
Token was
Token ID373
Feature activation+5.29e-02

Pos logit contributions
opsy+0.032
oppy+0.032
 Remy+0.029
 bur+0.028
chy+0.028
Neg logit contributions
folk-0.034
 digits-0.033
 sale-0.030
epad-0.029
 customer-0.029
Token scared
Token ID12008
Feature activation+9.02e-02

Pos logit contributions
opsy+0.078
chy+0.074
oppy+0.073
 Remy+0.070
 bur+0.069
Neg logit contributions
folk-0.112
 digits-0.109
 occasions-0.098
boxes-0.098
 sale-0.097
Token because
Token ID780
Feature activation+1.54e-01

Pos logit contributions
opsy+0.193
oppy+0.188
 Remy+0.172
chy+0.167
 bur+0.167
Neg logit contributions
folk-0.139
 digits-0.135
 sale-0.130
 customer-0.120
 letters-0.119
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
folk+0.224
 digits+0.218
 sale+0.204
 customer+0.189
 letters+0.187
Neg logit contributions
opsy-0.318
oppy-0.313
 Remy-0.290
 bur-0.282
chy-0.280
Token He
Token ID679
Feature activation-3.40e-02

Pos logit contributions
folk+0.022
 digits+0.021
 sale+0.019
epad+0.018
 cheering+0.018
Neg logit contributions
oppy-0.028
opsy-0.028
 Remy-0.027
chy-0.025
 bur-0.025
Token is
Token ID318
Feature activation+3.02e-02

Pos logit contributions
 digits+0.052
folk+0.051
 sale+0.049
 letters+0.046
 customer+0.045
Neg logit contributions
opsy-0.073
oppy-0.069
 Remy-0.065
 bur-0.063
chy-0.061
Token not
Token ID407
Feature activation+1.30e-02

Pos logit contributions
oppy+0.056
opsy+0.055
 Remy+0.054
chy+0.053
 bur+0.051
Neg logit contributions
folk-0.054
 digits-0.051
 sale-0.046
 Amen-0.044
bench-0.043
Token for
Token ID329
Feature activation+1.12e-01

Pos logit contributions
oppy+0.022
 Remy+0.022
opsy+0.022
chy+0.021
 bur+0.019
Neg logit contributions
folk-0.025
 digits-0.022
 Amen-0.022
 sale-0.020
 salesman-0.019
Token sale
Token ID5466
Feature activation-4.18e-01

Pos logit contributions
oppy+0.203
 Remy+0.202
opsy+0.195
 bur+0.189
 Ho+0.175
Neg logit contributions
folk-0.197
 digits-0.184
 Amen-0.176
bench-0.175
boxes-0.165
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
folk+0.869
 digits+0.857
 Amen+0.848
 cheering+0.768
Gu+0.756
Neg logit contributions
oppy-0.602
chy-0.560
 Remy-0.535
opsy-0.532
uffy-0.509
Token Please
Token ID4222
Feature activation-1.90e-01

Pos logit contributions
folk+0.023
 digits+0.022
 sale+0.020
 cheering+0.020
epad+0.019
Neg logit contributions
oppy-0.027
opsy-0.026
 Remy-0.026
 bur-0.023
chy-0.023
Token,
Token ID11
Feature activation-4.80e-02

Pos logit contributions
folk+0.360
 digits+0.340
 sale+0.303
epad+0.300
bench+0.298
Neg logit contributions
oppy-0.352
opsy-0.345
 Remy-0.323
chy-0.305
uffy-0.297
Token put
Token ID1234
Feature activation-5.67e-02

Pos logit contributions
folk+0.083
 digits+0.080
 sale+0.074
bench+0.069
 letters+0.069
Neg logit contributions
oppy-0.093
opsy-0.092
 Remy-0.087
chy-0.082
 bur-0.082
Token him
Token ID683
Feature activation-1.72e-03

Pos logit contributions
folk+0.101
 digits+0.096
epad+0.089
 sale+0.086
 Amen+0.085
Neg logit contributions
oppy-0.101
 Remy-0.101
opsy-0.099
 bur-0.091
 Lucky-0.089
TokenT
Token ID51
Feature activation+1.36e-01

Pos logit contributions
 digits+0.243
folk+0.242
 invitations+0.229
epad+0.222
 sale+0.221
Neg logit contributions
opsy-0.223
 Remy-0.203
oppy-0.195
chy-0.185
 bur-0.180
Tokenoys
Token ID19417
Feature activation-1.30e-01

Pos logit contributions
opsy+0.306
oppy+0.303
 Remy+0.282
 bur+0.276
chy+0.276
Neg logit contributions
folk-0.192
 digits-0.187
 sale-0.174
 customer-0.159
 letters-0.157
Token and
Token ID290
Feature activation+2.53e-02

Pos logit contributions
folk+0.199
 digits+0.193
 sale+0.177
 customer+0.165
 letters+0.162
Neg logit contributions
opsy-0.273
oppy-0.273
 Remy-0.253
chy-0.246
 bur-0.244
Token books
Token ID3835
Feature activation-1.19e-01

Pos logit contributions
oppy+0.048
opsy+0.047
 Remy+0.045
 bur+0.043
chy+0.042
Neg logit contributions
folk-0.045
 digits-0.043
 sale-0.040
epad-0.038
 customer-0.037
Token for
Token ID329
Feature activation+1.14e-01

Pos logit contributions
folk+0.211
 digits+0.208
 sale+0.187
 customer+0.180
 Amen+0.178
Neg logit contributions
oppy-0.216
opsy-0.215
chy-0.199
 Remy-0.199
 bur-0.190
Token sale
Token ID5466
Feature activation-4.18e-01

Pos logit contributions
 Remy+0.199
oppy+0.195
opsy+0.195
 bur+0.193
 Ho+0.175
Neg logit contributions
folk-0.214
 digits-0.193
bench-0.179
epad-0.172
 salesman-0.171
Token!
Token ID0
Feature activation+9.41e-02

Pos logit contributions
folk+0.827
 digits+0.801
 Amen+0.771
 jury+0.700
 cheering+0.696
Neg logit contributions
oppy-0.661
opsy-0.623
 Remy-0.604
chy-0.594
uffy-0.565
Token One
Token ID1881
Feature activation-9.39e-02

Pos logit contributions
oppy+0.178
opsy+0.177
 Remy+0.173
 bur+0.155
 Lucky+0.154
Neg logit contributions
folk-0.159
 digits-0.154
 sale-0.137
bench-0.135
epad-0.134
Token dollar
Token ID8872
Feature activation-2.60e-01

Pos logit contributions
folk+0.166
 digits+0.161
epad+0.144
 sale+0.143
 jury+0.139
Neg logit contributions
opsy-0.177
oppy-0.175
 Remy-0.162
chy-0.159
 bur-0.155
Token each
Token ID1123
Feature activation+1.39e-02

Pos logit contributions
folk+0.473
 digits+0.456
 Amen+0.431
epad+0.414
 cheering+0.406
Neg logit contributions
oppy-0.457
opsy-0.456
 Remy-0.435
 bur-0.400
chy-0.398
Token!"
Token ID2474
Feature activation-8.69e-02

Pos logit contributions
opsy+0.029
oppy+0.028
 Remy+0.027
chy+0.026
 bur+0.025
Neg logit contributions
folk-0.021
 digits-0.021
 Amen-0.018
epad-0.018
 sale-0.018
Token these
Token ID777
Feature activation-1.38e-01

Pos logit contributions
folk+0.035
 digits+0.035
 sale+0.032
 customer+0.030
 letters+0.030
Neg logit contributions
opsy-0.042
oppy-0.041
 Remy-0.038
chy-0.037
 bur-0.037
Token carrots
Token ID34397
Feature activation+1.75e-01

Pos logit contributions
folk+0.199
 digits+0.185
 letters+0.184
 sale+0.180
 prices+0.168
Neg logit contributions
opsy-0.308
oppy-0.299
chy-0.271
 Remy-0.268
 bur-0.266
Token are
Token ID389
Feature activation+1.66e-02

Pos logit contributions
opsy+0.396
oppy+0.384
 Remy+0.359
 bur+0.345
rig+0.334
Neg logit contributions
folk-0.242
 sale-0.225
 digits-0.224
 letters-0.204
 winners-0.196
Token not
Token ID407
Feature activation+1.70e-02

Pos logit contributions
opsy+0.035
oppy+0.035
 Remy+0.030
uffy+0.030
 bur+0.030
Neg logit contributions
 sale-0.024
folk-0.024
 digits-0.024
 letters-0.022
 customer-0.022
Token for
Token ID329
Feature activation+1.14e-01

Pos logit contributions
opsy+0.034
oppy+0.033
 Remy+0.031
chy+0.030
 bur+0.030
Neg logit contributions
folk-0.028
 digits-0.028
 sale-0.026
 customer-0.024
 letters-0.024
Token sale
Token ID5466
Feature activation-4.18e-01

Pos logit contributions
opsy+0.221
oppy+0.220
 Remy+0.209
 bur+0.200
chy+0.194
Neg logit contributions
folk-0.193
 digits-0.190
 sale-0.166
bench-0.162
 customer-0.162
Token.
Token ID13
Feature activation-7.04e-03

Pos logit contributions
folk+0.733
 digits+0.727
 Amen+0.651
 sale+0.645
 customer+0.628
Neg logit contributions
oppy-0.775
opsy-0.760
 Remy-0.709
chy-0.707
 bur-0.677
Token They
Token ID1119
Feature activation-3.36e-02

Pos logit contributions
folk+0.010
 digits+0.010
 sale+0.009
 customer+0.008
 letters+0.008
Neg logit contributions
opsy-0.016
oppy-0.015
 Remy-0.014
chy-0.014
 bur-0.014
Token are
Token ID389
Feature activation+1.78e-02

Pos logit contributions
folk+0.054
 digits+0.052
 sale+0.049
 letters+0.046
 customer+0.045
Neg logit contributions
opsy-0.069
oppy-0.068
 Remy-0.062
 bur-0.060
chy-0.060
Token for
Token ID329
Feature activation+1.15e-01

Pos logit contributions
opsy+0.035
oppy+0.035
 Remy+0.031
 bur+0.030
chy+0.030
Neg logit contributions
folk-0.029
 digits-0.028
 sale-0.028
 letters-0.026
 customer-0.026
Token our
Token ID674
Feature activation+6.26e-02

Pos logit contributions
opsy+0.244
oppy+0.242
 Remy+0.232
 bur+0.223
chy+0.216
Neg logit contributions
folk-0.175
 digits-0.170
 sale-0.146
bench-0.143
epad-0.142
Token.
Token ID13
Feature activation-9.16e-03

Pos logit contributions
opsy+0.237
oppy+0.230
 Remy+0.214
 bur+0.210
chy+0.203
Neg logit contributions
folk-0.141
 sale-0.136
 digits-0.135
 customer-0.124
 letters-0.120
Token He
Token ID679
Feature activation-2.83e-02

Pos logit contributions
folk+0.010
 digits+0.010
 Amen+0.009
 sale+0.009
 customer+0.009
Neg logit contributions
opsy-0.023
oppy-0.022
 bur-0.021
chy-0.021
rig-0.020
Token is
Token ID318
Feature activation+3.58e-02

Pos logit contributions
 digits+0.039
folk+0.039
 sale+0.038
 letters+0.037
 customer+0.035
Neg logit contributions
opsy-0.063
oppy-0.060
 Remy-0.056
 bur-0.054
rig-0.052
Token not
Token ID407
Feature activation+1.72e-02

Pos logit contributions
opsy+0.069
oppy+0.068
 Remy+0.065
chy+0.063
 bur+0.062
Neg logit contributions
folk-0.063
 digits-0.060
 sale-0.054
 customer-0.050
 Amen-0.050
Token for
Token ID329
Feature activation+1.15e-01

Pos logit contributions
opsy+0.030
oppy+0.030
 Remy+0.029
chy+0.029
 bur+0.027
Neg logit contributions
folk-0.033
 digits-0.031
 sale-0.027
 Amen-0.027
 salesman-0.026
Token sale
Token ID5466
Feature activation-4.18e-01

Pos logit contributions
oppy+0.208
 Remy+0.207
opsy+0.204
 bur+0.195
 Ho+0.181
Neg logit contributions
folk-0.206
 digits-0.195
bench-0.179
 Amen-0.176
 salesman-0.173
Token.
Token ID13
Feature activation-8.68e-03

Pos logit contributions
folk+0.875
 digits+0.867
 Amen+0.856
 cheering+0.775
 banners+0.756
Neg logit contributions
oppy-0.594
chy-0.560
 Remy-0.530
opsy-0.516
uffy-0.503
Token He
Token ID679
Feature activation-2.73e-02

Pos logit contributions
folk+0.013
 digits+0.012
 sale+0.011
 customer+0.011
 letters+0.010
Neg logit contributions
opsy-0.019
oppy-0.019
 Remy-0.017
chy-0.017
 bur-0.017
Token is
Token ID318
Feature activation+3.71e-02

Pos logit contributions
 digits+0.040
folk+0.039
 sale+0.038
 letters+0.037
 customer+0.035
Neg logit contributions
opsy-0.060
oppy-0.057
 Remy-0.053
 bur-0.052
chy-0.049
Token my
Token ID616
Feature activation+2.34e-03

Pos logit contributions
opsy+0.069
oppy+0.069
 Remy+0.066
chy+0.065
 bur+0.063
Neg logit contributions
folk-0.066
 digits-0.063
 sale-0.057
 Amen-0.053
 salesman-0.053
Token friend
Token ID1545
Feature activation-1.73e-02

Pos logit contributions
opsy+0.005
oppy+0.005
 Remy+0.004
chy+0.004
 bur+0.004
Neg logit contributions
folk-0.004
 digits-0.004
 sale-0.004
 customer-0.003
 letters-0.003
Token's
Token ID338
Feature activation+9.19e-02

Pos logit contributions
folk+0.198
 digits+0.187
 sale+0.182
 letters+0.174
 customer+0.164
Neg logit contributions
opsy-0.274
oppy-0.264
 Remy-0.247
 bur-0.242
rig-0.229
Token yard
Token ID12699
Feature activation+9.43e-02

Pos logit contributions
opsy+0.193
oppy+0.191
 Remy+0.177
chy+0.171
 bur+0.170
Neg logit contributions
folk-0.141
 digits-0.139
 sale-0.132
 letters-0.122
 customer-0.122
Token was
Token ID373
Feature activation+5.41e-02

Pos logit contributions
opsy+0.187
oppy+0.183
 Remy+0.169
 bur+0.162
chy+0.160
Neg logit contributions
folk-0.160
 digits-0.155
 sale-0.148
 letters-0.138
 customer-0.136
Token not
Token ID407
Feature activation+2.46e-02

Pos logit contributions
opsy+0.093
oppy+0.092
chy+0.089
 Remy+0.087
 bur+0.086
Neg logit contributions
folk-0.103
 digits-0.100
 sale-0.088
 Amen-0.085
 customer-0.085
Token for
Token ID329
Feature activation+1.18e-01

Pos logit contributions
opsy+0.040
oppy+0.040
chy+0.040
 Remy+0.039
 bur+0.037
Neg logit contributions
folk-0.047
 digits-0.046
 Amen-0.041
 sale-0.040
 jury-0.039
Token sale
Token ID5466
Feature activation-4.18e-01

Pos logit contributions
oppy+0.216
 Remy+0.215
opsy+0.210
 bur+0.209
chy+0.190
Neg logit contributions
folk-0.194
 digits-0.189
 Amen-0.186
bench-0.170
 salesman-0.164
Token.
Token ID13
Feature activation-1.34e-03

Pos logit contributions
 digits+0.755
folk+0.755
 Amen+0.722
 sale+0.654
 cheering+0.649
Neg logit contributions
oppy-0.732
opsy-0.701
chy-0.683
 Remy-0.658
 bur-0.632
Token Tim
Token ID5045
Feature activation+7.20e-02

Pos logit contributions
folk+0.002
 digits+0.002
 sale+0.002
 customer+0.002
epad+0.002
Neg logit contributions
opsy-0.002
oppy-0.002
 Remy-0.002
 bur-0.002
chy-0.002
Tokenmy
Token ID1820
Feature activation-1.28e-01

Pos logit contributions
opsy+0.179
oppy+0.177
 Remy+0.165
chy+0.163
 bur+0.162
Neg logit contributions
folk-0.086
 digits-0.083
 sale-0.076
 customer-0.068
 letters-0.066
Token was
Token ID373
Feature activation+5.53e-02

Pos logit contributions
folk+0.217
 digits+0.211
 sale+0.199
 customer+0.186
 letters+0.185
Neg logit contributions
opsy-0.249
oppy-0.246
 Remy-0.227
chy-0.219
 bur-0.218
Token very
Token ID845
Feature activation-3.52e-02

Pos logit contributions
opsy+0.094
oppy+0.091
 Remy+0.086
chy+0.086
 bur+0.083
Neg logit contributions
folk-0.108
 digits-0.107
 sale-0.096
epad-0.092
boxes-0.092
Token old
Token ID1468
Feature activation+4.50e-03

Pos logit contributions
folk+0.075
 digits+0.069
epad+0.064
 Amen+0.063
bench+0.062
Neg logit contributions
opsy-0.102
oppy-0.100
 Remy-0.093
 bur-0.092
uffy-0.088
Token toys
Token ID14958
Feature activation-1.48e-01

Pos logit contributions
opsy+0.008
 bur+0.008
oppy+0.008
 Remy+0.008
uffy+0.007
Neg logit contributions
folk-0.007
 digits-0.007
 Amen-0.007
epad-0.007
Adam-0.006
Token at
Token ID379
Feature activation+6.58e-02

Pos logit contributions
folk+0.263
 digits+0.262
 sale+0.231
 Amen+0.228
epad+0.222
Neg logit contributions
oppy-0.272
opsy-0.271
 Remy-0.248
chy-0.247
 bur-0.240
Token a
Token ID257
Feature activation+7.54e-03

Pos logit contributions
oppy+0.117
opsy+0.116
 Remy+0.110
 bur+0.106
chy+0.100
Neg logit contributions
folk-0.123
 digits-0.120
epad-0.105
 Amen-0.103
 sale-0.103
Token garage
Token ID15591
Feature activation-2.65e-02

Pos logit contributions
opsy+0.015
oppy+0.015
 Remy+0.014
 bur+0.014
chy+0.013
Neg logit contributions
folk-0.013
 digits-0.012
 sale-0.011
 letters-0.010
epad-0.010
Token sale
Token ID5466
Feature activation-4.17e-01

Pos logit contributions
 digits+0.055
folk+0.054
 Amen+0.050
 cheering+0.046
 letters+0.046
Neg logit contributions
chy-0.037
oppy-0.037
 bur-0.036
opsy-0.035
 Remy-0.033
Token.
Token ID13
Feature activation-1.92e-03

Pos logit contributions
folk+0.851
 digits+0.829
 Amen+0.774
 cheering+0.734
 winners+0.722
Neg logit contributions
oppy-0.637
opsy-0.618
chy-0.594
 Remy-0.566
 bur-0.560
Token Tim
Token ID5045
Feature activation+7.11e-02

Pos logit contributions
folk+0.004
 digits+0.004
 sale+0.003
epad+0.003
 customer+0.003
Neg logit contributions
opsy-0.003
oppy-0.003
 Remy-0.003
 bur-0.003
chy-0.003
Tokenmy
Token ID1820
Feature activation-1.32e-01

Pos logit contributions
opsy+0.172
oppy+0.171
 Remy+0.158
chy+0.156
 bur+0.156
Neg logit contributions
folk-0.091
 digits-0.086
 sale-0.080
 customer-0.071
 jury-0.070
Token thought
Token ID1807
Feature activation-1.60e-01

Pos logit contributions
folk+0.234
 digits+0.225
 sale+0.207
epad+0.200
 customer+0.195
Neg logit contributions
opsy-0.252
oppy-0.249
 Remy-0.227
 bur-0.222
chy-0.221
Token it
Token ID340
Feature activation-1.26e-01

Pos logit contributions
folk+0.239
 digits+0.236
 sale+0.230
 customer+0.207
 letters+0.207
Neg logit contributions
opsy-0.350
oppy-0.340
 Remy-0.311
 bur-0.309
chy-0.304
Tokenens
Token ID641
Feature activation+3.57e-01

Pos logit contributions
opsy+0.620
oppy+0.607
 bur+0.589
rig+0.580
 web+0.524
Neg logit contributions
folk-0.725
 letters-0.716
 ones-0.710
 customer-0.698
 digits-0.698
Token by
Token ID416
Feature activation+4.97e-02

Pos logit contributions
opsy+0.968
oppy+0.914
rig+0.901
 Remy+0.823
uffy+0.799
Neg logit contributions
 sale-0.347
folk-0.291
 letters-0.283
 cheering-0.270
 digits-0.267
Token mistake
Token ID7457
Feature activation+4.69e-02

Pos logit contributions
opsy+0.103
oppy+0.100
 Remy+0.097
 bur+0.093
chy+0.092
Neg logit contributions
folk-0.081
 digits-0.078
 sale-0.069
 customer-0.066
 Amen-0.066
Token.
Token ID13
Feature activation-5.35e-03

Pos logit contributions
opsy+0.118
oppy+0.114
rig+0.106
 bur+0.104
chy+0.103
Neg logit contributions
folk-0.053
 sale-0.050
 digits-0.049
 letters-0.048
 cheering-0.043
Token Mitt
Token ID16627
Feature activation+4.15e-01

Pos logit contributions
 sale+0.007
folk+0.006
 digits+0.006
 customer+0.006
 letters+0.005
Neg logit contributions
opsy-0.012
oppy-0.012
rig-0.011
chy-0.011
 bur-0.010
Tokenens
Token ID641
Feature activation+3.57e-01

Pos logit contributions
opsy+0.646
oppy+0.631
 bur+0.611
rig+0.586
 web+0.534
Neg logit contributions
 ones-0.676
folk-0.676
 digits-0.667
 letters-0.661
 customer-0.654
Token was
Token ID373
Feature activation+5.25e-02

Pos logit contributions
opsy+0.823
oppy+0.807
rig+0.776
 Remy+0.717
chy+0.692
Neg logit contributions
folk-0.440
 sale-0.425
 digits-0.423
 letters-0.388
 begged-0.379
Token upset
Token ID9247
Feature activation-2.50e-02

Pos logit contributions
opsy+0.109
oppy+0.109
 Remy+0.099
 bur+0.096
chy+0.094
Neg logit contributions
folk-0.080
 digits-0.079
 sale-0.077
 customer-0.071
 cheering-0.070
Token and
Token ID290
Feature activation+3.01e-02

Pos logit contributions
 sale+0.023
folk+0.022
 digits+0.022
 cheering+0.021
 letters+0.020
Neg logit contributions
opsy-0.067
oppy-0.064
rig-0.058
 bur-0.057
 Remy-0.056
Token said
Token ID531
Feature activation-1.53e-02

Pos logit contributions
opsy+0.071
oppy+0.069
rig+0.065
uffy+0.061
 bur+0.057
Neg logit contributions
folk-0.034
 begged-0.034
 sale-0.033
 asked-0.032
 letters-0.032
Token,
Token ID11
Feature activation-3.94e-02

Pos logit contributions
folk+0.022
 digits+0.021
 sale+0.020
 customer+0.018
 letters+0.018
Neg logit contributions
opsy-0.034
oppy-0.034
 Remy-0.031
chy-0.031
 bur-0.030
Token Spot
Token ID15899
Feature activation+2.29e-01

Pos logit contributions
folk+0.013
 sale+0.013
 digits+0.012
 customer+0.012
 letters+0.012
Neg logit contributions
opsy-0.015
oppy-0.014
chy-0.013
 bur-0.013
rig-0.013
Token and
Token ID290
Feature activation+3.40e-02

Pos logit contributions
opsy+0.533
oppy+0.525
 bur+0.478
rig+0.470
chy+0.469
Neg logit contributions
folk-0.283
 sale-0.275
 digits-0.261
 customer-0.252
 letters-0.239
Token a
Token ID257
Feature activation+9.00e-03

Pos logit contributions
opsy+0.068
oppy+0.068
chy+0.060
rig+0.059
 bur+0.058
Neg logit contributions
folk-0.054
 digits-0.053
 sale-0.052
 customer-0.052
 letters-0.050
Token cat
Token ID3797
Feature activation+1.10e-01

Pos logit contributions
opsy+0.017
oppy+0.017
 Remy+0.015
chy+0.015
 bur+0.015
Neg logit contributions
folk-0.015
 digits-0.015
 sale-0.014
 customer-0.014
 letters-0.014
Token named
Token ID3706
Feature activation-6.74e-03

Pos logit contributions
opsy+0.261
oppy+0.255
 Remy+0.231
chy+0.227
 bur+0.224
Neg logit contributions
folk-0.138
 sale-0.133
 digits-0.131
 customer-0.116
 letters-0.116
Token Fl
Token ID1610
Feature activation+3.84e-01

Pos logit contributions
folk+0.012
 sale+0.012
 customer+0.011
 digits+0.010
 letters+0.010
Neg logit contributions
opsy-0.012
oppy-0.012
rig-0.011
 bur-0.011
chy-0.011
Tokenuffy
Token ID15352
Feature activation+4.61e-01

Pos logit contributions
chy+0.350
rig+0.286
 Remy+0.286
 refreshing+0.264
 web+0.254
Neg logit contributions
folk-0.909
 sale-0.903
 customer-0.902
 digits-0.897
 number-0.842
Token.
Token ID13
Feature activation+2.45e-03

Pos logit contributions
opsy+1.120
oppy+1.101
 bur+0.995
 Remy+0.990
chy+0.969
Neg logit contributions
folk-0.555
 sale-0.536
 digits-0.504
 customer-0.470
 letters-0.460
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
oppy+0.005
opsy+0.005
chy+0.005
 bur+0.005
 Remy+0.005
Neg logit contributions
folk-0.004
 digits-0.003
 sale-0.003
 customer-0.003
 Amen-0.003
Token
Token ID198
Feature activation+2.52e-02

Pos logit contributions
opsy+0.048
oppy+0.048
 Remy+0.045
 bur+0.042
chy+0.042
Neg logit contributions
folk-0.043
 digits-0.042
 sale-0.039
 letters-0.037
epad-0.037
TokenOne
Token ID3198
Feature activation-1.34e-01

Pos logit contributions
opsy+0.059
oppy+0.057
 Remy+0.056
 bur+0.053
chy+0.052
Neg logit contributions
folk-0.034
 digits-0.032
 sale-0.029
epad-0.028
 letters-0.027
Token cat
Token ID3797
Feature activation+1.15e-01

Pos logit contributions
opsy+0.010
oppy+0.010
 Remy+0.009
chy+0.009
 bur+0.009
Neg logit contributions
folk-0.009
 digits-0.009
 sale-0.009
 customer-0.008
 letters-0.008
Token named
Token ID3706
Feature activation-9.07e-04

Pos logit contributions
opsy+0.262
oppy+0.259
 Remy+0.236
 bur+0.233
chy+0.232
Neg logit contributions
folk-0.152
 digits-0.147
 sale-0.143
 customer-0.128
 Amen-0.127
Token Mitt
Token ID16627
Feature activation+4.19e-01

Pos logit contributions
 sale+0.001
 digits+0.001
 customer+0.001
folk+0.001
 number+0.001
Neg logit contributions
opsy-0.002
oppy-0.002
rig-0.002
 bur-0.002
chy-0.002
Tokenens
Token ID641
Feature activation+3.58e-01

Pos logit contributions
oppy+0.641
opsy+0.631
rig+0.628
 bur+0.594
 web+0.583
Neg logit contributions
 ones-0.675
folk-0.665
 customer-0.657
 sale-0.644
bench-0.628
Token.
Token ID13
Feature activation+4.57e-03

Pos logit contributions
opsy+0.945
oppy+0.930
rig+0.857
 bur+0.845
uffy+0.828
Neg logit contributions
 sale-0.342
folk-0.328
 digits-0.296
 customer-0.275
 letters-0.274
Token Mitt
Token ID16627
Feature activation+4.20e-01

Pos logit contributions
opsy+0.006
oppy+0.006
rig+0.006
chy+0.005
 bur+0.005
Neg logit contributions
 digits-0.009
 sale-0.009
folk-0.009
 letters-0.009
 customer-0.009
Tokenens
Token ID641
Feature activation+3.59e-01

Pos logit contributions
oppy+0.642
opsy+0.621
 bur+0.589
rig+0.575
 web+0.543
Neg logit contributions
 ones-0.681
 digits-0.662
bench-0.657
folk-0.656
 letters-0.651
Token loved
Token ID6151
Feature activation+3.92e-02

Pos logit contributions
opsy+0.864
oppy+0.858
rig+0.798
 bur+0.766
 Remy+0.757
Neg logit contributions
folk-0.384
 sale-0.378
 digits-0.367
 letters-0.347
 number-0.344
Token to
Token ID284
Feature activation+4.61e-03

Pos logit contributions
oppy+0.094
opsy+0.094
chy+0.083
uffy+0.081
rig+0.081
Neg logit contributions
 sale-0.048
 digits-0.048
folk-0.046
 letters-0.044
 customer-0.043
Token play
Token ID711
Feature activation+5.72e-02

Pos logit contributions
opsy+0.010
oppy+0.010
uffy+0.009
rig+0.009
 Remy+0.009
Neg logit contributions
 sale-0.006
 digits-0.006
folk-0.006
 number-0.006
 letters-0.006
Token with
Token ID351
Feature activation-8.52e-02

Pos logit contributions
opsy+0.137
oppy+0.135
chy+0.122
 Remy+0.121
 bur+0.119
Neg logit contributions
folk-0.071
 digits-0.070
 sale-0.069
 customer-0.061
 letters-0.061
Token was
Token ID373
Feature activation+4.71e-02

Pos logit contributions
 digits+0.144
folk+0.143
 sale+0.141
 number+0.123
 cheering+0.123
Neg logit contributions
opsy-0.305
oppy-0.303
 Remy-0.279
 bur-0.279
rig-0.276
Token a
Token ID257
Feature activation+3.51e-03

Pos logit contributions
oppy+0.119
opsy+0.116
 bur+0.107
chy+0.106
 Remy+0.106
Neg logit contributions
 sale-0.049
 digits-0.048
folk-0.047
 customer-0.044
 letters-0.042
Token little
Token ID1310
Feature activation+5.96e-02

Pos logit contributions
oppy+0.007
opsy+0.007
 Remy+0.007
chy+0.007
 bur+0.007
Neg logit contributions
 digits-0.005
 customer-0.005
folk-0.005
 sale-0.005
 Amen-0.004
Token rabbit
Token ID22746
Feature activation+2.00e-01

Pos logit contributions
opsy+0.145
oppy+0.144
chy+0.136
 Remy+0.135
rig+0.131
Neg logit contributions
folk-0.066
 digits-0.063
 customer-0.058
 sale-0.058
 letters-0.054
Token named
Token ID3706
Feature activation-1.05e-02

Pos logit contributions
opsy+0.491
oppy+0.487
 Remy+0.447
chy+0.447
rig+0.445
Neg logit contributions
folk-0.198
 sale-0.196
 digits-0.192
 Amen-0.184
 customer-0.169
Token Remy
Token ID32912
Feature activation+5.27e-01

Pos logit contributions
 sale+0.014
 digits+0.013
 customer+0.012
 one+0.012
 number+0.012
Neg logit contributions
opsy-0.022
rig-0.021
oppy-0.020
chy-0.019
uffy-0.018
Token.
Token ID13
Feature activation-7.68e-03

Pos logit contributions
opsy+1.454
oppy+1.419
rig+1.354
uffy+1.344
 bur+1.339
Neg logit contributions
 sale-0.295
 digits-0.271
 one-0.255
 asked-0.238
 letters-0.236
Token Remy
Token ID32912
Feature activation+5.28e-01

Pos logit contributions
 digits+0.017
 ones+0.017
 number+0.016
 sale+0.016
 letters+0.016
Neg logit contributions
rig-0.008
opsy-0.008
oppy-0.008
chy-0.006
iqu-0.006
Token loved
Token ID6151
Feature activation+2.90e-02

Pos logit contributions
opsy+1.299
oppy+1.261
rig+1.197
 bur+1.159
 Remy+1.141
Neg logit contributions
 digits-0.469
 sale-0.454
 asked-0.453
 letters-0.453
 number-0.451
Token to
Token ID284
Feature activation-5.23e-03

Pos logit contributions
oppy+0.071
opsy+0.070
chy+0.064
uffy+0.063
rig+0.063
Neg logit contributions
 sale-0.033
 digits-0.033
 letters-0.032
folk-0.030
 customer-0.029
Token spring
Token ID6076
Feature activation+2.18e-01

Pos logit contributions
 digits+0.008
 sale+0.008
 number+0.007
folk+0.007
 letters+0.007
Neg logit contributions
opsy-0.011
oppy-0.010
uffy-0.010
rig-0.009
chy-0.009
Token.
Token ID13
Feature activation-1.05e-05

Pos logit contributions
opsy+0.024
oppy+0.024
 Remy+0.022
 bur+0.021
chy+0.020
Neg logit contributions
folk-0.013
 digits-0.012
 sale-0.012
 letters-0.011
 cheering-0.011
Token She
Token ID1375
Feature activation+2.86e-02

Pos logit contributions
folk+0.000
 digits+0.000
 sale+0.000
 letters+0.000
 Amen+0.000
Neg logit contributions
oppy-0.000
opsy-0.000
chy-0.000
 bur-0.000
rig-0.000
Token wanted
Token ID2227
Feature activation-1.06e-01

Pos logit contributions
opsy+0.069
oppy+0.069
 Remy+0.062
chy+0.061
 bur+0.060
Neg logit contributions
folk-0.033
 digits-0.032
 sale-0.030
 letters-0.028
 Amen-0.027
Token Kitty
Token ID21168
Feature activation+2.12e-01

Pos logit contributions
folk+0.160
 digits+0.157
 sale+0.150
 customer+0.138
 letters+0.136
Neg logit contributions
opsy-0.227
oppy-0.225
 Remy-0.204
chy-0.201
 bur-0.200
Token and
Token ID290
Feature activation+3.29e-02

Pos logit contributions
opsy+0.553
oppy+0.537
 bur+0.489
 Remy+0.481
rig+0.476
Neg logit contributions
 sale-0.219
folk-0.205
 letters-0.193
 digits-0.187
 customer-0.180
Token Bunny
Token ID28683
Feature activation+4.08e-01

Pos logit contributions
opsy+0.070
oppy+0.068
chy+0.061
rig+0.061
 bur+0.059
Neg logit contributions
folk-0.050
 digits-0.047
 sale-0.046
 letters-0.043
 customer-0.042
Token to
Token ID284
Feature activation-1.63e-03

Pos logit contributions
opsy+0.882
oppy+0.866
 Remy+0.797
 bur+0.775
chy+0.771
Neg logit contributions
folk-0.614
 digits-0.595
 sale-0.564
 letters-0.519
 customer-0.516
Token be
Token ID307
Feature activation-4.27e-02

Pos logit contributions
folk+0.003
 digits+0.003
 sale+0.002
 customer+0.002
 letters+0.002
Neg logit contributions
opsy-0.003
oppy-0.003
 Remy-0.003
chy-0.003
 bur-0.003
Token friends
Token ID2460
Feature activation-6.16e-02

Pos logit contributions
folk+0.097
 digits+0.091
 sale+0.082
person+0.081
 alphabet+0.079
Neg logit contributions
opsy-0.060
oppy-0.060
chy-0.057
 bur-0.056
 Remy-0.055
Token again
Token ID757
Feature activation-2.98e-02

Pos logit contributions
folk+0.120
 digits+0.119
 sale+0.105
 letters+0.101
 jury+0.100
Neg logit contributions
opsy-0.107
oppy-0.106
 Remy-0.097
chy-0.097
 bur-0.096
Token.
Token ID13
Feature activation+9.03e-04

Pos logit contributions
folk+0.052
 digits+0.050
 sale+0.046
 customer+0.043
 letters+0.043
Neg logit contributions
opsy-0.058
oppy-0.058
 Remy-0.054
 bur-0.052
chy-0.052
Token Suddenly
Token ID24975
Feature activation-5.74e-02

Pos logit contributions
folk+0.013
 digits+0.012
 sale+0.011
 customer+0.011
 letters+0.010
Neg logit contributions
opsy-0.017
oppy-0.017
 Remy-0.016
 bur-0.015
chy-0.015
Token he
Token ID339
Feature activation+3.08e-02

Pos logit contributions
folk+0.082
 digits+0.080
 sale+0.074
 customer+0.068
 letters+0.068
Neg logit contributions
opsy-0.128
oppy-0.126
 Remy-0.117
chy-0.114
 bur-0.114
Token saw
Token ID2497
Feature activation-4.85e-02

Pos logit contributions
opsy+0.077
oppy+0.075
 Remy+0.072
rig+0.069
chy+0.067
Neg logit contributions
folk-0.034
 digits-0.033
 sale-0.029
 letters-0.027
 cheering-0.026
Token the
Token ID262
Feature activation+2.39e-02

Pos logit contributions
folk+0.081
 digits+0.080
 sale+0.073
 customer+0.069
 Amen+0.069
Neg logit contributions
opsy-0.094
oppy-0.093
 Remy-0.089
 bur-0.085
chy-0.084
Token book
Token ID1492
Feature activation-8.36e-02

Pos logit contributions
opsy+0.052
oppy+0.052
 Remy+0.048
 bur+0.046
chy+0.045
Neg logit contributions
folk-0.035
 digits-0.035
 sale-0.033
 letters-0.031
 customer-0.031
Token tucked
Token ID29779
Feature activation+1.42e-01

Pos logit contributions
folk+0.135
 digits+0.131
 sale+0.126
 letters+0.115
 customer+0.114
Neg logit contributions
opsy-0.174
oppy-0.171
 Remy-0.158
 bur-0.150
chy-0.146
Token away
Token ID1497
Feature activation-2.50e-02

Pos logit contributions
opsy+0.296
oppy+0.293
 Remy+0.269
 bur+0.261
chy+0.261
Neg logit contributions
folk-0.226
 digits-0.217
 sale-0.205
 letters-0.191
 customer-0.190
Token in
Token ID287
Feature activation+2.89e-02

Pos logit contributions
folk+0.038
 digits+0.036
 sale+0.036
 letters+0.032
 customer+0.032
Neg logit contributions
opsy-0.054
oppy-0.053
 Remy-0.049
 bur-0.046
chy-0.046
Token a
Token ID257
Feature activation+5.47e-03

Pos logit contributions
 bur+0.050
opsy+0.049
 Remy+0.048
oppy+0.048
chy+0.045
Neg logit contributions
folk-0.055
 digits-0.052
 Amen-0.045
 jury-0.044
 salesman-0.044
Token corner
Token ID5228
Feature activation-1.63e-01

Pos logit contributions
opsy+0.010
oppy+0.010
 Remy+0.009
chy+0.009
 bur+0.009
Neg logit contributions
folk-0.010
 digits-0.009
 sale-0.009
 customer-0.008
 letters-0.008
Token.
Token ID13
Feature activation-6.55e-03

Pos logit contributions
folk+0.280
 digits+0.275
 sale+0.251
 Amen+0.241
 customer+0.240
Neg logit contributions
opsy-0.302
oppy-0.300
 Remy-0.279
chy-0.276
 bur-0.275
Token tape
Token ID9154
Feature activation-1.00e-01

Pos logit contributions
opsy+0.038
oppy+0.037
 Remy+0.036
rig+0.033
chy+0.033
Neg logit contributions
 letters-0.020
 sale-0.019
 digits-0.019
 presents-0.019
folk-0.018
Token and
Token ID290
Feature activation+2.93e-02

Pos logit contributions
folk+0.157
 digits+0.153
 sale+0.147
 letters+0.138
 customer+0.136
Neg logit contributions
opsy-0.209
oppy-0.205
 Remy-0.190
chy-0.182
 bur-0.181
Token go
Token ID467
Feature activation+7.29e-02

Pos logit contributions
opsy+0.064
oppy+0.063
 Remy+0.058
chy+0.056
 bur+0.056
Neg logit contributions
folk-0.043
 digits-0.043
 sale-0.039
 letters-0.038
 customer-0.037
Token for
Token ID329
Feature activation+1.18e-01

Pos logit contributions
oppy+0.129
opsy+0.127
 Remy+0.119
 bur+0.117
chy+0.115
Neg logit contributions
folk-0.141
 digits-0.132
 sale-0.124
 jury-0.117
 customer-0.117
Token a
Token ID257
Feature activation+8.97e-03

Pos logit contributions
opsy+0.216
oppy+0.215
 Remy+0.205
 bur+0.196
chy+0.193
Neg logit contributions
folk-0.219
 digits-0.205
 sale-0.189
 customer-0.182
 jury-0.179
Token walk
Token ID2513
Feature activation+1.95e-01

Pos logit contributions
opsy+0.015
oppy+0.015
 Remy+0.014
chy+0.013
 bur+0.013
Neg logit contributions
 digits-0.017
folk-0.017
 sale-0.016
 customer-0.016
 letters-0.015
Token in
Token ID287
Feature activation+3.02e-02

Pos logit contributions
opsy+0.356
oppy+0.353
 Remy+0.326
chy+0.326
 bur+0.316
Neg logit contributions
folk-0.353
 digits-0.351
 sale-0.315
 customer-0.301
 jury-0.300
Token the
Token ID262
Feature activation+3.42e-02

Pos logit contributions
opsy+0.056
oppy+0.055
 Remy+0.052
 bur+0.050
chy+0.049
Neg logit contributions
folk-0.055
 digits-0.053
 sale-0.049
 customer-0.046
epad-0.046
Token park
Token ID3952
Feature activation-1.08e-02

Pos logit contributions
oppy+0.085
opsy+0.083
 Remy+0.076
chy+0.075
uffy+0.072
Neg logit contributions
 digits-0.040
 sale-0.037
folk-0.037
 letters-0.035
 customer-0.034
Token.
Token ID13
Feature activation-1.61e-03

Pos logit contributions
folk+0.021
 digits+0.021
 sale+0.018
 Amen+0.018
 jury+0.018
Neg logit contributions
opsy-0.018
oppy-0.018
chy-0.017
 Remy-0.016
 bur-0.016
Token One
Token ID1881
Feature activation-8.40e-02

Pos logit contributions
folk+0.003
 digits+0.003
 sale+0.002
 customer+0.002
 letters+0.002
Neg logit contributions
opsy-0.003
oppy-0.003
 Remy-0.003
chy-0.003
 bur-0.003
Token also
Token ID635
Feature activation+3.96e-02

Pos logit contributions
opsy+0.176
oppy+0.170
 Remy+0.157
 bur+0.153
chy+0.152
Neg logit contributions
folk-0.111
 digits-0.106
 sale-0.102
 letters-0.094
 Amen-0.092
Token made
Token ID925
Feature activation-7.77e-02

Pos logit contributions
opsy+0.088
oppy+0.087
 Remy+0.081
 bur+0.078
chy+0.077
Neg logit contributions
folk-0.055
 digits-0.054
 sale-0.051
 letters-0.047
 customer-0.047
Token Angel
Token ID3905
Feature activation+1.37e-01

Pos logit contributions
 digits+0.099
 sale+0.096
 letters+0.092
folk+0.092
 customer+0.085
Neg logit contributions
opsy-0.181
oppy-0.178
chy-0.161
 Remy-0.161
 bur-0.158
Token wet
Token ID9583
Feature activation+1.61e-01

Pos logit contributions
opsy+0.276
oppy+0.273
 Remy+0.251
chy+0.246
 bur+0.243
Neg logit contributions
folk-0.224
 digits-0.219
 sale-0.204
 customer-0.190
 letters-0.187
Token and
Token ID290
Feature activation+3.61e-02

Pos logit contributions
opsy+0.331
oppy+0.327
 Remy+0.303
chy+0.294
 bur+0.293
Neg logit contributions
folk-0.259
 digits-0.252
 sale-0.235
 customer-0.219
 letters-0.216
Token dirty
Token ID11841
Feature activation+1.01e-01

Pos logit contributions
opsy+0.067
oppy+0.065
 Remy+0.059
rig+0.055
 bur+0.055
Neg logit contributions
folk-0.062
 digits-0.061
 sale-0.058
 letters-0.058
 cheering-0.056
Token.
Token ID13
Feature activation+1.82e-03

Pos logit contributions
opsy+0.203
oppy+0.200
 Remy+0.185
chy+0.184
 bur+0.182
Neg logit contributions
folk-0.163
 digits-0.162
 sale-0.147
 customer-0.138
epad-0.136
Token She
Token ID1375
Feature activation+3.10e-02

Pos logit contributions
opsy+0.004
oppy+0.004
 Remy+0.003
chy+0.003
 bur+0.003
Neg logit contributions
folk-0.003
 digits-0.003
 sale-0.003
 letters-0.002
 Amen-0.002
Token could
Token ID714
Feature activation+1.49e-01

Pos logit contributions
opsy+0.072
oppy+0.070
 Remy+0.066
rig+0.062
 bur+0.061
Neg logit contributions
folk-0.037
 digits-0.036
 letters-0.036
 Amen-0.033
 sale-0.033
Token have
Token ID423
Feature activation-8.01e-02

Pos logit contributions
opsy+0.323
oppy+0.322
 Remy+0.293
rig+0.289
 bur+0.284
Neg logit contributions
 sale-0.191
folk-0.191
 digits-0.188
 Amen-0.175
 customer-0.173
Token been
Token ID587
Feature activation-1.35e-01

Pos logit contributions
folk+0.146
 digits+0.143
 sale+0.135
 customer+0.127
 letters+0.126
Neg logit contributions
opsy-0.146
oppy-0.145
 Remy-0.132
chy-0.127
 bur-0.127
Token:
Token ID25
Feature activation-6.98e-03

Pos logit contributions
folk+0.020
 digits+0.019
 sale+0.017
bench+0.017
 customer+0.017
Neg logit contributions
oppy-0.020
opsy-0.020
 Remy-0.018
chy-0.018
 bur-0.017
Token "
Token ID366
Feature activation-1.25e-01

Pos logit contributions
folk+0.011
 digits+0.010
 sale+0.009
bench+0.009
 letters+0.009
Neg logit contributions
opsy-0.015
oppy-0.015
 Remy-0.014
 bur-0.013
chy-0.013
TokenHello
Token ID15496
Feature activation-1.57e-01

Pos logit contributions
folk+0.202
 digits+0.199
 sale+0.194
 customer+0.176
 letters+0.173
Neg logit contributions
opsy-0.258
oppy-0.245
 Remy-0.232
chy-0.226
 bur-0.222
Token Ab
Token ID2275
Feature activation+6.88e-02

Pos logit contributions
folk+0.261
 digits+0.252
 sale+0.236
bench+0.223
 customer+0.220
Neg logit contributions
opsy-0.317
oppy-0.314
 Remy-0.287
 bur-0.278
chy-0.274
Tokenig
Token ID328
Feature activation+2.65e-01

Pos logit contributions
opsy+0.079
 Remy+0.078
oppy+0.076
chy+0.073
 bur+0.068
Neg logit contributions
 digits-0.162
folk-0.158
 sale-0.148
 customer-0.144
 letters-0.143
Tokenail
Token ID603
Feature activation+2.59e-01

Pos logit contributions
opsy+0.466
oppy+0.457
 Remy+0.424
 bur+0.411
chy+0.407
Neg logit contributions
folk-0.494
 digits-0.482
 sale-0.455
 customer-0.430
 letters-0.424
Token!
Token ID0
Feature activation+9.99e-02

Pos logit contributions
opsy+0.484
oppy+0.483
 Remy+0.437
chy+0.430
 bur+0.419
Neg logit contributions
folk-0.454
 digits-0.449
 sale-0.413
 customer-0.388
epad-0.386
Token I
Token ID314
Feature activation+7.35e-03

Pos logit contributions
oppy+0.209
opsy+0.208
 Remy+0.194
 bur+0.183
chy+0.183
Neg logit contributions
folk-0.154
 digits-0.152
 sale-0.143
 letters-0.132
bench-0.131
Token'm
Token ID1101
Feature activation+6.07e-02

Pos logit contributions
opsy+0.014
oppy+0.014
 Remy+0.013
 bur+0.013
chy+0.013
Neg logit contributions
folk-0.012
 digits-0.012
 sale-0.011
 customer-0.010
 cheering-0.010
Token glad
Token ID9675
Feature activation-6.19e-03

Pos logit contributions
opsy+0.136
oppy+0.135
 Remy+0.126
chy+0.123
 bur+0.122
Neg logit contributions
folk-0.086
 digits-0.083
 sale-0.077
 customer-0.071
 letters-0.070
Token you
Token ID345
Feature activation+8.05e-02

Pos logit contributions
folk+0.010
 digits+0.010
 sale+0.009
 customer+0.009
 letters+0.009
Neg logit contributions
opsy-0.012
oppy-0.012
 Remy-0.011
chy-0.011
 bur-0.011
Token,
Token ID11
Feature activation-3.46e-02

Pos logit contributions
folk+0.002
 digits+0.002
 sale+0.002
 customer+0.002
 letters+0.002
Neg logit contributions
opsy-0.004
oppy-0.004
 Remy-0.003
chy-0.003
 bur-0.003
Token Annie
Token ID25860
Feature activation-6.59e-02

Pos logit contributions
folk+0.048
 digits+0.046
 sale+0.044
 customer+0.040
 letters+0.039
Neg logit contributions
opsy-0.077
oppy-0.076
 bur-0.070
 Remy-0.070
chy-0.070
Token was
Token ID373
Feature activation+5.70e-02

Pos logit contributions
folk+0.081
 digits+0.079
 sale+0.073
 letters+0.068
 customer+0.066
Neg logit contributions
opsy-0.152
oppy-0.149
 Remy-0.144
chy-0.137
rig-0.135
Token feeling
Token ID4203
Feature activation-5.79e-02

Pos logit contributions
opsy+0.131
oppy+0.130
 Remy+0.123
chy+0.118
 bur+0.116
Neg logit contributions
folk-0.074
 digits-0.073
 sale-0.069
 customer-0.064
 cheering-0.062
Token very
Token ID845
Feature activation-3.44e-02

Pos logit contributions
folk+0.072
 digits+0.067
 sale+0.067
 customer+0.065
 cheering+0.063
Neg logit contributions
opsy-0.131
oppy-0.128
 Remy-0.126
uffy-0.120
rig-0.117
Token brave
Token ID14802
Feature activation+1.06e-01

Pos logit contributions
 digits+0.045
folk+0.043
 sale+0.042
 cheering+0.040
 customer+0.040
Neg logit contributions
 Remy-0.070
opsy-0.070
oppy-0.067
ches-0.064
uffy-0.064
Token.
Token ID13
Feature activation+9.44e-04

Pos logit contributions
opsy+0.198
oppy+0.196
 Remy+0.182
chy+0.178
 bur+0.178
Neg logit contributions
folk-0.187
 digits-0.185
 sale-0.171
 customer-0.160
 jury-0.158
Token She
Token ID1375
Feature activation+2.81e-02

Pos logit contributions
opsy+0.002
oppy+0.002
 Remy+0.002
chy+0.002
 bur+0.002
Neg logit contributions
folk-0.002
 digits-0.002
 sale-0.002
 jury-0.001
 customer-0.001
Token decided
Token ID3066
Feature activation-8.81e-02

Pos logit contributions
opsy+0.066
oppy+0.064
 Remy+0.061
 bur+0.057
chy+0.057
Neg logit contributions
 digits-0.036
folk-0.036
 sale-0.033
 letters-0.030
 customer-0.029
Token to
Token ID284
Feature activation+1.93e-03

Pos logit contributions
folk+0.144
 digits+0.140
 sale+0.130
 customer+0.122
 letters+0.120
Neg logit contributions
opsy-0.178
oppy-0.176
 Remy-0.163
chy-0.159
 bur-0.158
Token escape
Token ID6654
Feature activation+1.43e-01

Pos logit contributions
opsy+0.004
oppy+0.003
 Remy+0.003
 bur+0.003
chy+0.003
Neg logit contributions
folk-0.004
 digits-0.003
 sale-0.003
 customer-0.003
 letters-0.003
Token One
Token ID1881
Feature activation-8.60e-02

Pos logit contributions
folk+0.002
 digits+0.002
 sale+0.002
 letters+0.002
epad+0.002
Neg logit contributions
opsy-0.002
oppy-0.002
 Remy-0.002
 bur-0.002
chy-0.002
Token day
Token ID1110
Feature activation-1.18e-03

Pos logit contributions
 sale+0.069
 customer+0.069
folk+0.068
 digits+0.067
 letters+0.064
Neg logit contributions
opsy-0.229
oppy-0.221
 Remy-0.219
 bur-0.209
rig-0.203
Token,
Token ID11
Feature activation-3.52e-02

Pos logit contributions
folk+0.002
 digits+0.002
 sale+0.002
 customer+0.002
 letters+0.002
Neg logit contributions
oppy-0.003
opsy-0.002
 Remy-0.002
chy-0.002
 bur-0.002
Token she
Token ID673
Feature activation+7.93e-02

Pos logit contributions
folk+0.063
 digits+0.062
 sale+0.058
 customer+0.054
 letters+0.054
Neg logit contributions
opsy-0.066
oppy-0.065
 Remy-0.059
chy-0.058
 bur-0.057
Token found
Token ID1043
Feature activation-5.37e-02

Pos logit contributions
opsy+0.183
oppy+0.179
 Remy+0.170
chy+0.163
 bur+0.160
Neg logit contributions
folk-0.105
 digits-0.103
 sale-0.095
 customer-0.087
 letters-0.086
Token a
Token ID257
Feature activation+9.43e-03

Pos logit contributions
folk+0.064
 digits+0.063
 sale+0.061
 letters+0.059
 customer+0.055
Neg logit contributions
opsy-0.129
oppy-0.128
rig-0.118
 Remy-0.116
chy-0.115
Token veil
Token ID30615
Feature activation+8.10e-02

Pos logit contributions
opsy+0.018
oppy+0.018
 Remy+0.017
chy+0.016
 bur+0.016
Neg logit contributions
folk-0.016
 digits-0.016
 sale-0.015
 customer-0.014
 letters-0.014
Token in
Token ID287
Feature activation+3.20e-02

Pos logit contributions
opsy+0.175
oppy+0.174
 Remy+0.160
 bur+0.152
chy+0.146
Neg logit contributions
folk-0.123
 sale-0.117
 digits-0.116
 letters-0.106
 customer-0.106
Token her
Token ID607
Feature activation+1.58e-02

Pos logit contributions
opsy+0.053
oppy+0.051
 Remy+0.050
 bur+0.049
chy+0.046
Neg logit contributions
folk-0.064
 digits-0.060
 Amen-0.053
 jury-0.053
 winners-0.053
Token sack
Token ID23704
Feature activation+1.31e-01

Pos logit contributions
opsy+0.035
oppy+0.034
 Remy+0.034
chy+0.033
rig+0.033
Neg logit contributions
 digits-0.021
folk-0.019
 customer-0.019
 letters-0.019
 sale-0.019
Token.
Token ID13
Feature activation-5.72e-05

Pos logit contributions
opsy+0.270
oppy+0.267
 Remy+0.247
chy+0.239
 bur+0.238
Neg logit contributions
folk-0.207
 digits-0.201
 sale-0.189
 customer-0.175
 letters-0.174
Token,
Token ID11
Feature activation-3.06e-02

Pos logit contributions
folk+0.034
 digits+0.033
 sale+0.031
 customer+0.027
 cheering+0.027
Neg logit contributions
opsy-0.068
oppy-0.066
chy-0.062
 Remy-0.062
 bur-0.062
Token there
Token ID612
Feature activation-1.17e-01

Pos logit contributions
folk+0.025
 digits+0.024
 sale+0.022
 customer+0.019
 Amen+0.018
Neg logit contributions
opsy-0.083
oppy-0.082
 bur-0.078
 Remy-0.078
chy-0.076
Token was
Token ID373
Feature activation+6.02e-02

Pos logit contributions
folk+0.141
 digits+0.140
 sale+0.137
 cheering+0.118
 number+0.118
Neg logit contributions
opsy-0.270
oppy-0.267
 Remy-0.246
rig-0.243
 bur-0.243
Token a
Token ID257
Feature activation+1.76e-02

Pos logit contributions
oppy+0.151
opsy+0.149
chy+0.136
 bur+0.135
uffy+0.134
Neg logit contributions
 digits-0.063
 sale-0.063
folk-0.060
 customer-0.057
 letters-0.056
Token little
Token ID1310
Feature activation+7.27e-02

Pos logit contributions
opsy+0.036
oppy+0.036
 Remy+0.033
chy+0.033
 bur+0.032
Neg logit contributions
 digits-0.026
folk-0.025
 customer-0.024
 sale-0.024
 Amen-0.022
Token boy
Token ID2933
Feature activation-1.16e-01

Pos logit contributions
opsy+0.177
oppy+0.175
chy+0.164
 Remy+0.164
 bur+0.158
Neg logit contributions
folk-0.083
 digits-0.079
 sale-0.073
 customer-0.072
 letters-0.067
Token named
Token ID3706
Feature activation-6.44e-04

Pos logit contributions
folk+0.179
 digits+0.175
 sale+0.164
 customer+0.152
 letters+0.150
Neg logit contributions
opsy-0.244
oppy-0.241
 Remy-0.223
chy-0.218
 bur-0.217
Token John
Token ID1757
Feature activation-1.88e-01

Pos logit contributions
 digits+0.001
folk+0.001
 sale+0.001
 customer+0.001
 letters+0.001
Neg logit contributions
opsy-0.001
oppy-0.001
 bur-0.001
chy-0.001
 Remy-0.001
Token.
Token ID13
Feature activation+5.38e-03

Pos logit contributions
folk+0.326
 digits+0.313
 sale+0.294
 customer+0.272
 letters+0.269
Neg logit contributions
opsy-0.367
oppy-0.364
 Remy-0.334
chy-0.330
 bur-0.323
Token He
Token ID679
Feature activation-1.20e-02

Pos logit contributions
 Remy+0.009
chy+0.008
opsy+0.007
 bur+0.007
oppy+0.007
Neg logit contributions
folk-0.010
 jury-0.009
 winners-0.009
 judges-0.009
iers-0.009
Token loved
Token ID6151
Feature activation+4.06e-02

Pos logit contributions
 digits+0.011
 sale+0.010
folk+0.010
 Amen+0.010
 number+0.010
Neg logit contributions
opsy-0.031
oppy-0.030
 Remy-0.028
rig-0.028
 bur-0.028
Token a
Token ID257
Feature activation-5.18e-03

Pos logit contributions
opsy+0.355
oppy+0.353
 Remy+0.321
 bur+0.318
chy+0.314
Neg logit contributions
folk-0.208
 digits-0.207
 sale-0.194
 customer-0.179
 letters-0.178
Token time
Token ID640
Feature activation-4.68e-02

Pos logit contributions
 digits+0.004
 customer+0.004
 sale+0.004
folk+0.004
John+0.003
Neg logit contributions
opsy-0.013
oppy-0.013
 Remy-0.013
 bur-0.013
chy-0.012
Token,
Token ID11
Feature activation-5.49e-02

Pos logit contributions
folk+0.057
 digits+0.055
 sale+0.053
 customer+0.046
 cheering+0.045
Neg logit contributions
opsy-0.112
oppy-0.109
 Remy-0.103
 bur-0.102
chy-0.102
Token there
Token ID612
Feature activation-1.36e-01

Pos logit contributions
folk+0.065
 digits+0.063
 sale+0.057
 customer+0.053
 letters+0.051
Neg logit contributions
opsy-0.133
oppy-0.132
 Remy-0.124
 bur-0.122
chy-0.121
Token was
Token ID373
Feature activation+3.60e-02

Pos logit contributions
folk+0.144
 digits+0.144
 sale+0.142
 cheering+0.123
 number+0.122
Neg logit contributions
opsy-0.327
oppy-0.326
rig-0.301
 bur-0.300
 Remy-0.300
Token a
Token ID257
Feature activation-6.55e-03

Pos logit contributions
oppy+0.089
opsy+0.088
chy+0.081
 bur+0.080
rig+0.079
Neg logit contributions
 sale-0.038
 digits-0.038
folk-0.037
 customer-0.035
 letters-0.033
Token girl
Token ID2576
Feature activation-1.35e-01

Pos logit contributions
 digits+0.009
folk+0.009
 customer+0.009
 sale+0.009
 Amen+0.008
Neg logit contributions
oppy-0.013
opsy-0.013
 Remy-0.012
chy-0.012
 bur-0.012
Token called
Token ID1444
Feature activation+2.40e-02

Pos logit contributions
folk+0.211
 digits+0.206
 sale+0.192
 customer+0.179
 letters+0.177
Neg logit contributions
opsy-0.282
oppy-0.279
 Remy-0.259
chy-0.252
 bur-0.251
Token Jill
Token ID22772
Feature activation-1.71e-01

Pos logit contributions
opsy+0.048
oppy+0.047
 Remy+0.044
chy+0.043
 bur+0.043
Neg logit contributions
folk-0.039
 digits-0.038
 sale-0.037
 customer-0.034
 letters-0.033
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
folk+0.184
 digits+0.180
 sale+0.172
 customer+0.158
 letters+0.153
Neg logit contributions
opsy-0.418
oppy-0.416
 Remy-0.399
 bur-0.389
rig-0.365
Token She
Token ID1375
Feature activation+8.63e-03

Pos logit contributions
folk+0.033
 digits+0.029
 Amen+0.029
 sale+0.028
 customer+0.028
Neg logit contributions
oppy-0.027
opsy-0.026
chy-0.025
 Remy-0.025
 bur-0.024
Token feels
Token ID5300
Feature activation+1.26e-01

Pos logit contributions
 digits+0.031
folk+0.027
 letters+0.026
 number+0.026
 prices+0.025
Neg logit contributions
opsy-0.053
oppy-0.052
 Remy-0.046
uffy-0.044
chy-0.044
Token the
Token ID262
Feature activation+3.51e-02

Pos logit contributions
opsy+0.283
oppy+0.279
 bur+0.250
 Remy+0.250
chy+0.246
Neg logit contributions
folk-0.178
 digits-0.174
 sale-0.156
 cheering-0.153
 letters-0.153
Token wind
Token ID2344
Feature activation-6.57e-02

Pos logit contributions
opsy+0.073
oppy+0.072
 Remy+0.067
chy+0.065
 bur+0.065
Neg logit contributions
folk-0.055
 digits-0.054
 sale-0.050
 customer-0.047
 letters-0.046
Token in
Token ID287
Feature activation+3.93e-02

Pos logit contributions
folk+0.102
 digits+0.098
 sale+0.092
 customer+0.085
 letters+0.085
Neg logit contributions
opsy-0.139
oppy-0.138
 Remy-0.128
 bur-0.124
chy-0.121
Token his
Token ID465
Feature activation-4.15e-02

Pos logit contributions
opsy+0.078
oppy+0.076
 Remy+0.075
 bur+0.071
chy+0.069
Neg logit contributions
folk-0.066
 digits-0.063
 sale-0.057
epad-0.055
 Amen-0.054
Token hair
Token ID4190
Feature activation-1.51e-01

Pos logit contributions
folk+0.050
 digits+0.049
 letters+0.044
 sale+0.044
 customer+0.041
Neg logit contributions
opsy-0.102
oppy-0.100
 Remy-0.094
chy-0.092
 bur-0.090
Token.
Token ID13
Feature activation-2.49e-03

Pos logit contributions
folk+0.228
 digits+0.222
 sale+0.209
 letters+0.192
 customer+0.191
Neg logit contributions
opsy-0.326
oppy-0.323
 Remy-0.299
 bur-0.288
chy-0.282
Token He
Token ID679
Feature activation-2.11e-02

Pos logit contributions
folk+0.003
 digits+0.003
 sale+0.003
 customer+0.003
 letters+0.003
Neg logit contributions
opsy-0.006
oppy-0.006
chy-0.005
 bur-0.005
 Remy-0.005
Token sees
Token ID7224
Feature activation+3.55e-02

Pos logit contributions
 digits+0.029
folk+0.026
 letters+0.025
 number+0.025
 prices+0.024
Neg logit contributions
opsy-0.051
oppy-0.049
 Remy-0.044
uffy-0.042
 bur-0.041
Token the
Token ID262
Feature activation+3.67e-02

Pos logit contributions
opsy+0.071
oppy+0.070
 Remy+0.065
chy+0.063
 bur+0.063
Neg logit contributions
folk-0.059
 digits-0.057
 sale-0.053
 customer-0.050
 letters-0.049
Token trees
Token ID7150
Feature activation+3.83e-02

Pos logit contributions
opsy+0.061
oppy+0.058
 bur+0.057
chy+0.057
 Remy+0.056
Neg logit contributions
folk-0.070
 digits-0.069
 sale-0.063
 Amen-0.061
epad-0.061
Token could
Token ID714
Feature activation+1.35e-01

Pos logit contributions
folk+0.202
 digits+0.195
 sale+0.186
 letters+0.174
 customer+0.171
Neg logit contributions
opsy-0.226
oppy-0.221
 Remy-0.204
 bur-0.197
chy-0.193
Token help
Token ID1037
Feature activation-8.66e-03

Pos logit contributions
opsy+0.276
oppy+0.272
 Remy+0.251
 bur+0.242
chy+0.240
Neg logit contributions
folk-0.216
 digits-0.212
 sale-0.202
 customer-0.185
 letters-0.185
Token him
Token ID683
Feature activation-1.96e-03

Pos logit contributions
folk+0.014
 digits+0.013
 sale+0.012
 customer+0.012
 letters+0.011
Neg logit contributions
opsy-0.018
oppy-0.018
 Remy-0.017
chy-0.016
 bur-0.016
Token be
Token ID307
Feature activation-5.08e-02

Pos logit contributions
folk+0.003
 digits+0.003
 sale+0.003
 customer+0.003
 letters+0.003
Neg logit contributions
opsy-0.004
oppy-0.004
 Remy-0.004
chy-0.003
 bur-0.003
Token free
Token ID1479
Feature activation+1.25e-01

Pos logit contributions
folk+0.110
 digits+0.104
 sale+0.099
 jury+0.094
 customer+0.094
Neg logit contributions
oppy-0.074
opsy-0.074
 Remy-0.068
 bur-0.068
chy-0.068
Token.
Token ID13
Feature activation-1.88e-02

Pos logit contributions
opsy+0.241
oppy+0.240
 Remy+0.222
chy+0.219
 bur+0.217
Neg logit contributions
folk-0.213
 digits-0.209
 sale-0.191
 customer-0.181
 jury-0.177
Token He
Token ID679
Feature activation-3.17e-02

Pos logit contributions
folk+0.030
 digits+0.029
 sale+0.027
 customer+0.025
 letters+0.025
Neg logit contributions
opsy-0.039
oppy-0.038
 Remy-0.036
 bur-0.035
chy-0.034
Token was
Token ID373
Feature activation+4.26e-02

Pos logit contributions
folk+0.045
 digits+0.044
 sale+0.041
 customer+0.038
 letters+0.038
Neg logit contributions
opsy-0.071
oppy-0.070
 Remy-0.065
chy-0.063
 bur-0.062
Token so
Token ID523
Feature activation-1.10e-01

Pos logit contributions
opsy+0.068
 Remy+0.064
chy+0.064
oppy+0.063
 bur+0.063
Neg logit contributions
folk-0.085
 digits-0.081
 sale-0.075
 jury-0.074
boxes-0.072
Token happy
Token ID3772
Feature activation-8.08e-02

Pos logit contributions
folk+0.180
 digits+0.173
 sale+0.164
 customer+0.150
 prices+0.147
Neg logit contributions
opsy-0.225
oppy-0.223
 Remy-0.206
chy-0.203
 bur-0.201
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
folk+0.133
 digits+0.130
 sale+0.124
 customer+0.114
 letters+0.114
Neg logit contributions
opsy-0.163
oppy-0.161
 Remy-0.146
chy-0.144
 bur-0.142
Token again
Token ID757
Feature activation-3.42e-02

Pos logit contributions
opsy+0.236
oppy+0.233
 Remy+0.210
uffy+0.203
 bur+0.201
Neg logit contributions
folk-0.137
 digits-0.128
 letters-0.123
 sale-0.118
 cheering-0.111
Token.
Token ID13
Feature activation-5.56e-03

Pos logit contributions
folk+0.054
 digits+0.052
 sale+0.049
 customer+0.045
 letters+0.045
Neg logit contributions
opsy-0.071
oppy-0.070
 Remy-0.065
chy-0.063
 bur-0.063
Token
Token ID220
Feature activation-2.22e-01

Pos logit contributions
folk+0.009
 digits+0.009
 sale+0.008
 customer+0.008
 winners+0.008
Neg logit contributions
oppy-0.011
opsy-0.011
 Remy-0.010
 bur-0.010
chy-0.010
Token
Token ID198
Feature activation+1.89e-02

Pos logit contributions
folk+0.295
 digits+0.290
 sale+0.268
 customer+0.239
 letters+0.238
Neg logit contributions
opsy-0.505
oppy-0.487
chy-0.463
 bur-0.460
 Remy-0.452
Token
Token ID198
Feature activation+1.80e-02

Pos logit contributions
oppy+0.031
opsy+0.031
 Remy+0.030
 bur+0.027
chy+0.026
Neg logit contributions
folk-0.038
 digits-0.036
 sale-0.034
 prices-0.033
 letters-0.033
TokenSarah
Token ID29284
Feature activation-1.93e-01

Pos logit contributions
opsy+0.032
oppy+0.032
 Remy+0.030
 bur+0.028
chy+0.028
Neg logit contributions
folk-0.033
 digits-0.032
 sale-0.030
 customer-0.028
 letters-0.028
Token thanked
Token ID26280
Feature activation-5.23e-02

Pos logit contributions
folk+0.274
 digits+0.262
 sale+0.239
 letters+0.227
 cheering+0.220
Neg logit contributions
oppy-0.429
opsy-0.429
 Remy-0.398
chy-0.372
 bur-0.369
Token the
Token ID262
Feature activation+2.90e-02

Pos logit contributions
folk+0.087
 digits+0.084
 sale+0.082
 letters+0.075
 customer+0.075
Neg logit contributions
opsy-0.104
oppy-0.103
chy-0.094
 Remy-0.092
 bur-0.091
Token bear
Token ID6842
Feature activation+8.85e-02

Pos logit contributions
opsy+0.050
oppy+0.049
 Remy+0.045
chy+0.043
 bur+0.043
Neg logit contributions
folk-0.057
 digits-0.056
 sale-0.053
 customer-0.050
 letters-0.049
Token and
Token ID290
Feature activation+2.74e-02

Pos logit contributions
opsy+0.180
oppy+0.176
 Remy+0.157
chy+0.157
 bur+0.154
Neg logit contributions
folk-0.141
 digits-0.134
 sale-0.134
 customer-0.127
 letters-0.125
Token gave
Token ID2921
Feature activation-6.49e-02

Pos logit contributions
opsy+0.062
oppy+0.062
chy+0.057
uffy+0.055
 Remy+0.055
Neg logit contributions
folk-0.037
 digits-0.035
 sale-0.033
 letters-0.032
 customer-0.031
Token He
Token ID679
Feature activation-2.12e-02

Pos logit contributions
folk+0.007
 digits+0.007
 sale+0.006
 customer+0.006
 letters+0.006
Neg logit contributions
opsy-0.010
oppy-0.010
 Remy-0.010
 bur-0.009
chy-0.009
Token laughed
Token ID13818
Feature activation-4.08e-02

Pos logit contributions
folk+0.027
 digits+0.026
 sale+0.024
 number+0.023
 cheering+0.022
Neg logit contributions
oppy-0.049
opsy-0.049
 Remy-0.044
uffy-0.043
chy-0.042
Token and
Token ID290
Feature activation+3.04e-02

Pos logit contributions
folk+0.060
 digits+0.057
 sale+0.055
 letters+0.051
 cheering+0.050
Neg logit contributions
opsy-0.091
oppy-0.090
 Remy-0.080
 bur-0.078
chy-0.078
Token laughed
Token ID13818
Feature activation-4.08e-02

Pos logit contributions
opsy+0.066
oppy+0.066
chy+0.059
 Remy+0.058
 bur+0.057
Neg logit contributions
folk-0.045
 digits-0.044
 sale-0.040
 cheering-0.038
 letters-0.038
Token.
Token ID13
Feature activation-4.11e-03

Pos logit contributions
folk+0.064
 digits+0.062
 sale+0.058
 customer+0.053
 letters+0.053
Neg logit contributions
opsy-0.086
oppy-0.085
 Remy-0.078
 bur-0.076
chy-0.076
Token
Token ID220
Feature activation-2.22e-01

Pos logit contributions
folk+0.005
 digits+0.005
 sale+0.005
 customer+0.005
epad+0.005
Neg logit contributions
opsy-0.009
oppy-0.009
 Remy-0.009
 bur-0.009
chy-0.008
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
folk+0.250
 digits+0.247
 sale+0.223
 cheering+0.197
John+0.195
Neg logit contributions
opsy-0.545
oppy-0.524
 bur-0.502
chy-0.501
 Remy-0.476
Token
Token ID198
Feature activation+1.92e-02

Pos logit contributions
opsy+0.042
oppy+0.042
chy+0.038
 Remy+0.038
 bur+0.038
Neg logit contributions
folk-0.029
 digits-0.029
 sale-0.027
 customer-0.024
 cheering-0.024
TokenThe
Token ID464
Feature activation+9.69e-02

Pos logit contributions
opsy+0.037
oppy+0.036
 Remy+0.033
chy+0.032
 bur+0.032
Neg logit contributions
folk-0.034
 digits-0.033
 sale-0.031
 customer-0.029
 letters-0.028
Token man
Token ID582
Feature activation-1.40e-01

Pos logit contributions
opsy+0.208
oppy+0.207
 Remy+0.191
chy+0.186
 bur+0.185
Neg logit contributions
folk-0.149
 digits-0.145
 sale-0.134
 customer-0.125
 letters-0.123
Token was
Token ID373
Feature activation+5.13e-02

Pos logit contributions
folk+0.217
 digits+0.207
 sale+0.194
 letters+0.180
 customer+0.178
Neg logit contributions
opsy-0.297
oppy-0.296
 Remy-0.270
chy-0.264
 bur-0.258
Token tiny
Token ID7009
Feature activation+1.15e-01

Pos logit contributions
folk+0.005
 digits+0.005
 sale+0.005
epad+0.005
bench+0.005
Neg logit contributions
opsy-0.005
oppy-0.005
 bur-0.004
 Remy-0.004
chy-0.004
Token mouse
Token ID10211
Feature activation+6.81e-02

Pos logit contributions
opsy+0.197
oppy+0.196
 bur+0.183
 Remy+0.178
chy+0.170
Neg logit contributions
folk-0.224
 digits-0.217
 sale-0.199
epad-0.191
bench-0.189
Token.
Token ID13
Feature activation-1.52e-02

Pos logit contributions
opsy+0.140
oppy+0.138
 Remy+0.127
chy+0.123
 bur+0.122
Neg logit contributions
folk-0.108
 digits-0.106
 sale-0.100
 customer-0.092
 letters-0.092
Token The
Token ID383
Feature activation+8.72e-02

Pos logit contributions
folk+0.025
 digits+0.025
 sale+0.023
 customer+0.022
 letters+0.021
Neg logit contributions
opsy-0.031
oppy-0.030
chy-0.027
 Remy-0.027
 bur-0.027
Token mouse
Token ID10211
Feature activation+6.87e-02

Pos logit contributions
opsy+0.155
oppy+0.153
 Remy+0.139
chy+0.135
 bur+0.134
Neg logit contributions
folk-0.165
 digits-0.162
 sale-0.153
 customer-0.144
 letters-0.143
Token asked
Token ID1965
Feature activation-2.57e-01

Pos logit contributions
opsy+0.145
oppy+0.143
 Remy+0.132
chy+0.128
 bur+0.127
Neg logit contributions
folk-0.105
 digits-0.102
 sale-0.095
 letters-0.088
 customer-0.087
Token the
Token ID262
Feature activation+2.35e-02

Pos logit contributions
folk+0.440
 digits+0.432
 sale+0.394
 customer+0.371
bench+0.368
Neg logit contributions
oppy-0.499
opsy-0.499
 Remy-0.472
chy-0.442
 bur-0.441
Token bald
Token ID28273
Feature activation-8.05e-02

Pos logit contributions
opsy+0.041
oppy+0.041
 Remy+0.037
chy+0.036
 bur+0.036
Neg logit contributions
folk-0.045
 digits-0.044
 sale-0.042
 customer-0.039
 letters-0.039
Token man
Token ID582
Feature activation-1.53e-01

Pos logit contributions
folk+0.135
 digits+0.132
 sale+0.122
 customer+0.113
 letters+0.112
Neg logit contributions
opsy-0.160
oppy-0.158
 Remy-0.146
chy-0.142
 bur-0.141
Token if
Token ID611
Feature activation+1.41e-02

Pos logit contributions
folk+0.269
 digits+0.260
 sale+0.239
bench+0.227
 customer+0.223
Neg logit contributions
oppy-0.291
opsy-0.289
 Remy-0.272
chy-0.257
 bur-0.256
Token he
Token ID339
Feature activation+2.40e-02

Pos logit contributions
opsy+0.030
oppy+0.029
chy+0.026
 Remy+0.026
 bur+0.026
Neg logit contributions
folk-0.022
 digits-0.021
 sale-0.020
 customer-0.019
 letters-0.019
Token
Token ID8151
Feature activation+3.28e-02

Pos logit contributions
opsy+0.076
oppy+0.074
 Remy+0.068
chy+0.068
 bur+0.067
Neg logit contributions
folk-0.066
 digits-0.064
 sale-0.060
 customer-0.056
 letters-0.056
Tokens
Token ID82
Feature activation+1.92e-01

Pos logit contributions
opsy+0.055
oppy+0.054
 Remy+0.049
 bur+0.048
chy+0.048
Neg logit contributions
folk-0.064
 digits-0.062
 sale-0.060
 customer-0.056
 letters-0.055
Token go
Token ID467
Feature activation+5.97e-02

Pos logit contributions
opsy+0.387
oppy+0.382
 Remy+0.353
chy+0.344
 bur+0.341
Neg logit contributions
folk-0.311
 digits-0.303
 sale-0.285
 customer-0.265
 letters-0.262
Token to
Token ID284
Feature activation-8.71e-03

Pos logit contributions
opsy+0.118
oppy+0.118
 Remy+0.109
 bur+0.105
chy+0.104
Neg logit contributions
folk-0.100
 digits-0.097
 sale-0.090
 letters-0.084
 customer-0.084
Token the
Token ID262
Feature activation+2.36e-02

Pos logit contributions
 sale+0.012
folk+0.011
 digits+0.011
 customer+0.011
 cheering+0.010
Neg logit contributions
opsy-0.020
oppy-0.019
chy-0.018
uffy-0.017
rig-0.017
Token store
Token ID3650
Feature activation-2.04e-01

Pos logit contributions
oppy+0.050
opsy+0.050
 Remy+0.045
chy+0.044
 bur+0.043
Neg logit contributions
folk-0.035
 digits-0.035
 sale-0.034
 customer-0.032
 letters-0.031
Token and
Token ID290
Feature activation+1.89e-02

Pos logit contributions
folk+0.373
 digits+0.371
 Amen+0.324
 sale+0.323
epad+0.321
Neg logit contributions
opsy-0.357
oppy-0.355
 Remy-0.337
 bur-0.320
chy-0.314
Token get
Token ID651
Feature activation+1.35e-03

Pos logit contributions
opsy+0.042
oppy+0.041
chy+0.038
 Remy+0.037
 bur+0.036
Neg logit contributions
folk-0.027
 digits-0.026
 sale-0.025
 customer-0.023
 letters-0.022
Token you
Token ID345
Feature activation+6.59e-02

Pos logit contributions
opsy+0.003
oppy+0.003
 Remy+0.003
 bur+0.003
chy+0.002
Neg logit contributions
folk-0.002
 digits-0.002
 sale-0.002
 customer-0.002
epad-0.002
Token a
Token ID257
Feature activation+4.79e-05

Pos logit contributions
opsy+0.142
oppy+0.139
 Remy+0.130
chy+0.126
 bur+0.125
Neg logit contributions
folk-0.097
 digits-0.094
 sale-0.090
 customer-0.083
 letters-0.082
Token battery
Token ID6555
Feature activation-9.05e-02

Pos logit contributions
opsy+0.000
oppy+0.000
 Remy+0.000
chy+0.000
 bur+0.000
Neg logit contributions
folk-0.000
 digits-0.000
 sale-0.000
 customer-0.000
 letters-0.000
Tokenbons
Token ID23461
Feature activation-1.73e-01

Pos logit contributions
opsy+0.008
oppy+0.008
 Remy+0.008
 bur+0.008
chy+0.007
Neg logit contributions
folk-0.004
 digits-0.004
 sale-0.004
 customer-0.003
 jury-0.003
Token and
Token ID290
Feature activation+3.48e-02

Pos logit contributions
folk+0.288
 digits+0.280
 sale+0.262
 customer+0.245
 letters+0.243
Neg logit contributions
opsy-0.343
oppy-0.339
 Remy-0.313
chy-0.302
 bur-0.302
Token shiny
Token ID22441
Feature activation+7.88e-03

Pos logit contributions
opsy+0.066
oppy+0.064
 Remy+0.062
 bur+0.061
chy+0.061
Neg logit contributions
folk-0.059
 digits-0.056
 sale-0.054
 customer-0.051
 Amen-0.050
Token stars
Token ID5788
Feature activation-3.67e-02

Pos logit contributions
 bur+0.012
opsy+0.012
oppy+0.012
chy+0.011
 Remy+0.011
Neg logit contributions
folk-0.014
 Amen-0.014
 digits-0.013
 customer-0.013
epad-0.013
Token.
Token ID13
Feature activation+5.18e-04

Pos logit contributions
folk+0.062
 digits+0.061
 sale+0.056
 customer+0.053
 Amen+0.052
Neg logit contributions
opsy-0.071
oppy-0.070
 Remy-0.065
chy-0.064
 bur-0.063
Token
Token ID220
Feature activation-2.18e-01

Pos logit contributions
opsy+0.001
oppy+0.001
 Remy+0.001
chy+0.001
 bur+0.001
Neg logit contributions
folk-0.001
 digits-0.001
 sale-0.001
 customer-0.001
 letters-0.001
Token
Token ID198
Feature activation+2.61e-02

Pos logit contributions
folk+0.281
 digits+0.277
 sale+0.254
 letters+0.228
 cheering+0.224
Neg logit contributions
opsy-0.498
oppy-0.486
chy-0.465
 bur-0.462
 Remy-0.456
Token
Token ID198
Feature activation+2.56e-02

Pos logit contributions
oppy+0.059
opsy+0.058
chy+0.056
 bur+0.054
 Remy+0.053
Neg logit contributions
 digits-0.034
folk-0.034
 sale-0.032
 cheering-0.029
 customer-0.028
TokenWhen
Token ID2215
Feature activation+2.69e-02

Pos logit contributions
oppy+0.053
opsy+0.053
chy+0.049
 Remy+0.049
 bur+0.048
Neg logit contributions
folk-0.039
 digits-0.039
 sale-0.037
 customer-0.034
 cheering-0.033
Token it
Token ID340
Feature activation-1.22e-01

Pos logit contributions
opsy+0.056
oppy+0.056
chy+0.051
 Remy+0.051
 bur+0.050
Neg logit contributions
folk-0.041
 digits-0.040
 sale-0.039
 letters-0.035
 customer-0.035
Token was
Token ID373
Feature activation+5.76e-02

Pos logit contributions
folk+0.167
 digits+0.163
 sale+0.156
 cheering+0.137
 number+0.137
Neg logit contributions
opsy-0.279
oppy-0.274
 Remy-0.262
 bur-0.239
chy-0.235