TOP ACTIVATIONS
MAX = 1.602

, I think Reviewer : B iz r Pix
we follow the SH RM ( Str ategic Human Resource Management
was about homosexuality Reviewer : k imp unk rock
er magnet ? Reviewer : hey _ ler oy
are Here .... Reviewer : SAS K ATCH EW
iff Tra x Reviewer : V the Happy L
bad idea . Reviewer : Mike M anners -
2010 boys beware Reviewer : j wt 0001 -
What was the most interesting thing you learned from
Sound tracks [ edit ] Various sound
Video games [ edit ] In the
s annual barbecue d ub bed , naturally ,
Th rill ride [ edit ] The T
scholar in the legislature at that time , was one of
press X to kill , press Y to spare .
Enc ryption details [ edit ] WE P
os & Bonnie & Baby 2008 01 09 O & A
fabric of this country is being torn as under by a
ness . Continue Reading Below Advertisement <|endoftext|> There are
My top 10 EDIT OR ' S NOTE :

MIN ACTIVATIONS
MIN = -1.934

that the old address https :// . nice hash . com
01 606 7 201 99 ; head water . com ),
qa , for men ), iron ( tem ür ), steel
claim to be ( in theory at least ) universal .
. Color ] :: From Ar gb ($ FC 2 [
mus ics . It 's iron ical that a lot of
Rod olf o Al ar con Ortiz upon arrival at the
. Color ] :: From Ar gb ($ FC 1 [
. ed wards . af . mil / history / docs
your egg repl acer and set aside . 2 . Steam
and I think around 15 - 20 minutes for longest .
' a , T >> ; } In order
steal dragon , cause he 's notorious about stealing players from
< T > { pub fn load < ' a >
discern the size of individual pixels due to the amount they
down every day and then mineral izes , forming a hard
among farmland contaminated by heavy metals used to make batteries ,
avoid following the commands in his head ). Kid n apping
to avoid following the commands in his head ). Kid n
Europe had for the first time come to systematically compare the

INTERVAL 0.718 - 1.602
CONTAINS 0.876%

here but will talk a bit about its operation on the
are H VM with PV H VM drivers .
data structure . Sh ared < ' a ,
. Here is the link for buying the second edition of
current wallpaper $ ($ w path )" break } } else

INTERVAL -0.166 - 0.718
CONTAINS 71.521%

qualifier where they secured their spot for the major is of
meeting room internet at the West in cut out ( as
that the coalition was illegitimate , divisive , unstable and ,
and explore the world with kindred spirits . Be the first
the UL MB stro bed back light as well if you

INTERVAL -1.050 - -0.166
CONTAINS 27.532%

opus comment ] went quite big ! It was just a
variation as both cameras had near identical optical performance .
he would submit a bill proposing to criminal ize ritual circumcision
policies . That is not even the worst of it .
them access to all the evidence still outstanding so they can

INTERVAL -1.934 - -1.050
CONTAINS 0.070%

bind directive : < body ng - controller ="
qa , for men ), iron ( tem ür ), steel
was po in ­ ted ly denied a spot
Flag Reply 27 Recommend Recommend
Europe had for the first time come to systematically compare the
Token,
Token ID11
Feature activation-2.42e-01

Pos logit contributions
agine+0.847
ttp+0.799
 balloons+0.738
mingham+0.736
VERTISEMENT+0.714
Neg logit contributions
ature-1.102
onduct-1.084
arten-1.050
ores-1.027
=]-1.026
Token I
Token ID314
Feature activation-2.17e-01

Pos logit contributions
agine+1.766
ttp+1.675
 balloons+1.567
mingham+1.566
VERTISEMENT+1.518
Neg logit contributions
ature-1.982
onduct-1.941
arten-1.865
=]-1.847
ores-1.830
Token think
Token ID892
Feature activation+3.96e-02

Pos logit contributions
agine+1.414
ttp+1.311
mingham+1.192
 balloons+1.180
 FB+1.118
Neg logit contributions
ature-1.955
onduct-1.920
arten-1.878
=]-1.842
 Shiv-1.829
Token
Token ID198
Feature activation+9.94e-02

Pos logit contributions
ature+0.305
onduct+0.298
arten+0.287
=]+0.283
ores+0.281
Neg logit contributions
agine-0.311
ttp-0.293
 balloons-0.277
mingham-0.276
VERTISEMENT-0.269
Token
Token ID198
Feature activation-1.15e-01

Pos logit contributions
ature+0.757
onduct+0.738
arten+0.711
=]+0.700
ores+0.695
Neg logit contributions
agine-0.791
ttp-0.746
 balloons-0.703
mingham-0.702
VERTISEMENT-0.685
TokenReviewer
Token ID35407
Feature activation+1.60e+00

Pos logit contributions
agine+0.729
ttp+0.687
mingham+0.630
 balloons+0.622
VERTISEMENT+0.608
Neg logit contributions
ature-1.054
onduct-1.033
arten-1.001
 Shiv-0.994
=]-0.986
Token:
Token ID25
Feature activation-5.19e-01

Pos logit contributions
ature+7.375
=]+6.447
onduct+6.298
 Shiv+6.088
ores+5.958
Neg logit contributions
 confir-15.876
agine-15.598
 artif-14.623
VERTISEMENT-14.573
querque-14.183
Token B
Token ID347
Feature activation-1.12e-01

Pos logit contributions
agine+3.918
ttp+3.733
 balloons+3.608
mingham+3.485
 FB+3.436
Neg logit contributions
ature-3.926
onduct-3.907
arten-3.700
=]-3.635
ores-3.615
Tokeniz
Token ID528
Feature activation+3.59e-01

Pos logit contributions
agine+0.923
ttp+0.883
mingham+0.830
 balloons+0.821
VERTISEMENT+0.801
Neg logit contributions
ature-0.809
onduct-0.790
=]-0.756
arten-0.752
 Shiv-0.746
Tokenr
Token ID81
Feature activation+1.97e-01

Pos logit contributions
ature+2.716
onduct+2.641
arten+2.551
=]+2.503
ores+2.496
Neg logit contributions
agine-2.872
ttp-2.707
 balloons-2.555
mingham-2.544
VERTISEMENT-2.489
Token Pix
Token ID21642
Feature activation+1.13e-02

Pos logit contributions
ature+1.515
onduct+1.481
arten+1.426
=]+1.407
ores+1.394
Neg logit contributions
agine-1.548
ttp-1.460
 balloons-1.373
mingham-1.372
VERTISEMENT-1.334
Token we
Token ID356
Feature activation-6.45e-02

Pos logit contributions
ature+1.057
onduct+1.027
arten+0.993
=]+0.983
ores+0.970
Neg logit contributions
agine-1.011
ttp-0.950
 balloons-0.898
mingham-0.889
VERTISEMENT-0.867
Token follow
Token ID1061
Feature activation+8.09e-02

Pos logit contributions
agine+0.487
ttp+0.452
 balloons+0.432
mingham+0.428
 FB+0.411
Neg logit contributions
ature-0.517
onduct-0.496
arten-0.492
=]-0.481
arella-0.472
Token the
Token ID262
Feature activation+2.80e-02

Pos logit contributions
ature+0.645
onduct+0.628
arten+0.604
=]+0.600
ores+0.595
Neg logit contributions
agine-0.616
ttp-0.580
 balloons-0.544
mingham-0.539
VERTISEMENT-0.531
Token SH
Token ID6006
Feature activation+2.08e-01

Pos logit contributions
ature+0.227
onduct+0.221
arten+0.214
=]+0.211
ores+0.209
Neg logit contributions
agine-0.209
ttp-0.197
 balloons-0.185
mingham-0.183
VERTISEMENT-0.180
TokenRM
Token ID29138
Feature activation-5.54e-02

Pos logit contributions
ature+1.650
onduct+1.611
arten+1.554
=]+1.532
ores+1.521
Neg logit contributions
agine-1.587
ttp-1.493
 balloons-1.403
mingham-1.401
VERTISEMENT-1.363
Token (
Token ID357
Feature activation+1.60e+00

Pos logit contributions
agine+0.394
ttp+0.371
 balloons+0.340
mingham+0.338
VERTISEMENT+0.336
Neg logit contributions
ature-0.466
onduct-0.453
arten-0.443
=]-0.443
 Shiv-0.432
TokenStr
Token ID13290
Feature activation+3.40e-01

Pos logit contributions
ature+10.036
onduct+9.998
shit+9.807
living+9.567
+9.324
Neg logit contributions
agine-12.447
 balloons-11.827
ttp-11.391
VERTISEMENT-11.158
mingham-11.029
Tokenategic
Token ID47917
Feature activation+1.65e-01

Pos logit contributions
ature+2.466
onduct+2.400
arten+2.308
=]+2.271
ores+2.257
Neg logit contributions
agine-2.816
ttp-2.665
 balloons-2.530
mingham-2.512
VERTISEMENT-2.458
Token Human
Token ID5524
Feature activation+3.91e-01

Pos logit contributions
ature+1.145
onduct+1.116
arten+1.080
=]+1.052
ores+1.044
Neg logit contributions
agine-1.431
ttp-1.348
 balloons-1.280
mingham-1.269
VERTISEMENT-1.245
Token Resource
Token ID20857
Feature activation+1.56e-02

Pos logit contributions
ature+3.112
onduct+3.040
arten+2.930
=]+2.887
ores+2.875
Neg logit contributions
agine-2.961
ttp-2.793
 balloons-2.627
mingham-2.615
VERTISEMENT-2.541
Token Management
Token ID8549
Feature activation-7.41e-02

Pos logit contributions
ature+0.098
onduct+0.095
arten+0.092
=]+0.090
arella+0.089
Neg logit contributions
agine-0.145
ttp-0.137
mingham-0.131
 balloons-0.131
VERTISEMENT-0.128
Token was
Token ID373
Feature activation-7.85e-02

Pos logit contributions
ature+1.530
onduct+1.496
arten+1.441
=]+1.423
 Shiv+1.406
Neg logit contributions
agine-1.425
ttp-1.340
 balloons-1.263
mingham-1.253
VERTISEMENT-1.217
Token about
Token ID546
Feature activation-5.34e-01

Pos logit contributions
agine+0.582
ttp+0.545
 balloons+0.518
mingham+0.509
VERTISEMENT+0.492
Neg logit contributions
ature-0.638
onduct-0.624
arten-0.599
=]-0.594
arella-0.587
Token homosexuality
Token ID19822
Feature activation+2.14e-02

Pos logit contributions
agine+3.867
 balloons+3.542
ttp+3.487
 FB+3.293
mingham+3.264
Neg logit contributions
ature-4.271
onduct-4.223
arella-4.021
arten-4.016
=]-4.000
Token
Token ID198
Feature activation+2.20e-02

Pos logit contributions
ature+0.181
onduct+0.177
arten+0.171
=]+0.169
 Shiv+0.167
Neg logit contributions
agine-0.151
ttp-0.142
 balloons-0.134
mingham-0.132
VERTISEMENT-0.128
Token
Token ID198
Feature activation-2.19e-01

Pos logit contributions
ature+0.172
onduct+0.169
arten+0.163
=]+0.160
 Shiv+0.159
Neg logit contributions
agine-0.170
ttp-0.161
mingham-0.151
 balloons-0.150
VERTISEMENT-0.146
TokenReviewer
Token ID35407
Feature activation+1.59e+00

Pos logit contributions
agine+1.670
ttp+1.601
mingham+1.475
 balloons+1.454
VERTISEMENT+1.432
Neg logit contributions
ature-1.703
onduct-1.682
arten-1.605
 Shiv-1.597
arella-1.591
Token:
Token ID25
Feature activation-2.99e-01

Pos logit contributions
ature+8.043
onduct+7.424
 Shiv+7.417
ores+7.309
=]+7.185
Neg logit contributions
agine-14.342
ttp-13.598
VERTISEMENT-13.295
mingham-13.228
cknowled-12.763
Token k
Token ID479
Feature activation-4.46e-02

Pos logit contributions
agine+2.274
ttp+2.152
 balloons+2.062
mingham+2.012
 FB+1.951
Neg logit contributions
ature-2.312
onduct-2.297
arten-2.184
=]-2.144
ores-2.130
Tokenimp
Token ID11011
Feature activation-2.34e-01

Pos logit contributions
agine+0.379
ttp+0.360
mingham+0.337
 balloons+0.334
VERTISEMENT+0.326
Neg logit contributions
ature-0.313
onduct-0.306
=]-0.293
arten-0.290
 Shiv-0.288
Tokenunk
Token ID2954
Feature activation-2.72e-01

Pos logit contributions
agine+1.919
ttp+1.810
mingham+1.713
 balloons+1.693
VERTISEMENT+1.606
Neg logit contributions
ature-1.689
onduct-1.675
=]-1.615
arten-1.591
 Shiv-1.582
Tokenrock
Token ID10823
Feature activation+6.45e-02

Pos logit contributions
agine+1.972
ttp+1.875
mingham+1.742
 balloons+1.737
VERTISEMENT+1.649
Neg logit contributions
ature-2.187
onduct-2.173
=]-2.079
arten-2.078
 Shiv-2.040
Tokener
Token ID263
Feature activation+1.46e-01

Pos logit contributions
ature+1.794
onduct+1.742
arten+1.679
=]+1.642
ores+1.636
Neg logit contributions
agine-1.984
ttp-1.874
 balloons-1.778
mingham-1.765
VERTISEMENT-1.732
Token magnet
Token ID19972
Feature activation-6.61e-01

Pos logit contributions
ature+1.039
onduct+1.018
arten+0.981
=]+0.958
ores+0.951
Neg logit contributions
agine-1.233
ttp-1.166
 balloons-1.111
mingham-1.103
VERTISEMENT-1.079
Token?
Token ID30
Feature activation-2.16e-01

Pos logit contributions
agine+3.454
ttp+3.128
mingham+2.950
 balloons+2.896
VERTISEMENT+2.788
Neg logit contributions
onduct-6.538
ature-6.493
arten-6.335
arella-6.210
=]-6.191
Token
Token ID198
Feature activation+6.95e-02

Pos logit contributions
agine+1.679
ttp+1.593
mingham+1.491
 balloons+1.490
VERTISEMENT+1.453
Neg logit contributions
ature-1.675
onduct-1.642
arten-1.580
=]-1.562
ores-1.545
Token
Token ID198
Feature activation-2.00e-01

Pos logit contributions
ature+0.533
onduct+0.520
arten+0.501
=]+0.494
ores+0.490
Neg logit contributions
agine-0.548
ttp-0.517
 balloons-0.486
mingham-0.486
VERTISEMENT-0.473
TokenReviewer
Token ID35407
Feature activation+1.59e+00

Pos logit contributions
agine+1.197
ttp+1.127
mingham+1.023
VERTISEMENT+1.003
 balloons+1.001
Neg logit contributions
ature-1.879
onduct-1.847
arten-1.797
 Shiv-1.795
arella-1.777
Token:
Token ID25
Feature activation-5.16e-01

Pos logit contributions
ature+7.432
=]+6.434
onduct+6.355
 Shiv+6.149
ores+6.038
Neg logit contributions
 confir-15.632
agine-15.415
VERTISEMENT-14.427
 artif-14.424
querque-14.006
Token hey
Token ID17207
Feature activation-5.05e-01

Pos logit contributions
agine+3.897
ttp+3.707
 balloons+3.583
mingham+3.458
 FB+3.415
Neg logit contributions
ature-3.903
onduct-3.890
arten-3.685
=]-3.619
ores-3.594
Token_
Token ID62
Feature activation-2.94e-01

Pos logit contributions
agine+4.124
ttp+3.942
mingham+3.682
 balloons+3.663
cknowled+3.505
Neg logit contributions
onduct-3.538
ature-3.516
=]-3.336
arten-3.282
 Shiv-3.274
Tokenler
Token ID1754
Feature activation-7.23e-02

Pos logit contributions
agine+2.400
ttp+2.281
mingham+2.140
 balloons+2.112
VERTISEMENT+2.026
Neg logit contributions
ature-2.110
onduct-2.099
=]-1.989
arten-1.985
 Shiv-1.975
Tokenoy
Token ID726
Feature activation-7.24e-01

Pos logit contributions
agine+0.561
ttp+0.526
mingham+0.494
 balloons+0.492
VERTISEMENT+0.475
Neg logit contributions
ature-0.560
onduct-0.554
arten-0.533
=]-0.527
 Shiv-0.521
Token are
Token ID389
Feature activation-1.09e-01

Pos logit contributions
ature+3.394
onduct+3.293
arten+3.132
=]+3.112
ores+3.081
Neg logit contributions
agine-4.244
ttp-4.028
mingham-3.804
 balloons-3.789
VERTISEMENT-3.745
Token Here
Token ID3423
Feature activation-5.09e-01

Pos logit contributions
agine+0.839
ttp+0.793
 balloons+0.745
mingham+0.743
VERTISEMENT+0.722
Neg logit contributions
ature-0.859
onduct-0.840
arten-0.811
=]-0.796
ores-0.789
Token....
Token ID1106
Feature activation-3.12e-01

Pos logit contributions
agine+3.071
ttp+2.910
mingham+2.645
 balloons+2.642
VERTISEMENT+2.615
Neg logit contributions
ature-4.662
onduct-4.499
arten-4.479
 Shiv-4.400
arella-4.393
Token
Token ID198
Feature activation+5.28e-02

Pos logit contributions
agine+2.384
ttp+2.264
 balloons+2.116
mingham+2.112
VERTISEMENT+2.058
Neg logit contributions
ature-2.448
onduct-2.398
arten-2.307
=]-2.285
ores-2.252
Token
Token ID198
Feature activation+2.27e-02

Pos logit contributions
ature+0.407
onduct+0.398
arten+0.383
=]+0.377
ores+0.374
Neg logit contributions
agine-0.414
ttp-0.390
 balloons-0.367
mingham-0.366
VERTISEMENT-0.357
TokenReviewer
Token ID35407
Feature activation+1.58e+00

Pos logit contributions
ature+0.206
onduct+0.201
arten+0.195
=]+0.193
 Shiv+0.193
Neg logit contributions
agine-0.147
ttp-0.138
mingham-0.127
 balloons-0.126
VERTISEMENT-0.123
Token:
Token ID25
Feature activation-3.94e-01

Pos logit contributions
ature+7.467
=]+6.498
onduct+6.440
 Shiv+6.243
ores+6.121
Neg logit contributions
 confir-15.329
agine-15.268
VERTISEMENT-14.252
 artif-14.223
cknowled-13.756
Token SAS
Token ID35516
Feature activation-4.85e-02

Pos logit contributions
agine+2.975
ttp+2.823
 balloons+2.708
mingham+2.619
 FB+2.574
Neg logit contributions
ature-3.034
onduct-3.011
arten-2.864
=]-2.811
ores-2.798
TokenK
Token ID42
Feature activation-1.52e-02

Pos logit contributions
agine+0.382
ttp+0.363
mingham+0.340
 balloons+0.338
VERTISEMENT+0.328
Neg logit contributions
ature-0.370
onduct-0.362
arten-0.348
=]-0.345
 Shiv-0.341
TokenATCH
Token ID11417
Feature activation+4.21e-03

Pos logit contributions
agine+0.115
ttp+0.109
mingham+0.102
 balloons+0.102
VERTISEMENT+0.099
Neg logit contributions
ature-0.120
onduct-0.118
arten-0.113
=]-0.112
ores-0.111
TokenEW
Token ID6217
Feature activation-1.03e-01

Pos logit contributions
ature+0.034
onduct+0.033
arten+0.032
=]+0.032
ores+0.032
Neg logit contributions
agine-0.031
ttp-0.030
 balloons-0.027
mingham-0.027
VERTISEMENT-0.027
Tokeniff
Token ID733
Feature activation+1.42e-01

Pos logit contributions
agine+0.333
ttp+0.307
mingham+0.280
 balloons+0.276
VERTISEMENT+0.266
Neg logit contributions
ature-0.612
onduct-0.601
arten-0.586
=]-0.582
 Shiv-0.578
TokenTra
Token ID15721
Feature activation-2.00e-01

Pos logit contributions
ature+1.172
onduct+1.148
arten+1.113
=]+1.093
 Shiv+1.088
Neg logit contributions
agine-1.036
ttp-0.978
mingham-0.913
 balloons-0.910
VERTISEMENT-0.886
Tokenx
Token ID87
Feature activation-5.24e-01

Pos logit contributions
agine+1.410
ttp+1.318
mingham+1.243
 balloons+1.220
 FB+1.155
Neg logit contributions
ature-1.671
onduct-1.652
arten-1.601
=]-1.587
 Shiv-1.576
Token
Token ID198
Feature activation-4.03e-01

Pos logit contributions
agine+3.602
ttp+3.534
 balloons+3.208
mingham+3.172
VERTISEMENT+3.079
Neg logit contributions
ature-4.257
onduct-4.230
arten-4.150
=]-4.038
ores-4.034
Token
Token ID198
Feature activation-2.70e-01

Pos logit contributions
agine+2.665
ttp+2.559
 balloons+2.340
mingham+2.327
 FB+2.277
Neg logit contributions
ature-3.455
onduct-3.441
arten-3.333
=]-3.241
arella-3.229
TokenReviewer
Token ID35407
Feature activation+1.58e+00

Pos logit contributions
agine+1.594
ttp+1.519
mingham+1.374
 balloons+1.329
VERTISEMENT+1.316
Neg logit contributions
ature-2.533
onduct-2.504
arten-2.435
 Shiv-2.428
arella-2.396
Token:
Token ID25
Feature activation-5.99e-01

Pos logit contributions
ature+7.365
=]+6.390
onduct+6.351
ores+6.008
 Shiv+5.997
Neg logit contributions
 confir-15.569
agine-15.334
VERTISEMENT-14.370
 artif-14.367
querque-13.890
Token V
Token ID569
Feature activation-3.62e-01

Pos logit contributions
agine+4.477
ttp+4.269
 balloons+4.134
mingham+3.984
 FB+3.939
Neg logit contributions
ature-4.500
onduct-4.493
arten-4.242
=]-4.174
ores-4.146
Tokenthe
Token ID1169
Feature activation-7.39e-02

Pos logit contributions
agine+3.050
ttp+2.868
mingham+2.668
 balloons+2.614
VERTISEMENT+2.569
Neg logit contributions
ature-2.547
onduct-2.503
=]-2.410
 Shiv-2.371
arten-2.363
TokenHappy
Token ID25082
Feature activation+4.24e-01

Pos logit contributions
agine+0.602
ttp+0.574
mingham+0.537
 balloons+0.535
VERTISEMENT+0.517
Neg logit contributions
ature-0.544
onduct-0.533
arten-0.509
=]-0.505
 Shiv-0.498
TokenL
Token ID43
Feature activation+2.21e-01

Pos logit contributions
ature+3.293
onduct+3.182
arten+3.084
=]+3.040
ores+3.032
Neg logit contributions
agine-3.296
ttp-3.075
 balloons-2.916
mingham-2.897
VERTISEMENT-2.859
Token bad
Token ID2089
Feature activation-1.67e-01

Pos logit contributions
agine+1.472
ttp+1.344
mingham+1.193
 balloons+1.165
VERTISEMENT+1.094
Neg logit contributions
ature-4.036
onduct-4.035
arten-3.968
arella-3.899
=]-3.892
Token idea
Token ID2126
Feature activation+1.50e-01

Pos logit contributions
agine+1.217
ttp+1.153
 balloons+1.068
mingham+1.057
VERTISEMENT+1.032
Neg logit contributions
ature-1.375
onduct-1.359
arten-1.305
=]-1.289
ores-1.281
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
ature+1.289
onduct+1.260
arten+1.218
=]+1.204
ores+1.195
Neg logit contributions
agine-1.052
ttp-0.982
 balloons-0.919
mingham-0.916
VERTISEMENT-0.890
Token
Token ID198
Feature activation-2.77e-02

Pos logit contributions
agine+2.782
ttp+2.638
mingham+2.458
 balloons+2.440
VERTISEMENT+2.380
Neg logit contributions
ature-3.003
onduct-2.984
arten-2.863
=]-2.842
ores-2.806
Token
Token ID198
Feature activation-2.97e-01

Pos logit contributions
agine+0.212
ttp+0.200
 balloons+0.188
mingham+0.187
VERTISEMENT+0.181
Neg logit contributions
ature-0.218
onduct-0.214
arten-0.206
=]-0.203
ores-0.201
TokenReviewer
Token ID35407
Feature activation+1.57e+00

Pos logit contributions
agine+1.673
ttp+1.602
mingham+1.441
VERTISEMENT+1.352
 balloons+1.347
Neg logit contributions
ature-2.878
onduct-2.823
 Shiv-2.786
arella-2.737
arten-2.733
Token:
Token ID25
Feature activation-4.59e-01

Pos logit contributions
ature+7.500
=]+6.479
onduct+6.472
 Shiv+6.215
ores+6.197
Neg logit contributions
agine-15.072
 confir-15.066
VERTISEMENT-14.196
 artif-14.045
cknowled-13.651
Token Mike
Token ID4995
Feature activation-6.25e-02

Pos logit contributions
agine+3.472
ttp+3.298
 balloons+3.172
mingham+3.070
 FB+3.020
Neg logit contributions
ature-3.504
onduct-3.484
arten-3.307
=]-3.249
ores-3.230
TokenM
Token ID44
Feature activation-5.18e-01

Pos logit contributions
agine+0.496
ttp+0.474
 balloons+0.443
mingham+0.442
VERTISEMENT+0.430
Neg logit contributions
ature-0.469
onduct-0.462
arten-0.444
=]-0.439
ores-0.433
Tokenanners
Token ID15672
Feature activation-2.17e-01

Pos logit contributions
agine+3.942
ttp+3.734
 balloons+3.460
mingham+3.430
VERTISEMENT+3.334
Neg logit contributions
ature-3.893
onduct-3.823
=]-3.757
arten-3.718
 Shiv-3.690
Token -
Token ID532
Feature activation+4.55e-02

Pos logit contributions
agine+1.541
ttp+1.469
mingham+1.362
 balloons+1.360
VERTISEMENT+1.315
Neg logit contributions
ature-1.802
onduct-1.770
arten-1.713
=]-1.695
ores-1.677
Token 2010
Token ID3050
Feature activation-2.33e-01

Pos logit contributions
ature+0.407
onduct+0.395
arten+0.378
=]+0.370
ores+0.367
Neg logit contributions
agine-0.605
ttp-0.576
 balloons-0.548
mingham-0.547
VERTISEMENT-0.535
Tokenboys
Token ID13202
Feature activation-3.09e-01

Pos logit contributions
agine+1.995
ttp+1.887
mingham+1.771
 balloons+1.746
VERTISEMENT+1.674
Neg logit contributions
onduct-1.589
ature-1.587
 Shiv-1.548
arten-1.495
=]-1.490
Token beware
Token ID40600
Feature activation-2.29e-01

Pos logit contributions
agine+2.129
ttp+2.001
 balloons+1.855
VERTISEMENT+1.808
mingham+1.787
Neg logit contributions
ature-2.579
onduct-2.571
=]-2.450
arten-2.448
 Shiv-2.433
Token
Token ID198
Feature activation-2.54e-01

Pos logit contributions
agine+1.706
ttp+1.625
 balloons+1.522
mingham+1.505
VERTISEMENT+1.475
Neg logit contributions
ature-1.825
onduct-1.794
arten-1.717
=]-1.710
 Shiv-1.687
Token
Token ID198
Feature activation-6.71e-02

Pos logit contributions
agine+1.784
ttp+1.699
 balloons+1.573
mingham+1.570
 FB+1.508
Neg logit contributions
ature-2.121
onduct-2.099
arten-2.027
=]-1.988
arella-1.971
TokenReviewer
Token ID35407
Feature activation+1.54e+00

Pos logit contributions
agine+0.423
ttp+0.398
mingham+0.367
 balloons+0.361
VERTISEMENT+0.354
Neg logit contributions
ature-0.615
onduct-0.604
arten-0.585
 Shiv-0.582
=]-0.577
Token:
Token ID25
Feature activation-5.80e-01

Pos logit contributions
ature+7.335
=]+6.388
onduct+6.370
 Shiv+6.000
ores+5.988
Neg logit contributions
 confir-15.103
agine-15.005
 artif-14.017
VERTISEMENT-13.999
cknowled-13.566
Token j
Token ID474
Feature activation-7.53e-02

Pos logit contributions
agine+4.356
ttp+4.153
 balloons+4.018
mingham+3.880
 FB+3.825
Neg logit contributions
onduct-4.343
ature-4.342
arten-4.090
=]-4.035
ores-4.000
Tokenwt
Token ID46569
Feature activation-4.13e-01

Pos logit contributions
agine+0.619
ttp+0.587
mingham+0.553
 balloons+0.546
VERTISEMENT+0.527
Neg logit contributions
ature-0.549
onduct-0.536
=]-0.516
arten-0.513
 Shiv-0.509
Token0001
Token ID18005
Feature activation+1.68e-01

Pos logit contributions
agine+3.299
ttp+3.140
mingham+2.957
 balloons+2.906
VERTISEMENT+2.752
Neg logit contributions
ature-3.014
onduct-2.973
=]-2.864
arten-2.816
 Shiv-2.812
Token -
Token ID532
Feature activation+5.35e-02

Pos logit contributions
ature+1.391
onduct+1.354
arten+1.312
=]+1.287
ores+1.280
Neg logit contributions
agine-1.224
ttp-1.141
mingham-1.069
 balloons-1.069
VERTISEMENT-1.048
Token
Token ID198
Feature activation-3.15e-01

Pos logit contributions
agine+1.662
ttp+1.541
 balloons+1.477
mingham+1.441
VERTISEMENT+1.440
Neg logit contributions
ature-1.782
onduct-1.738
arten-1.702
=]-1.672
arella-1.655
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
agine+2.180
ttp+2.081
 balloons+1.930
mingham+1.905
 FB+1.854
Neg logit contributions
ature-2.644
onduct-2.625
arten-2.543
=]-2.480
arella-2.470
TokenWhat
Token ID2061
Feature activation+1.63e-01

Pos logit contributions
agine+0.916
ttp+0.877
mingham+0.826
 balloons+0.823
VERTISEMENT+0.814
Neg logit contributions
ature-0.673
onduct-0.661
arten-0.636
=]-0.620
arella-0.620
Token was
Token ID373
Feature activation+3.60e-01

Pos logit contributions
ature+1.241
onduct+1.204
arten+1.167
=]+1.148
arella+1.131
Neg logit contributions
agine-1.302
ttp-1.225
 balloons-1.169
mingham-1.145
VERTISEMENT-1.130
Token the
Token ID262
Feature activation+3.28e-01

Pos logit contributions
ature+3.014
onduct+2.941
arten+2.836
ores+2.784
 Shiv+2.773
Neg logit contributions
agine-2.583
ttp-2.415
mingham-2.245
 balloons-2.240
VERTISEMENT-2.193
Token most
Token ID749
Feature activation+1.45e+00

Pos logit contributions
ature+2.702
onduct+2.634
arten+2.552
ores+2.493
=]+2.486
Neg logit contributions
agine-2.405
ttp-2.263
 balloons-2.111
mingham-2.109
VERTISEMENT-2.057
Token interesting
Token ID3499
Feature activation+3.41e-01

Pos logit contributions
ature+7.795
onduct+7.685
 Shiv+7.614
arten+7.574
ores+7.487
Neg logit contributions
agine-13.126
ttp-12.155
mingham-11.866
VERTISEMENT-11.476
 balloons-11.135
Token thing
Token ID1517
Feature activation+2.74e-01

Pos logit contributions
ature+2.754
onduct+2.691
arten+2.598
=]+2.564
ores+2.541
Neg logit contributions
agine-2.550
ttp-2.397
 balloons-2.252
mingham-2.245
VERTISEMENT-2.184
Token you
Token ID345
Feature activation+6.59e-01

Pos logit contributions
ature+2.124
onduct+2.068
arten+1.996
=]+1.970
ores+1.941
Neg logit contributions
agine-2.148
ttp-2.034
 balloons-1.918
mingham-1.898
VERTISEMENT-1.850
Token learned
Token ID4499
Feature activation-6.05e-01

Pos logit contributions
ature+4.580
onduct+4.523
arten+4.330
ores+4.257
 Shiv+4.216
Neg logit contributions
agine-5.527
ttp-5.230
mingham-4.989
 balloons-4.956
VERTISEMENT-4.844
Token from
Token ID422
Feature activation-2.65e-01

Pos logit contributions
agine+3.693
ttp+3.436
 balloons+3.353
mingham+3.170
 FB+3.094
Neg logit contributions
ature-5.386
onduct-5.306
arten-5.069
=]-5.064
 Shiv-5.009
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
ature+3.160
onduct+3.069
arten+2.953
=]+2.914
 Shiv+2.902
Neg logit contributions
agine-3.482
ttp-3.269
mingham-3.101
 balloons-3.085
VERTISEMENT-3.004
Token
Token ID198
Feature activation+2.90e-02

Pos logit contributions
agine+0.929
ttp+0.882
 balloons+0.824
mingham+0.816
VERTISEMENT+0.788
Neg logit contributions
ature-1.022
onduct-1.010
arten-0.975
=]-0.954
ores-0.949
TokenSound
Token ID21369
Feature activation+4.98e-01

Pos logit contributions
ature+0.221
onduct+0.218
arten+0.210
 Shiv+0.205
=]+0.205
Neg logit contributions
agine-0.226
ttp-0.217
 balloons-0.201
mingham-0.201
VERTISEMENT-0.198
Tokentracks
Token ID46074
Feature activation+3.24e-01

Pos logit contributions
ature+2.522
onduct+2.413
arten+2.261
ores+2.203
=]+2.199
Neg logit contributions
agine-5.242
ttp-5.018
mingham-4.788
 balloons-4.750
VERTISEMENT-4.701
Token [
Token ID685
Feature activation+6.55e-01

Pos logit contributions
ature+2.529
onduct+2.466
arten+2.373
=]+2.339
ores+2.327
Neg logit contributions
agine-2.511
ttp-2.368
mingham-2.224
 balloons-2.217
VERTISEMENT-2.167
Token edit
Token ID4370
Feature activation+1.44e+00

Pos logit contributions
ature+3.182
onduct+3.007
arten+2.854
=]+2.795
ores+2.765
Neg logit contributions
agine-6.906
ttp-6.562
VERTISEMENT-6.387
mingham-6.323
 balloons-6.323
Token ]
Token ID2361
Feature activation-1.36e-01

Pos logit contributions
ature+4.725
=]+4.467
 Shiv+3.778
onduct+3.667
ores+3.553
Neg logit contributions
agine-16.115
 confir-15.774
 artif-15.302
VERTISEMENT-15.257
 balloons-15.136
Token
Token ID198
Feature activation+1.26e-01

Pos logit contributions
agine+0.969
ttp+0.926
mingham+0.851
 balloons+0.851
VERTISEMENT+0.830
Neg logit contributions
ature-1.125
onduct-1.112
arten-1.068
=]-1.058
ores-1.042
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
ature+0.951
onduct+0.926
arten+0.891
=]+0.880
ores+0.872
Neg logit contributions
agine-1.012
ttp-0.953
 balloons-0.899
mingham-0.899
VERTISEMENT-0.878
TokenVarious
Token ID40009
Feature activation+1.49e-01

Pos logit contributions
ature+0.997
onduct+0.977
arten+0.941
=]+0.924
 Shiv+0.919
Neg logit contributions
agine-0.986
ttp-0.936
 balloons-0.874
mingham-0.873
VERTISEMENT-0.854
Token sound
Token ID2128
Feature activation+3.46e-01

Pos logit contributions
ature+1.202
onduct+1.176
arten+1.136
=]+1.120
ores+1.108
Neg logit contributions
agine-1.108
ttp-1.042
 balloons-0.986
mingham-0.973
VERTISEMENT-0.949
Token
Token ID198
Feature activation-2.41e-01

Pos logit contributions
agine+2.223
ttp+2.108
 balloons+1.972
mingham+1.971
VERTISEMENT+1.924
Neg logit contributions
ature-2.267
onduct-2.222
arten-2.138
=]-2.110
ores-2.086
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
agine+1.708
ttp+1.630
 balloons+1.520
mingham+1.499
 FB+1.448
Neg logit contributions
ature-1.990
onduct-1.971
arten-1.905
=]-1.858
ores-1.853
TokenVideo
Token ID10798
Feature activation+2.66e-01

Pos logit contributions
agine+1.409
ttp+1.369
mingham+1.258
 balloons+1.253
VERTISEMENT+1.234
Neg logit contributions
ature-1.417
onduct-1.404
arten-1.348
 Shiv-1.328
arella-1.318
Token games
Token ID1830
Feature activation-3.27e-01

Pos logit contributions
ature+2.284
onduct+2.236
arten+2.163
=]+2.134
ores+2.119
Neg logit contributions
agine-1.859
ttp-1.740
 balloons-1.625
mingham-1.620
VERTISEMENT-1.572
Token [
Token ID685
Feature activation+5.52e-01

Pos logit contributions
agine+2.231
ttp+2.056
 balloons+2.009
mingham+1.928
VERTISEMENT+1.863
Neg logit contributions
ature-2.752
onduct-2.708
arten-2.644
=]-2.610
arella-2.562
Token edit
Token ID4370
Feature activation+1.44e+00

Pos logit contributions
ature+2.759
onduct+2.636
arten+2.485
=]+2.466
ores+2.423
Neg logit contributions
agine-5.757
ttp-5.470
VERTISEMENT-5.288
mingham-5.282
 balloons-5.279
Token ]
Token ID2361
Feature activation-2.07e-01

Pos logit contributions
ature+4.782
=]+4.463
 Shiv+3.775
onduct+3.700
ores+3.604
Neg logit contributions
agine-15.991
 confir-15.754
VERTISEMENT-15.351
 artif-15.345
 balloons-15.111
Token
Token ID198
Feature activation-2.08e-01

Pos logit contributions
agine+1.603
ttp+1.514
 balloons+1.421
mingham+1.421
VERTISEMENT+1.385
Neg logit contributions
ature-1.601
onduct-1.567
arten-1.508
=]-1.489
ores-1.474
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
agine+1.491
ttp+1.420
 balloons+1.326
mingham+1.310
 FB+1.264
Neg logit contributions
ature-1.702
onduct-1.686
arten-1.628
=]-1.587
ores-1.584
TokenIn
Token ID818
Feature activation-9.51e-02

Pos logit contributions
agine+2.485
ttp+2.441
mingham+2.237
 balloons+2.219
VERTISEMENT+2.209
Neg logit contributions
onduct-2.552
ature-2.543
arten-2.453
 Shiv-2.422
arella-2.405
Token the
Token ID262
Feature activation-4.25e-01

Pos logit contributions
agine+0.727
ttp+0.686
 balloons+0.654
mingham+0.644
VERTISEMENT+0.623
Neg logit contributions
ature-0.738
onduct-0.728
arten-0.703
=]-0.697
 Shiv-0.684
Token
Token ID247
Feature activation+1.42e-01

Pos logit contributions
agine+0.343
ttp+0.329
 balloons+0.311
mingham+0.309
VERTISEMENT+0.304
Neg logit contributions
ature-0.235
onduct-0.230
arten-0.219
=]-0.215
 Shiv-0.215
Tokens
Token ID82
Feature activation+1.94e-01

Pos logit contributions
ature+1.048
onduct+1.034
arten+0.994
=]+0.982
ores+0.968
Neg logit contributions
agine-1.150
ttp-1.091
 balloons-1.024
mingham-1.024
VERTISEMENT-1.002
Token annual
Token ID5079
Feature activation+1.22e-01

Pos logit contributions
ature+1.481
onduct+1.451
arten+1.397
=]+1.373
ores+1.360
Neg logit contributions
agine-1.529
ttp-1.445
 balloons-1.370
mingham-1.358
VERTISEMENT-1.328
Token barbecue
Token ID36646
Feature activation-7.97e-02

Pos logit contributions
ature+0.966
onduct+0.952
arten+0.921
=]+0.899
ores+0.891
Neg logit contributions
agine-0.922
ttp-0.872
 balloons-0.826
mingham-0.816
VERTISEMENT-0.797
Token
Token ID960
Feature activation+2.15e-01

Pos logit contributions
agine+0.542
ttp+0.512
 balloons+0.487
mingham+0.476
VERTISEMENT+0.458
Neg logit contributions
ature-0.681
onduct-0.679
=]-0.647
arten-0.647
ores-0.634
Tokend
Token ID67
Feature activation+1.43e+00

Pos logit contributions
ature+1.672
onduct+1.632
arten+1.577
=]+1.551
ores+1.537
Neg logit contributions
agine-1.677
ttp-1.581
 balloons-1.488
mingham-1.484
VERTISEMENT-1.444
Tokenub
Token ID549
Feature activation+2.15e-02

Pos logit contributions
ature+9.689
arten+9.202
onduct+9.145
ores+9.067
arella+8.671
Neg logit contributions
agine-10.669
ttp-10.376
 balloons-10.148
mingham-9.979
VERTISEMENT-9.932
Tokenbed
Token ID3077
Feature activation+3.47e-01

Pos logit contributions
ature+0.116
onduct+0.114
arten+0.107
=]+0.105
 Shiv+0.103
Neg logit contributions
agine-0.217
ttp-0.207
 balloons-0.199
mingham-0.198
VERTISEMENT-0.194
Token,
Token ID11
Feature activation-1.29e-01

Pos logit contributions
ature+2.748
onduct+2.673
arten+2.577
=]+2.544
 Shiv+2.532
Neg logit contributions
agine-2.643
ttp-2.484
 balloons-2.326
mingham-2.324
VERTISEMENT-2.248
Token naturally
Token ID8752
Feature activation-1.72e-01

Pos logit contributions
agine+0.948
ttp+0.882
 balloons+0.852
mingham+0.827
VERTISEMENT+0.809
Neg logit contributions
ature-1.047
onduct-1.034
arten-1.008
=]-0.991
ores-0.966
Token,
Token ID11
Feature activation-1.88e-01

Pos logit contributions
agine+1.227
ttp+1.151
 balloons+1.080
mingham+1.073
VERTISEMENT+1.049
Neg logit contributions
ature-1.446
onduct-1.419
arten-1.369
=]-1.355
ores-1.340
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
agine+1.231
ttp+1.169
 balloons+1.091
mingham+1.080
 FB+1.040
Neg logit contributions
ature-1.393
onduct-1.378
arten-1.331
=]-1.300
ores-1.294
TokenTh
Token ID817
Feature activation+4.96e-01

Pos logit contributions
agine+0.849
ttp+0.820
 balloons+0.756
mingham+0.755
VERTISEMENT+0.748
Neg logit contributions
ature-0.827
onduct-0.819
arten-0.789
 Shiv-0.774
=]-0.766
Tokenrill
Token ID20190
Feature activation-4.02e-02

Pos logit contributions
ature+3.686
onduct+3.604
arten+3.475
ores+3.431
=]+3.357
Neg logit contributions
agine-3.997
ttp-3.699
 balloons-3.607
mingham-3.578
VERTISEMENT-3.452
Token ride
Token ID6594
Feature activation-5.29e-02

Pos logit contributions
agine+0.300
ttp+0.282
 balloons+0.271
mingham+0.262
VERTISEMENT+0.255
Neg logit contributions
ature-0.324
onduct-0.320
arten-0.306
=]-0.304
arella-0.298
Token [
Token ID685
Feature activation+5.97e-01

Pos logit contributions
agine+0.388
ttp+0.365
 balloons+0.351
mingham+0.337
VERTISEMENT+0.333
Neg logit contributions
ature-0.430
onduct-0.420
arten-0.409
=]-0.403
ores-0.396
Token edit
Token ID4370
Feature activation+1.41e+00

Pos logit contributions
ature+2.992
onduct+2.812
arten+2.686
=]+2.658
ores+2.604
Neg logit contributions
agine-6.246
ttp-5.942
VERTISEMENT-5.732
 balloons-5.718
mingham-5.708
Token ]
Token ID2361
Feature activation+3.02e-02

Pos logit contributions
ature+4.730
=]+4.583
 Shiv+3.932
onduct+3.783
ores+3.702
Neg logit contributions
agine-15.620
 confir-15.017
VERTISEMENT-14.871
mingham-14.708
 artif-14.684
Token
Token ID198
Feature activation+4.79e-02

Pos logit contributions
ature+0.239
onduct+0.235
arten+0.226
=]+0.221
ores+0.221
Neg logit contributions
agine-0.229
ttp-0.217
 balloons-0.203
mingham-0.202
VERTISEMENT-0.196
Token
Token ID198
Feature activation+2.65e-02

Pos logit contributions
ature+0.370
onduct+0.361
arten+0.348
=]+0.343
ores+0.340
Neg logit contributions
agine-0.375
ttp-0.354
 balloons-0.333
mingham-0.332
VERTISEMENT-0.324
TokenThe
Token ID464
Feature activation+1.55e-01

Pos logit contributions
ature+0.208
onduct+0.205
arten+0.197
 Shiv+0.193
=]+0.192
Neg logit contributions
agine-0.201
ttp-0.194
 balloons-0.178
mingham-0.178
VERTISEMENT-0.176
Token T
Token ID309
Feature activation-5.05e-01

Pos logit contributions
ature+1.248
onduct+1.218
arten+1.177
=]+1.160
ores+1.150
Neg logit contributions
agine-1.169
ttp-1.099
 balloons-1.038
mingham-1.025
VERTISEMENT-1.002
Token scholar
Token ID15606
Feature activation-4.05e-01

Pos logit contributions
agine+2.702
ttp+2.556
mingham+2.466
 balloons+2.412
cknowled+2.329
Neg logit contributions
onduct-3.273
ature-3.272
 Shiv-3.077
arella-3.055
=]-3.053
Token in
Token ID287
Feature activation+6.23e-02

Pos logit contributions
agine+2.754
ttp+2.557
 balloons+2.437
mingham+2.423
cknowled+2.364
Neg logit contributions
ature-3.402
onduct-3.387
=]-3.238
arten-3.221
arella-3.197
Token the
Token ID262
Feature activation-1.39e-01

Pos logit contributions
ature+0.512
onduct+0.503
arten+0.485
=]+0.482
ores+0.473
Neg logit contributions
agine-0.456
ttp-0.427
mingham-0.402
 balloons-0.402
VERTISEMENT-0.388
Token legislature
Token ID15928
Feature activation+2.47e-01

Pos logit contributions
agine+1.057
ttp+0.981
 balloons+0.947
mingham+0.941
 FB+0.902
Neg logit contributions
ature-1.089
onduct-1.076
arten-1.041
=]-1.027
arella-1.011
Token at
Token ID379
Feature activation+7.57e-02

Pos logit contributions
ature+2.031
onduct+1.983
arten+1.917
=]+1.889
ores+1.879
Neg logit contributions
agine-1.806
ttp-1.695
 balloons-1.587
mingham-1.584
VERTISEMENT-1.540
Token that
Token ID326
Feature activation+1.39e+00

Pos logit contributions
ature+0.633
onduct+0.620
arten+0.599
=]+0.592
ores+0.586
Neg logit contributions
agine-0.544
ttp-0.509
 balloons-0.477
mingham-0.476
VERTISEMENT-0.463
Token time
Token ID640
Feature activation-2.10e-03

Pos logit contributions
ature+6.007
arten+5.371
onduct+5.123
 Shiv+5.090
=]+4.874
Neg logit contributions
agine-14.144
ttp-14.073
mingham-13.163
 balloons-13.062
VERTISEMENT-12.930
Token,
Token ID11
Feature activation+1.73e-01

Pos logit contributions
agine+0.015
ttp+0.014
 balloons+0.013
mingham+0.013
VERTISEMENT+0.012
Neg logit contributions
ature-0.018
onduct-0.018
arten-0.017
=]-0.017
 Shiv-0.017
Token was
Token ID373
Feature activation+2.93e-01

Pos logit contributions
ature+1.386
onduct+1.354
arten+1.307
=]+1.289
ores+1.276
Neg logit contributions
agine-1.304
ttp-1.226
 balloons-1.156
mingham-1.148
VERTISEMENT-1.116
Token one
Token ID530
Feature activation+2.23e-02

Pos logit contributions
ature+2.349
onduct+2.291
arten+2.212
=]+2.182
ores+2.170
Neg logit contributions
agine-2.207
ttp-2.079
mingham-1.946
 balloons-1.946
VERTISEMENT-1.895
Token of
Token ID286
Feature activation+5.67e-01

Pos logit contributions
ature+0.176
onduct+0.170
arten+0.166
 Shiv+0.162
=]+0.161
Neg logit contributions
agine-0.172
ttp-0.163
 balloons-0.153
mingham-0.151
VERTISEMENT-0.148
Tokenpress
Token ID8439
Feature activation+6.65e-01

Pos logit contributions
ature+1.319
onduct+1.291
arten+1.247
=]+1.225
 Shiv+1.217
Neg logit contributions
agine-1.299
ttp-1.224
 balloons-1.146
mingham-1.145
VERTISEMENT-1.117
Token X
Token ID1395
Feature activation+1.73e-01

Pos logit contributions
ature+5.663
onduct+5.455
arten+5.301
=]+5.250
ores+5.244
Neg logit contributions
agine-4.701
ttp-4.364
mingham-4.097
 balloons-4.020
VERTISEMENT-3.921
Token to
Token ID284
Feature activation+4.33e-01

Pos logit contributions
ature+1.412
onduct+1.381
arten+1.338
=]+1.315
 Shiv+1.304
Neg logit contributions
agine-1.275
ttp-1.201
 balloons-1.137
mingham-1.117
VERTISEMENT-1.101
Token kill
Token ID1494
Feature activation+1.94e-01

Pos logit contributions
ature+3.338
onduct+3.250
arten+3.133
=]+3.091
 Shiv+3.089
Neg logit contributions
agine-3.369
ttp-3.213
mingham-3.012
 balloons-2.975
VERTISEMENT-2.918
Token,
Token ID11
Feature activation+7.90e-01

Pos logit contributions
ature+1.548
onduct+1.516
arten+1.463
=]+1.439
ores+1.423
Neg logit contributions
agine-1.477
ttp-1.387
 balloons-1.316
mingham-1.290
VERTISEMENT-1.264
Token press
Token ID1803
Feature activation+1.39e+00

Pos logit contributions
ature+6.105
onduct+5.918
=]+5.676
ores+5.659
 Shiv+5.655
Neg logit contributions
agine-6.011
ttp-5.688
mingham-5.353
 balloons-5.228
VERTISEMENT-5.214
Token Y
Token ID575
Feature activation+6.14e-01

Pos logit contributions
ature+8.878
=]+8.167
onduct+8.118
ores+8.069
 Shiv+7.953
Neg logit contributions
agine-11.461
ttp-10.839
mingham-10.450
 balloons-9.983
VERTISEMENT-9.823
Token to
Token ID284
Feature activation+5.69e-01

Pos logit contributions
ature+3.992
onduct+3.876
arten+3.710
ores+3.692
 Shiv+3.646
Neg logit contributions
agine-5.405
ttp-5.063
mingham-4.832
 balloons-4.733
VERTISEMENT-4.643
Token spare
Token ID13952
Feature activation+7.33e-02

Pos logit contributions
ature+4.492
onduct+4.390
arten+4.244
 Shiv+4.219
=]+4.185
Neg logit contributions
agine-4.236
ttp-4.056
mingham-3.798
 balloons-3.685
VERTISEMENT-3.675
Token.
Token ID13
Feature activation-5.67e-02

Pos logit contributions
ature+0.575
onduct+0.564
arten+0.543
=]+0.535
ores+0.528
Neg logit contributions
agine-0.567
ttp-0.530
 balloons-0.508
mingham-0.495
VERTISEMENT-0.485
Token
Token ID447
Feature activation-9.74e-02

Pos logit contributions
agine+0.432
ttp+0.409
 balloons+0.388
VERTISEMENT+0.378
 FB+0.377
Neg logit contributions
onduct-0.439
ature-0.439
arten-0.421
ores-0.410
=]-0.408
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
agine+0.307
ttp+0.291
 balloons+0.273
mingham+0.271
VERTISEMENT+0.263
Neg logit contributions
ature-0.319
onduct-0.314
arten-0.302
=]-0.297
ores-0.295
TokenEnc
Token ID27195
Feature activation+8.76e-01

Pos logit contributions
ature+0.861
onduct+0.844
arten+0.814
=]+0.798
ores+0.795
Neg logit contributions
agine-0.838
ttp-0.795
 balloons-0.742
mingham-0.741
VERTISEMENT-0.725
Tokenryption
Token ID13168
Feature activation+5.77e-01

Pos logit contributions
ature+4.071
onduct+3.933
ores+3.567
arten+3.436
arella+3.285
Neg logit contributions
agine-9.442
ttp-9.035
 balloons-8.727
mingham-8.700
VERTISEMENT-8.447
Token details
Token ID3307
Feature activation+1.29e-01

Pos logit contributions
ature+4.531
onduct+4.383
arten+4.199
=]+4.163
ores+4.140
Neg logit contributions
agine-4.458
ttp-4.211
mingham-3.935
 balloons-3.876
VERTISEMENT-3.807
Token [
Token ID685
Feature activation+7.91e-01

Pos logit contributions
ature+1.035
onduct+1.017
arten+0.985
=]+0.969
ores+0.958
Neg logit contributions
agine-0.966
ttp-0.907
 balloons-0.859
mingham-0.848
VERTISEMENT-0.823
Token edit
Token ID4370
Feature activation+1.38e+00

Pos logit contributions
ature+3.635
onduct+3.401
arten+3.221
=]+3.209
ores+3.155
Neg logit contributions
agine-8.420
ttp-7.965
VERTISEMENT-7.852
 balloons-7.735
mingham-7.728
Token ]
Token ID2361
Feature activation-7.90e-02

Pos logit contributions
ature+4.942
=]+4.755
 Shiv+4.098
onduct+4.034
ores+3.940
Neg logit contributions
agine-15.010
 confir-14.532
VERTISEMENT-14.167
 artif-14.162
 balloons-14.084
Token
Token ID198
Feature activation+6.85e-02

Pos logit contributions
agine+0.581
ttp+0.553
 balloons+0.514
mingham+0.510
VERTISEMENT+0.494
Neg logit contributions
ature-0.640
onduct-0.631
arten-0.608
=]-0.594
ores-0.593
Token
Token ID198
Feature activation-3.10e-02

Pos logit contributions
ature+0.527
onduct+0.514
arten+0.496
=]+0.488
ores+0.484
Neg logit contributions
agine-0.540
ttp-0.509
 balloons-0.479
mingham-0.478
VERTISEMENT-0.466
TokenWE
Token ID8845
Feature activation+4.40e-01

Pos logit contributions
agine+0.235
ttp+0.225
mingham+0.207
 balloons+0.207
VERTISEMENT+0.203
Neg logit contributions
ature-0.244
onduct-0.241
arten-0.234
 Shiv-0.228
=]-0.226
TokenP
Token ID47
Feature activation+1.18e-01

Pos logit contributions
ature+4.186
onduct+4.087
arten+3.962
=]+3.952
 Shiv+3.914
Neg logit contributions
agine-2.663
ttp-2.401
mingham-2.259
 balloons-2.238
VERTISEMENT-2.108
Tokenos
Token ID418
Feature activation+2.77e-01

Pos logit contributions
ature+0.757
onduct+0.737
arten+0.707
=]+0.696
ores+0.689
Neg logit contributions
agine-0.950
ttp-0.900
 balloons-0.852
mingham-0.851
VERTISEMENT-0.831
Token &
Token ID1222
Feature activation-5.05e-02

Pos logit contributions
ature+2.104
onduct+2.053
arten+1.977
=]+1.947
ores+1.933
Neg logit contributions
agine-2.204
ttp-2.079
 balloons-1.959
mingham-1.955
VERTISEMENT-1.907
Token Bonnie
Token ID39203
Feature activation+7.25e-01

Pos logit contributions
agine+0.396
ttp+0.374
 balloons+0.354
mingham+0.349
VERTISEMENT+0.342
Neg logit contributions
ature-0.387
onduct-0.380
arten-0.368
=]-0.361
ores-0.355
Token &
Token ID1222
Feature activation-3.27e-01

Pos logit contributions
ature+5.472
onduct+5.285
arten+5.093
=]+5.040
 Shiv+5.036
Neg logit contributions
agine-5.628
ttp-5.238
 balloons-4.984
mingham-4.938
VERTISEMENT-4.915
Token Baby
Token ID14801
Feature activation-8.84e-02

Pos logit contributions
agine+2.393
ttp+2.253
 balloons+2.141
mingham+2.098
VERTISEMENT+2.065
Neg logit contributions
ature-2.598
onduct-2.582
arten-2.477
=]-2.450
arella-2.399
Token 2008
Token ID3648
Feature activation+1.38e+00

Pos logit contributions
agine+0.707
ttp+0.668
 balloons+0.630
mingham+0.628
VERTISEMENT+0.604
Neg logit contributions
ature-0.660
onduct-0.648
arten-0.627
=]-0.619
ores-0.610
Token01
Token ID486
Feature activation+3.93e-01

Pos logit contributions
onduct+4.825
ature+4.785
arten+4.575
arella+4.097
ores+4.030
Neg logit contributions
agine-14.878
ttp-14.287
 balloons-13.735
mingham-13.729
VERTISEMENT-13.494
Token09
Token ID2931
Feature activation+2.30e-01

Pos logit contributions
ature+2.427
onduct+2.346
arten+2.250
 Shiv+2.223
ores+2.221
Neg logit contributions
agine-3.671
ttp-3.454
 balloons-3.301
mingham-3.286
VERTISEMENT-3.246
Token O
Token ID440
Feature activation+1.54e-01

Pos logit contributions
ature+1.818
onduct+1.774
arten+1.709
=]+1.689
ores+1.674
Neg logit contributions
agine-1.765
ttp-1.658
mingham-1.558
 balloons-1.557
VERTISEMENT-1.516
Token&
Token ID5
Feature activation-9.76e-02

Pos logit contributions
ature+1.166
onduct+1.137
arten+1.094
=]+1.079
ores+1.070
Neg logit contributions
agine-1.231
ttp-1.161
 balloons-1.095
mingham-1.093
VERTISEMENT-1.065
TokenA
Token ID32
Feature activation+1.53e-01

Pos logit contributions
agine+0.835
ttp+0.801
mingham+0.748
 balloons+0.748
VERTISEMENT+0.732
Neg logit contributions
ature-0.670
onduct-0.663
arten-0.635
ores-0.621
=]-0.616
Token fabric
Token ID9664
Feature activation+5.91e-01

Pos logit contributions
agine+0.805
ttp+0.749
 balloons+0.720
mingham+0.700
cknowled+0.680
Neg logit contributions
ature-0.911
onduct-0.899
arten-0.873
=]-0.854
ores-0.843
Token of
Token ID286
Feature activation+2.62e-01

Pos logit contributions
ature+4.449
onduct+4.120
ores+4.044
arten+3.951
 Shiv+3.932
Neg logit contributions
agine-4.832
ttp-4.513
VERTISEMENT-4.236
mingham-4.232
 balloons-4.136
Token this
Token ID428
Feature activation+4.02e-02

Pos logit contributions
ature+2.107
onduct+2.058
arten+1.980
=]+1.953
 Shiv+1.941
Neg logit contributions
agine-1.961
ttp-1.848
mingham-1.729
 balloons-1.728
VERTISEMENT-1.685
Token country
Token ID1499
Feature activation+2.19e-01

Pos logit contributions
ature+0.331
onduct+0.326
arten+0.317
=]+0.311
ores+0.309
Neg logit contributions
agine-0.293
ttp-0.275
 balloons-0.259
mingham-0.256
VERTISEMENT-0.250
Token is
Token ID318
Feature activation+7.73e-01

Pos logit contributions
ature+1.799
onduct+1.758
arten+1.698
=]+1.675
ores+1.663
Neg logit contributions
agine-1.615
ttp-1.516
 balloons-1.421
mingham-1.418
VERTISEMENT-1.379
Token being
Token ID852
Feature activation+1.38e+00

Pos logit contributions
ature+5.874
onduct+5.659
 Shiv+5.432
arten+5.409
ores+5.383
Neg logit contributions
agine-5.920
ttp-5.691
mingham-5.274
VERTISEMENT-5.229
 balloons-5.128
Token torn
Token ID12445
Feature activation+8.18e-01

Pos logit contributions
ature+8.637
onduct+8.512
 Shiv+8.205
arten+8.097
ores+8.053
Neg logit contributions
agine-11.071
ttp-10.576
VERTISEMENT-10.204
mingham-9.903
 balloons-9.396
Token as
Token ID355
Feature activation-1.57e-02

Pos logit contributions
ature+5.051
onduct+4.806
ores+4.641
 Shiv+4.575
arten+4.554
Neg logit contributions
agine-7.290
ttp-6.993
mingham-6.729
VERTISEMENT-6.716
 balloons-6.424
Tokenunder
Token ID4625
Feature activation+3.84e-03

Pos logit contributions
agine+0.125
ttp+0.119
 balloons+0.113
mingham+0.111
VERTISEMENT+0.107
Neg logit contributions
ature-0.119
onduct-0.116
arten-0.113
=]-0.111
ores-0.109
Token by
Token ID416
Feature activation+2.81e-01

Pos logit contributions
ature+0.032
onduct+0.032
arten+0.031
=]+0.031
 Shiv+0.030
Neg logit contributions
agine-0.027
ttp-0.026
 balloons-0.024
mingham-0.024
VERTISEMENT-0.023
Token a
Token ID257
Feature activation+9.70e-02

Pos logit contributions
ature+2.254
onduct+2.199
arten+2.118
=]+2.093
 Shiv+2.078
Neg logit contributions
agine-2.115
ttp-1.990
mingham-1.868
 balloons-1.860
VERTISEMENT-1.818
Tokenness
Token ID1108
Feature activation+7.53e-02

Pos logit contributions
ature+2.975
onduct+2.896
arten+2.796
=]+2.750
ores+2.737
Neg logit contributions
agine-2.909
ttp-2.739
 balloons-2.570
mingham-2.570
VERTISEMENT-2.507
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
ature+0.635
onduct+0.626
arten+0.605
=]+0.601
 Shiv+0.590
Neg logit contributions
agine-0.534
ttp-0.499
 balloons-0.471
mingham-0.464
VERTISEMENT-0.450
Token
Token ID198
Feature activation-2.69e-02

Pos logit contributions
ature+1.216
onduct+1.200
arten+1.157
=]+1.139
ores+1.132
Neg logit contributions
agine-1.006
ttp-0.947
 balloons-0.886
mingham-0.880
VERTISEMENT-0.859
Token
Token ID198
Feature activation-2.49e-01

Pos logit contributions
agine+0.197
ttp+0.188
mingham+0.175
 balloons+0.174
VERTISEMENT+0.171
Neg logit contributions
ature-0.218
onduct-0.216
arten-0.208
=]-0.203
ores-0.203
TokenContinue
Token ID29453
Feature activation+8.52e-01

Pos logit contributions
agine+1.736
ttp+1.676
mingham+1.524
VERTISEMENT+1.522
 balloons+1.512
Neg logit contributions
onduct-2.055
ature-2.040
arten-1.961
arella-1.935
 Shiv-1.933
Token Reading
Token ID11725
Feature activation+1.37e+00

Pos logit contributions
ature+5.307
onduct+5.039
arten+4.880
 Shiv+4.804
ores+4.718
Neg logit contributions
agine-7.680
ttp-7.429
mingham-7.006
 balloons-6.824
VERTISEMENT-6.744
Token Below
Token ID10383
Feature activation+3.01e-01

Pos logit contributions
ature+7.045
onduct+6.557
 Shiv+6.512
ores+6.171
arten+6.128
Neg logit contributions
agine-12.783
 balloons-12.093
ttp-12.018
mingham-11.797
cknowled-11.421
Token Advertisement
Token ID39711
Feature activation+1.97e-01

Pos logit contributions
ature+1.798
onduct+1.760
arten+1.660
 Shiv+1.630
=]+1.623
Neg logit contributions
agine-2.871
ttp-2.742
mingham-2.611
 balloons-2.602
VERTISEMENT-2.524
Token<|endoftext|>
Token ID50256
Feature activation-1.70e-02

Pos logit contributions
ature+1.440
onduct+1.391
arten+1.340
=]+1.322
 Shiv+1.322
Neg logit contributions
agine-1.625
ttp-1.533
 balloons-1.458
mingham-1.449
VERTISEMENT-1.393
TokenThere
Token ID1858
Feature activation+1.58e-01

Pos logit contributions
agine+0.130
ttp+0.124
mingham+0.115
 balloons+0.114
VERTISEMENT+0.112
Neg logit contributions
ature-0.134
onduct-0.132
arten-0.127
 Shiv-0.125
arella-0.124
Token are
Token ID389
Feature activation+3.64e-02

Pos logit contributions
ature+1.248
onduct+1.220
arten+1.178
=]+1.156
ores+1.152
Neg logit contributions
agine-1.208
ttp-1.134
 balloons-1.071
mingham-1.063
VERTISEMENT-1.028
Token My
Token ID2011
Feature activation+8.86e-02

Pos logit contributions
ature+2.617
onduct+2.554
arten+2.462
=]+2.419
ores+2.409
Neg logit contributions
agine-2.619
ttp-2.470
mingham-2.319
 balloons-2.317
VERTISEMENT-2.254
Token top
Token ID1353
Feature activation-5.66e-02

Pos logit contributions
ature+0.659
onduct+0.645
arten+0.623
=]+0.619
 Shiv+0.606
Neg logit contributions
agine-0.715
ttp-0.674
 balloons-0.641
mingham-0.634
VERTISEMENT-0.620
Token 10
Token ID838
Feature activation-1.58e-01

Pos logit contributions
agine+0.407
ttp+0.381
 balloons+0.367
mingham+0.354
 FB+0.351
Neg logit contributions
ature-0.463
onduct-0.459
arten-0.440
=]-0.440
ores-0.428
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
agine+1.150
ttp+1.075
 balloons+1.030
mingham+1.001
VERTISEMENT+0.992
Neg logit contributions
ature-1.279
onduct-1.260
arten-1.213
=]-1.205
 Shiv-1.189
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
agine+0.787
ttp+0.746
 balloons+0.698
mingham+0.693
VERTISEMENT+0.667
Neg logit contributions
ature-0.848
onduct-0.833
arten-0.805
=]-0.789
ores-0.783
TokenEDIT
Token ID24706
Feature activation+1.37e+00

Pos logit contributions
agine+0.738
ttp+0.702
mingham+0.651
 balloons+0.650
VERTISEMENT+0.643
Neg logit contributions
ature-0.805
onduct-0.795
arten-0.768
 Shiv-0.756
=]-0.752
TokenOR
Token ID1581
Feature activation+5.06e-01

Pos logit contributions
ature+6.428
ores+6.191
onduct+6.059
=]+5.971
 Shiv+5.732
Neg logit contributions
agine-13.824
ttp-12.794
mingham-12.625
 balloons-12.011
cknowled-11.854
Token'
Token ID6
Feature activation-1.75e-01

Pos logit contributions
ature+4.890
onduct+4.723
=]+4.626
arten+4.580
 Shiv+4.563
Neg logit contributions
agine-2.976
ttp-2.730
mingham-2.552
 balloons-2.482
cknowled-2.300
TokenS
Token ID50
Feature activation-1.82e-01

Pos logit contributions
agine+1.327
ttp+1.283
VERTISEMENT+1.221
 balloons+1.207
 FB+1.188
Neg logit contributions
ature-1.328
onduct-1.323
arten-1.285
arella-1.242
ores-1.235
Token NOTE
Token ID24550
Feature activation+6.12e-01

Pos logit contributions
agine+1.222
ttp+1.133
 balloons+1.065
VERTISEMENT+1.062
 FB+1.046
Neg logit contributions
ature-1.566
onduct-1.557
arten-1.524
ores-1.491
=]-1.487
Token:
Token ID25
Feature activation+3.50e-01

Pos logit contributions
ature+4.011
onduct+3.896
=]+3.676
arten+3.668
ores+3.643
Neg logit contributions
agine-5.319
ttp-5.033
 balloons-4.740
mingham-4.728
VERTISEMENT-4.639
Token that
Token ID326
Feature activation-7.33e-01

Pos logit contributions
agine+1.596
ttp+1.501
 balloons+1.399
mingham+1.380
 FB+1.311
Neg logit contributions
ature-2.247
onduct-2.209
arten-2.144
=]-2.125
arella-2.099
Token the
Token ID262
Feature activation-1.22e+00

Pos logit contributions
agine+4.111
ttp+4.028
 balloons+3.669
 FB+3.560
mingham+3.529
Neg logit contributions
onduct-6.750
ature-6.740
arten-6.561
=]-6.428
arella-6.403
Token old
Token ID1468
Feature activation-7.80e-01

Pos logit contributions
agine+4.506
ttp+4.261
 balloons+3.659
 FB+3.614
 execut+3.598
Neg logit contributions
onduct-12.981
arten-12.859
ature-12.782
=]-12.571
ores-12.325
Token address
Token ID2209
Feature activation-9.54e-01

Pos logit contributions
agine+4.674
ttp+4.464
 balloons+4.074
 FB+4.000
 execut+3.962
Neg logit contributions
onduct-6.888
ature-6.782
arten-6.692
=]-6.612
arella-6.514
Token https
Token ID3740
Feature activation-4.00e-01

Pos logit contributions
agine+6.041
ttp+5.894
 balloons+5.310
mingham+5.215
 FB+5.087
Neg logit contributions
onduct-8.014
ature-7.906
arten-7.679
=]-7.654
arella-7.434
Token://
Token ID1378
Feature activation-1.93e+00

Pos logit contributions
agine+2.853
ttp+2.757
mingham+2.483
 balloons+2.463
 FB+2.366
Neg logit contributions
onduct-3.253
ature-3.240
arten-3.118
=]-3.034
arella-3.030
Token.
Token ID764
Feature activation-1.14e+00

Pos logit contributions
ttp+10.877
agine+10.836
 execut+9.794
 balloons+9.608
 htt+9.429
Neg logit contributions
onduct-13.947
=]-13.470
ature-13.339
arten-13.317
antam-13.188
Tokennice
Token ID44460
Feature activation-6.08e-02

Pos logit contributions
agine+7.420
ttp+7.103
 balloons+6.014
mingham+5.907
fy+5.814
Neg logit contributions
onduct-9.598
arten-9.108
 Shiv-9.094
ature-9.036
=]-8.974
Tokenhash
Token ID17831
Feature activation-1.33e-01

Pos logit contributions
agine+0.523
ttp+0.497
mingham+0.470
 balloons+0.461
VERTISEMENT+0.449
Neg logit contributions
ature-0.422
onduct-0.417
arten-0.398
=]-0.389
 Shiv-0.385
Token.
Token ID13
Feature activation-4.72e-01

Pos logit contributions
agine+0.863
ttp+0.815
 balloons+0.750
mingham+0.746
VERTISEMENT+0.712
Neg logit contributions
ature-1.199
onduct-1.182
arten-1.144
=]-1.128
ores-1.121
Tokencom
Token ID785
Feature activation-4.55e-01

Pos logit contributions
agine+2.298
ttp+2.195
mingham+1.877
 balloons+1.848
 FB+1.752
Neg logit contributions
ature-4.854
onduct-4.848
arten-4.773
 Shiv-4.696
=]-4.628
Token01
Token ID486
Feature activation+1.62e-02

Pos logit contributions
agine+2.258
ttp+2.153
mingham+1.988
 balloons+1.961
VERTISEMENT+1.889
Neg logit contributions
ature-2.477
onduct-2.406
arten-2.330
 Shiv-2.293
=]-2.293
Token606
Token ID33206
Feature activation-4.53e-01

Pos logit contributions
ature+0.136
onduct+0.133
arten+0.129
=]+0.127
ores+0.126
Neg logit contributions
agine-0.116
ttp-0.109
 balloons-0.102
mingham-0.101
VERTISEMENT-0.098
Token 7
Token ID767
Feature activation-1.73e-01

Pos logit contributions
agine+2.841
ttp+2.676
 balloons+2.508
 FB+2.471
mingham+2.410
Neg logit contributions
ature-4.020
onduct-3.979
arten-3.886
arella-3.778
ores-3.757
Token201
Token ID1264
Feature activation-1.54e-01

Pos logit contributions
agine+1.224
ttp+1.157
 balloons+1.077
mingham+1.061
VERTISEMENT+1.038
Neg logit contributions
ature-1.434
onduct-1.417
arten-1.377
=]-1.343
arella-1.335
Token99
Token ID2079
Feature activation-2.40e-01

Pos logit contributions
agine+1.017
ttp+0.957
 balloons+0.897
mingham+0.875
 FB+0.853
Neg logit contributions
ature-1.359
onduct-1.341
arten-1.302
arella-1.268
=]-1.268
Token;
Token ID26
Feature activation-1.76e+00

Pos logit contributions
agine+1.696
ttp+1.613
 balloons+1.510
mingham+1.487
VERTISEMENT+1.428
Neg logit contributions
ature-2.001
onduct-1.967
arten-1.902
=]-1.873
arella-1.872
Token head
Token ID1182
Feature activation-6.16e-01

Pos logit contributions
agine+9.674
ttp+8.599
 balloons+8.565
mingham+8.273
 beh+7.960
Neg logit contributions
onduct-13.250
ature-13.121
arella-12.937
 Shiv-12.881
arten-12.544
Tokenwater
Token ID7050
Feature activation-5.10e-01

Pos logit contributions
agine+4.762
ttp+4.421
mingham+4.232
 balloons+4.004
fy+3.852
Neg logit contributions
ature-4.569
onduct-4.510
 Shiv-4.493
=]-4.393
arten-4.323
Token.
Token ID13
Feature activation-7.09e-01

Pos logit contributions
agine+3.705
ttp+3.446
mingham+3.225
 balloons+3.175
VERTISEMENT+2.963
Neg logit contributions
ature-4.108
onduct-4.038
=]-3.926
 Shiv-3.924
arten-3.877
Tokencom
Token ID785
Feature activation-7.53e-01

Pos logit contributions
agine+6.549
ttp+6.243
mingham+6.022
 balloons+5.783
 FB+5.613
Neg logit contributions
onduct-4.044
ature-3.974
 Shiv-3.851
=]-3.846
arten-3.842
Token),
Token ID828
Feature activation-3.94e-01

Pos logit contributions
agine+3.682
ttp+3.334
mingham+3.066
 balloons+2.995
 FB+2.801
Neg logit contributions
ature-7.566
onduct-7.416
=]-7.353
arten-7.256
 Shiv-7.182
Tokenqa
Token ID20402
Feature activation+9.11e-02

Pos logit contributions
ature+0.683
onduct+0.670
arten+0.643
=]+0.636
 Shiv+0.628
Neg logit contributions
agine-0.713
ttp-0.671
 balloons-0.632
mingham-0.631
VERTISEMENT-0.613
Token,
Token ID11
Feature activation-4.25e-01

Pos logit contributions
ature+0.796
onduct+0.781
arten+0.757
=]+0.748
ores+0.739
Neg logit contributions
agine-0.620
ttp-0.578
 balloons-0.540
mingham-0.537
VERTISEMENT-0.521
Token for
Token ID329
Feature activation-1.64e-01

Pos logit contributions
agine+3.219
ttp+3.038
 balloons+2.902
mingham+2.818
VERTISEMENT+2.744
Neg logit contributions
ature-3.266
onduct-3.232
arten-3.122
=]-3.064
arella-3.026
Token men
Token ID1450
Feature activation-2.78e-01

Pos logit contributions
agine+1.235
ttp+1.161
 balloons+1.106
mingham+1.087
VERTISEMENT+1.058
Neg logit contributions
ature-1.292
onduct-1.284
arten-1.233
=]-1.206
arella-1.202
Token),
Token ID828
Feature activation-1.95e-02

Pos logit contributions
agine+1.749
ttp+1.606
 balloons+1.522
mingham+1.475
VERTISEMENT+1.388
Neg logit contributions
onduct-2.493
ature-2.487
arten-2.415
=]-2.390
arella-2.389
Token iron
Token ID6953
Feature activation-1.69e+00

Pos logit contributions
agine+0.142
ttp+0.133
 balloons+0.127
mingham+0.125
VERTISEMENT+0.122
Neg logit contributions
ature-0.160
onduct-0.156
arten-0.151
=]-0.149
ores-0.147
Token (
Token ID357
Feature activation+1.71e-02

Pos logit contributions
agine+9.919
 balloons+9.226
mingham+8.872
ttp+8.802
VERTISEMENT+8.390
Neg logit contributions
onduct-12.337
=]-12.075
arella-12.054
arten-11.977
ature-11.691
Tokentem
Token ID11498
Feature activation-1.41e-01

Pos logit contributions
ature+0.130
onduct+0.127
arten+0.122
=]+0.121
 Shiv+0.120
Neg logit contributions
agine-0.136
ttp-0.128
mingham-0.121
 balloons-0.120
VERTISEMENT-0.116
Tokenür
Token ID25151
Feature activation-2.76e-01

Pos logit contributions
agine+1.124
ttp+1.051
mingham+0.988
 balloons+0.987
VERTISEMENT+0.943
Neg logit contributions
ature-1.059
onduct-1.046
=]-1.007
arten-1.004
 Shiv-0.987
Token),
Token ID828
Feature activation+2.35e-03

Pos logit contributions
agine+1.961
ttp+1.830
mingham+1.713
 balloons+1.713
VERTISEMENT+1.632
Neg logit contributions
ature-2.275
onduct-2.267
arten-2.189
=]-2.168
 Shiv-2.139
Token steel
Token ID7771
Feature activation-9.95e-01

Pos logit contributions
ature+0.019
onduct+0.019
arten+0.018
=]+0.018
ores+0.018
Neg logit contributions
agine-0.017
ttp-0.016
 balloons-0.015
mingham-0.015
VERTISEMENT-0.015
Token claim
Token ID1624
Feature activation-1.38e-01

Pos logit contributions
agine+1.808
ttp+1.664
 balloons+1.628
mingham+1.572
 FB+1.520
Neg logit contributions
ature-2.013
onduct-1.983
arten-1.936
=]-1.906
arella-1.868
Token to
Token ID284
Feature activation-3.35e-01

Pos logit contributions
agine+1.042
ttp+0.987
 balloons+0.934
mingham+0.918
VERTISEMENT+0.904
Neg logit contributions
ature-1.088
onduct-1.061
arten-1.029
=]-1.017
arella-1.004
Token be
Token ID307
Feature activation-2.74e-01

Pos logit contributions
agine+2.396
ttp+2.172
 balloons+2.124
mingham+2.070
 FB+1.993
Neg logit contributions
ature-2.807
onduct-2.733
arten-2.677
=]-2.606
arella-2.566
Token (
Token ID357
Feature activation+6.50e-02

Pos logit contributions
agine+1.958
ttp+1.814
 balloons+1.758
mingham+1.708
 FB+1.654
Neg logit contributions
ature-2.259
onduct-2.218
arten-2.173
=]-2.122
arella-2.088
Tokenin
Token ID259
Feature activation-5.22e-01

Pos logit contributions
ature+0.492
onduct+0.483
arten+0.466
=]+0.455
 Shiv+0.454
Neg logit contributions
agine-0.518
ttp-0.489
 balloons-0.459
mingham-0.459
VERTISEMENT-0.444
Token theory
Token ID4583
Feature activation-1.69e+00

Pos logit contributions
agine+3.421
ttp+3.202
 balloons+3.052
mingham+2.945
 FB+2.845
Neg logit contributions
ature-4.412
onduct-4.358
arten-4.279
=]-4.186
arella-4.159
Token at
Token ID379
Feature activation-5.61e-01

Pos logit contributions
agine+7.298
 balloons+6.690
ttp+6.606
mingham+6.121
cknowled+5.594
Neg logit contributions
ature-15.178
arten-15.099
onduct-14.982
arella-14.820
=]-14.627
Token least
Token ID1551
Feature activation-1.08e+00

Pos logit contributions
agine+3.424
ttp+3.174
 balloons+3.063
mingham+2.859
 FB+2.820
Neg logit contributions
ature-5.022
onduct-4.911
arten-4.826
ores-4.733
=]-4.712
Token)
Token ID8
Feature activation-1.72e-01

Pos logit contributions
agine+4.237
ttp+3.957
 balloons+3.766
mingham+3.577
cknowled+3.408
Neg logit contributions
ature-11.023
arten-10.924
onduct-10.710
=]-10.595
 Shiv-10.512
Token universal
Token ID10112
Feature activation+1.86e-01

Pos logit contributions
agine+1.260
ttp+1.175
 balloons+1.130
mingham+1.107
VERTISEMENT+1.066
Neg logit contributions
ature-1.397
onduct-1.378
arten-1.343
=]-1.310
arella-1.294
Token.
Token ID13
Feature activation-3.02e-02

Pos logit contributions
ature+1.631
onduct+1.603
arten+1.551
=]+1.532
ores+1.515
Neg logit contributions
agine-1.261
ttp-1.178
 balloons-1.100
mingham-1.090
VERTISEMENT-1.062
Token.
Token ID13
Feature activation-6.60e-01

Pos logit contributions
agine+0.762
ttp+0.719
 balloons+0.660
mingham+0.659
VERTISEMENT+0.631
Neg logit contributions
ature-1.056
onduct-1.040
arten-1.010
=]-0.989
ores-0.988
TokenColor
Token ID10258
Feature activation-1.48e-01

Pos logit contributions
agine+3.900
ttp+3.824
mingham+3.475
VERTISEMENT+3.446
 balloons+3.440
Neg logit contributions
onduct-5.715
ature-5.684
arten-5.644
arella-5.563
 Shiv-5.453
Token]
Token ID60
Feature activation+3.72e-01

Pos logit contributions
agine+1.199
ttp+1.148
mingham+1.074
 balloons+1.068
VERTISEMENT+1.033
Neg logit contributions
ature-1.079
onduct-1.054
arten-1.018
ores-0.992
arella-0.990
Token::
Token ID3712
Feature activation-1.28e-01

Pos logit contributions
ature+1.379
onduct+1.270
=]+1.189
arten+1.161
ores+1.140
Neg logit contributions
agine-4.429
ttp-4.212
 balloons-4.112
mingham-4.080
VERTISEMENT-4.038
TokenFrom
Token ID4863
Feature activation-1.03e+00

Pos logit contributions
agine+0.793
ttp+0.756
 balloons+0.686
mingham+0.681
VERTISEMENT+0.673
Neg logit contributions
ature-1.179
onduct-1.171
arten-1.136
 Shiv-1.109
ores-1.107
TokenAr
Token ID3163
Feature activation-1.66e+00

Pos logit contributions
ttp+4.759
agine+4.494
mingham+3.865
GI+3.865
 balloons+3.843
Neg logit contributions
onduct-10.008
arten-9.578
 Shiv-9.558
ature-9.518
arella-9.488
Tokengb
Token ID22296
Feature activation-1.06e+00

Pos logit contributions
agine+5.003
ttp+4.561
mingham+4.540
fy+3.435
gb+3.121
Neg logit contributions
onduct-17.770
 Shiv-17.677
-17.556
arten-17.125
ature-16.953
Token($
Token ID16763
Feature activation-3.69e-01

Pos logit contributions
ttp+5.985
agine+5.680
mingham+5.162
tml+5.045
VERTISEMENT+4.918
Neg logit contributions
ature-9.221
onduct-9.150
arten-9.081
 Shiv-8.966
ores-8.830
TokenFC
Token ID4851
Feature activation+4.03e-01

Pos logit contributions
agine+3.136
ttp+2.998
mingham+2.830
 balloons+2.813
VERTISEMENT+2.758
Neg logit contributions
ature-2.479
onduct-2.461
arten-2.379
 Shiv-2.354
arella-2.291
Token2
Token ID17
Feature activation+3.52e-01

Pos logit contributions
ature+2.973
onduct+2.898
=]+2.762
arten+2.751
ores+2.729
Neg logit contributions
agine-3.267
ttp-3.061
 balloons-2.922
mingham-2.904
VERTISEMENT-2.801
Token[
Token ID58
Feature activation+8.16e-02

Pos logit contributions
ature+2.430
onduct+2.367
arten+2.268
=]+2.231
ores+2.208
Neg logit contributions
agine-3.047
ttp-2.885
 balloons-2.738
mingham-2.733
VERTISEMENT-2.669
Token mus
Token ID1928
Feature activation-6.31e-01

Pos logit contributions
agine+4.141
ttp+3.727
 balloons+3.682
mingham+3.506
VERTISEMENT+3.467
Neg logit contributions
ature-4.705
onduct-4.669
arten-4.559
arella-4.497
=]-4.437
Tokenics
Token ID873
Feature activation-8.14e-02

Pos logit contributions
agine+4.181
ttp+3.854
mingham+3.720
 balloons+3.630
 FB+3.378
Neg logit contributions
onduct-5.130
ature-5.123
=]-5.086
arten-5.034
 Shiv-4.933
Token.
Token ID13
Feature activation-1.16e-01

Pos logit contributions
agine+0.563
ttp+0.523
 balloons+0.496
mingham+0.487
VERTISEMENT+0.469
Neg logit contributions
ature-0.693
onduct-0.683
=]-0.663
arten-0.663
 Shiv-0.651
Token It
Token ID632
Feature activation-3.14e-01

Pos logit contributions
agine+0.862
ttp+0.813
 balloons+0.769
mingham+0.757
 FB+0.743
Neg logit contributions
ature-0.924
onduct-0.919
arten-0.889
=]-0.862
arella-0.861
Token's
Token ID338
Feature activation-2.37e-01

Pos logit contributions
agine+2.218
ttp+2.026
 balloons+2.004
mingham+1.889
cknowled+1.818
Neg logit contributions
ature-2.623
onduct-2.597
=]-2.501
arten-2.490
arella-2.444
Token iron
Token ID6953
Feature activation-1.64e+00

Pos logit contributions
agine+1.767
ttp+1.612
 balloons+1.573
mingham+1.531
VERTISEMENT+1.469
Neg logit contributions
ature-1.913
onduct-1.888
arten-1.812
=]-1.791
arella-1.781
Tokenical
Token ID605
Feature activation+7.89e-02

Pos logit contributions
agine+10.006
 balloons+9.774
ttp+9.310
mingham+9.035
fy+8.639
Neg logit contributions
onduct-11.548
arten-11.226
=]-11.037
ature-10.779
arella-10.715
Token that
Token ID326
Feature activation-3.44e-01

Pos logit contributions
ature+0.658
onduct+0.648
arten+0.627
=]+0.618
ores+0.612
Neg logit contributions
agine-0.566
ttp-0.529
 balloons-0.500
mingham-0.494
VERTISEMENT-0.479
Token a
Token ID257
Feature activation-4.84e-01

Pos logit contributions
agine+2.485
ttp+2.292
 balloons+2.242
mingham+2.145
 FB+2.095
Neg logit contributions
ature-2.804
onduct-2.776
arten-2.690
arella-2.633
=]-2.610
Token lot
Token ID1256
Feature activation+3.83e-02

Pos logit contributions
agine+3.332
ttp+3.050
 balloons+2.888
cknowled+2.881
mingham+2.880
Neg logit contributions
onduct-4.085
ature-4.026
arten-3.946
arella-3.833
ores-3.776
Token of
Token ID286
Feature activation-1.84e-02

Pos logit contributions
ature+0.305
onduct+0.296
arten+0.287
ores+0.282
=]+0.282
Neg logit contributions
agine-0.293
ttp-0.275
mingham-0.257
 balloons-0.257
VERTISEMENT-0.252
Token Rod
Token ID6882
Feature activation-2.77e-01

Pos logit contributions
agine+2.607
ttp+2.457
 balloons+2.365
mingham+2.280
 FB+2.231
Neg logit contributions
ature-2.862
onduct-2.815
arten-2.723
=]-2.702
arella-2.644
Tokenolf
Token ID4024
Feature activation-4.76e-01

Pos logit contributions
agine+1.954
ttp+1.803
mingham+1.693
VERTISEMENT+1.655
 balloons+1.646
Neg logit contributions
ature-2.325
=]-2.263
onduct-2.247
arten-2.174
 Shiv-2.167
Tokeno
Token ID78
Feature activation-5.45e-01

Pos logit contributions
agine+2.113
ttp+1.936
mingham+1.645
 balloons+1.637
 FB+1.629
Neg logit contributions
ature-4.977
onduct-4.928
arten-4.902
=]-4.897
-4.856
Token Al
Token ID978
Feature activation-3.34e-01

Pos logit contributions
agine+4.308
ttp+3.988
 balloons+3.888
 FB+3.843
mingham+3.720
Neg logit contributions
onduct-3.950
ature-3.921
arten-3.752
=]-3.585
arella-3.568
Tokenar
Token ID283
Feature activation-7.49e-01

Pos logit contributions
agine+3.036
ttp+2.820
mingham+2.744
 balloons+2.627
VERTISEMENT+2.615
Neg logit contributions
ature-2.131
onduct-2.081
=]-1.966
-1.952
arten-1.949
Tokencon
Token ID1102
Feature activation-1.58e+00

Pos logit contributions
agine+5.021
ttp+4.332
mingham+4.127
 balloons+3.786
cknowled+3.777
Neg logit contributions
ature-6.386
-6.309
onduct-6.292
 Shiv-6.038
=]-6.017
Token Ortiz
Token ID39039
Feature activation-8.28e-01

Pos logit contributions
agine+9.388
ttp+8.833
 balloons+8.822
mingham+8.335
 FB+7.991
Neg logit contributions
onduct-11.495
=]-11.338
ature-11.125
arten-10.932
antam-10.765
Token upon
Token ID2402
Feature activation-2.02e-01

Pos logit contributions
agine+4.933
ttp+4.525
 balloons+4.475
mingham+4.224
 FB+4.048
Neg logit contributions
onduct-7.246
ature-7.135
=]-6.962
arten-6.955
antam-6.606
Token arrival
Token ID10325
Feature activation-4.59e-01

Pos logit contributions
agine+1.288
ttp+1.206
 balloons+1.163
mingham+1.097
VERTISEMENT+1.065
Neg logit contributions
ature-1.807
onduct-1.776
arten-1.738
=]-1.716
arella-1.693
Token at
Token ID379
Feature activation-4.25e-01

Pos logit contributions
agine+2.936
ttp+2.747
 balloons+2.660
mingham+2.533
 FB+2.390
Neg logit contributions
ature-4.000
onduct-3.983
arten-3.850
=]-3.803
 Shiv-3.721
Token the
Token ID262
Feature activation+2.98e-02

Pos logit contributions
agine+2.959
ttp+2.816
 balloons+2.706
 FB+2.543
mingham+2.529
Neg logit contributions
ature-3.458
onduct-3.428
arten-3.308
=]-3.281
arella-3.237
Token.
Token ID13
Feature activation-6.87e-01

Pos logit contributions
agine+0.846
ttp+0.803
mingham+0.734
 balloons+0.733
VERTISEMENT+0.705
Neg logit contributions
ature-1.183
onduct-1.164
arten-1.130
ores-1.106
=]-1.104
TokenColor
Token ID10258
Feature activation+6.39e-02

Pos logit contributions
agine+3.713
ttp+3.633
mingham+3.259
VERTISEMENT+3.212
 balloons+3.203
Neg logit contributions
onduct-6.373
ature-6.292
arten-6.208
arella-6.115
 Shiv-6.069
Token]
Token ID60
Feature activation+3.75e-01

Pos logit contributions
ature+0.423
onduct+0.409
arten+0.390
=]+0.390
ores+0.383
Neg logit contributions
agine-0.578
ttp-0.545
 balloons-0.520
mingham-0.516
VERTISEMENT-0.508
Token::
Token ID3712
Feature activation-1.92e-01

Pos logit contributions
ature+1.413
onduct+1.324
=]+1.223
arten+1.213
ores+1.183
Neg logit contributions
agine-4.429
ttp-4.219
 balloons-4.110
mingham-4.085
VERTISEMENT-4.019
TokenFrom
Token ID4863
Feature activation-1.02e+00

Pos logit contributions
agine+1.289
ttp+1.223
 balloons+1.123
mingham+1.120
VERTISEMENT+1.104
Neg logit contributions
ature-1.667
onduct-1.650
arten-1.600
 Shiv-1.562
=]-1.559
TokenAr
Token ID3163
Feature activation-1.56e+00

Pos logit contributions
ttp+6.424
agine+6.366
VERTISEMENT+5.753
mingham+5.703
 balloons+5.651
Neg logit contributions
onduct-8.217
ature-7.815
arten-7.790
 Shiv-7.724
arella-7.691
Tokengb
Token ID22296
Feature activation-7.96e-01

Pos logit contributions
agine+4.251
ttp+4.018
mingham+3.834
fy+2.881
 FB+2.626
Neg logit contributions
onduct-17.188
 Shiv-17.016
-16.963
arten-16.648
ature-16.514
Token($
Token ID16763
Feature activation-8.05e-01

Pos logit contributions
agine+5.537
ttp+5.367
mingham+4.979
VERTISEMENT+4.872
 balloons+4.856
Neg logit contributions
ature-6.273
onduct-6.203
arten-6.038
=]-5.949
 Shiv-5.920
TokenFC
Token ID4851
Feature activation+1.33e-01

Pos logit contributions
agine+4.643
ttp+4.426
mingham+4.007
 balloons+3.992
 FB+3.944
Neg logit contributions
onduct-7.223
ature-7.076
 Shiv-7.071
arten-6.943
arella-6.822
Token1
Token ID16
Feature activation+3.36e-01

Pos logit contributions
ature+0.973
onduct+0.950
arten+0.916
=]+0.901
 Shiv+0.893
Neg logit contributions
agine-1.084
ttp-1.028
 balloons-0.966
mingham-0.966
VERTISEMENT-0.947
Token[
Token ID58
Feature activation+3.29e-01

Pos logit contributions
ature+2.465
onduct+2.406
arten+2.304
=]+2.270
ores+2.255
Neg logit contributions
agine-2.752
ttp-2.598
 balloons-2.457
mingham-2.454
VERTISEMENT-2.381
Token.
Token ID13
Feature activation-5.86e-01

Pos logit contributions
ature+0.645
onduct+0.633
arten+0.613
=]+0.604
ores+0.600
Neg logit contributions
agine-0.498
ttp-0.467
 balloons-0.433
mingham-0.432
VERTISEMENT-0.416
Tokened
Token ID276
Feature activation+2.74e-01

Pos logit contributions
agine+4.764
ttp+4.535
mingham+4.249
 balloons+4.124
fy+3.966
Neg logit contributions
 Shiv-4.105
ature-4.079
onduct-4.069
=]-3.940
arella-3.833
Tokenwards
Token ID2017
Feature activation-1.09e+00

Pos logit contributions
ature+1.126
onduct+1.071
arten+0.995
=]+0.961
ores+0.959
Neg logit contributions
agine-3.136
ttp-3.018
 balloons-2.897
mingham-2.887
VERTISEMENT-2.856
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
agine+8.375
ttp+7.954
mingham+7.360
 balloons+7.279
fy+6.906
Neg logit contributions
 Shiv-7.609
=]-7.239
onduct-7.114
ature-7.110
arella-7.045
Tokenaf
Token ID1878
Feature activation-7.20e-01

Pos logit contributions
agine+9.271
ttp+8.772
mingham+8.301
fy+8.146
 balloons+8.038
Neg logit contributions
 Shiv-7.887
onduct-7.646
=]-7.561
-7.514
ature-7.440
Token.
Token ID13
Feature activation-1.54e+00

Pos logit contributions
agine+4.996
ttp+4.586
mingham+4.420
 FB+4.054
 balloons+4.040
Neg logit contributions
ature-5.821
onduct-5.701
arten-5.677
=]-5.620
-5.526
Tokenmil
Token ID25433
Feature activation-5.08e-01

Pos logit contributions
agine+9.623
ttp+9.351
mingham+9.144
fy+8.671
 balloons+8.318
Neg logit contributions
 Shiv-10.877
-10.810
arten-10.806
=]-10.764
ature-10.702
Token/
Token ID14
Feature activation+6.65e-02

Pos logit contributions
agine+3.753
ttp+3.597
mingham+3.279
 balloons+3.221
 FB+3.182
Neg logit contributions
ature-4.012
onduct-3.927
arten-3.836
=]-3.826
arella-3.762
Tokenhistory
Token ID23569
Feature activation+1.29e-01

Pos logit contributions
ature+0.497
onduct+0.486
arten+0.468
=]+0.463
 Shiv+0.461
Neg logit contributions
agine-0.536
ttp-0.511
 balloons-0.477
mingham-0.477
VERTISEMENT-0.465
Token/
Token ID14
Feature activation+2.35e-02

Pos logit contributions
ature+0.975
onduct+0.952
arten+0.916
=]+0.904
ores+0.894
Neg logit contributions
agine-1.031
ttp-0.974
 balloons-0.917
mingham-0.915
VERTISEMENT-0.891
Tokendocs
Token ID31628
Feature activation-1.02e-02

Pos logit contributions
ature+0.175
onduct+0.171
arten+0.165
=]+0.163
 Shiv+0.162
Neg logit contributions
agine-0.189
ttp-0.180
 balloons-0.168
mingham-0.168
VERTISEMENT-0.164
Token your
Token ID534
Feature activation-1.58e-01

Pos logit contributions
agine+2.453
ttp+2.243
 balloons+2.152
mingham+2.039
VERTISEMENT+2.028
Neg logit contributions
onduct-3.675
ature-3.661
=]-3.562
arten-3.480
ores-3.465
Token egg
Token ID5935
Feature activation-7.66e-01

Pos logit contributions
agine+1.132
ttp+1.043
 balloons+1.001
mingham+0.971
VERTISEMENT+0.954
Neg logit contributions
ature-1.310
onduct-1.310
=]-1.253
arten-1.235
ores-1.221
Token repl
Token ID2186
Feature activation-3.06e-01

Pos logit contributions
agine+6.079
ttp+5.694
 balloons+5.680
mingham+5.284
 FB+5.259
Neg logit contributions
onduct-5.349
ature-5.250
=]-5.065
 Shiv-4.902
arten-4.871
Tokenacer
Token ID11736
Feature activation-5.70e-02

Pos logit contributions
agine+1.401
ttp+1.244
mingham+1.102
 balloons+1.038
 FB+0.956
Neg logit contributions
onduct-3.300
ature-3.295
=]-3.240
 Shiv-3.206
arten-3.185
Token and
Token ID290
Feature activation-2.14e-01

Pos logit contributions
agine+0.404
ttp+0.379
 balloons+0.355
mingham+0.351
VERTISEMENT+0.342
Neg logit contributions
ature-0.479
onduct-0.472
arten-0.455
=]-0.452
ores-0.446
Token set
Token ID900
Feature activation-1.54e+00

Pos logit contributions
agine+1.333
ttp+1.246
 balloons+1.150
mingham+1.147
VERTISEMENT+1.102
Neg logit contributions
ature-1.986
onduct-1.954
arten-1.890
=]-1.878
ores-1.857
Token aside
Token ID7263
Feature activation-3.39e-01

Pos logit contributions
agine+7.072
ttp+6.545
VERTISEMENT+5.914
 balloons+5.685
mingham+5.678
Neg logit contributions
-13.889
onduct-13.876
ature-13.466
 Shiv-13.433
arella-13.314
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
agine+2.207
ttp+2.074
 balloons+1.922
mingham+1.908
VERTISEMENT+1.870
Neg logit contributions
ature-3.016
onduct-2.959
arten-2.876
=]-2.842
ores-2.816
Token 2
Token ID362
Feature activation+2.48e-01

Pos logit contributions
ature+1.506
onduct+1.465
arten+1.410
=]+1.386
ores+1.381
Neg logit contributions
agine-1.590
ttp-1.488
 balloons-1.418
mingham-1.410
VERTISEMENT-1.368
Token.
Token ID13
Feature activation-2.41e-01

Pos logit contributions
ature+2.072
onduct+2.015
arten+1.949
=]+1.925
ores+1.913
Neg logit contributions
agine-1.790
ttp-1.664
mingham-1.567
 balloons-1.559
VERTISEMENT-1.529
Token Steam
Token ID9094
Feature activation-4.24e-01

Pos logit contributions
agine+1.850
ttp+1.751
mingham+1.628
 balloons+1.611
VERTISEMENT+1.586
Neg logit contributions
ature-1.854
onduct-1.829
arten-1.759
=]-1.747
ores-1.730
Token and
Token ID290
Feature activation-4.81e-01

Pos logit contributions
agine+1.707
ttp+1.637
 balloons+1.565
mingham+1.497
 FB+1.496
Neg logit contributions
ature-1.695
onduct-1.680
arten-1.619
=]-1.601
ores-1.562
Token I
Token ID314
Feature activation-2.04e-01

Pos logit contributions
agine+3.440
ttp+3.203
 balloons+3.124
mingham+3.013
VERTISEMENT+2.985
Neg logit contributions
ature-3.959
onduct-3.755
arten-3.678
=]-3.625
arella-3.601
Token think
Token ID892
Feature activation+3.15e-02

Pos logit contributions
agine+1.500
ttp+1.390
 balloons+1.317
mingham+1.290
cknowled+1.237
Neg logit contributions
ature-1.662
onduct-1.619
arten-1.583
=]-1.543
 Shiv-1.540
Token around
Token ID1088
Feature activation-9.82e-01

Pos logit contributions
ature+0.267
onduct+0.261
arten+0.252
=]+0.249
ores+0.246
Neg logit contributions
agine-0.224
ttp-0.209
 balloons-0.199
mingham-0.195
VERTISEMENT-0.189
Token 15
Token ID1315
Feature activation-5.55e-01

Pos logit contributions
agine+5.971
 balloons+5.418
ttp+5.305
 FB+5.080
 ounce+4.780
Neg logit contributions
ature-8.232
onduct-8.186
arella-7.991
arten-7.973
=]-7.875
Token-
Token ID12
Feature activation-1.52e+00

Pos logit contributions
agine+4.120
ttp+3.886
 balloons+3.858
mingham+3.683
VERTISEMENT+3.617
Neg logit contributions
ature-4.144
onduct-4.133
arten-3.979
=]-3.922
arella-3.873
Token20
Token ID1238
Feature activation-4.83e-01

Pos logit contributions
agine+6.226
 balloons+5.233
fy+5.135
mingham+5.042
ttp+4.772
Neg logit contributions
onduct-14.404
ature-14.113
=]-13.845
arten-13.740
arella-13.697
Token minutes
Token ID2431
Feature activation-5.35e-01

Pos logit contributions
agine+3.745
ttp+3.545
 balloons+3.497
mingham+3.387
 FB+3.267
Neg logit contributions
ature-3.520
onduct-3.503
arten-3.397
=]-3.337
arella-3.271
Token for
Token ID329
Feature activation-5.92e-01

Pos logit contributions
agine+3.466
ttp+3.267
 balloons+3.166
 FB+2.931
VERTISEMENT+2.925
Neg logit contributions
onduct-4.589
ature-4.555
=]-4.378
arten-4.345
arella-4.240
Token longest
Token ID14069
Feature activation-2.88e-01

Pos logit contributions
agine+4.175
 balloons+3.914
ttp+3.913
 FB+3.683
VERTISEMENT+3.652
Neg logit contributions
ature-4.766
onduct-4.672
arten-4.518
=]-4.453
arella-4.363
Token.
Token ID13
Feature activation-4.92e-01

Pos logit contributions
agine+1.965
ttp+1.867
 balloons+1.788
mingham+1.686
VERTISEMENT+1.684
Neg logit contributions
ature-2.429
onduct-2.416
arten-2.341
=]-2.320
arella-2.273
Token '
Token ID705
Feature activation+6.17e-02

Pos logit contributions
ature+1.622
onduct+1.578
arten+1.516
=]+1.495
ores+1.481
Neg logit contributions
agine-1.903
ttp-1.801
 balloons-1.702
mingham-1.701
VERTISEMENT-1.660
Tokena
Token ID64
Feature activation+6.10e-01

Pos logit contributions
ature+0.462
onduct+0.453
arten+0.436
=]+0.429
ores+0.426
Neg logit contributions
agine-0.496
ttp-0.470
mingham-0.439
 balloons-0.438
VERTISEMENT-0.423
Token,
Token ID837
Feature activation-1.17e-01

Pos logit contributions
ature+3.865
onduct+3.621
arten+3.547
 Shiv+3.456
=]+3.408
Neg logit contributions
agine-5.423
ttp-5.168
 balloons-4.950
mingham-4.930
VERTISEMENT-4.887
Token T
Token ID309
Feature activation+1.98e-01

Pos logit contributions
agine+0.969
ttp+0.920
 balloons+0.867
mingham+0.862
VERTISEMENT+0.846
Neg logit contributions
ature-0.850
onduct-0.832
arten-0.800
ores-0.781
=]-0.779
Token >>
Token ID9609
Feature activation-2.04e-01

Pos logit contributions
ature+1.135
onduct+1.093
arten+1.040
=]+1.020
ores+1.009
Neg logit contributions
agine-1.947
ttp-1.861
 balloons-1.780
mingham-1.773
VERTISEMENT-1.743
Token ;
Token ID2162
Feature activation-1.52e+00

Pos logit contributions
agine+1.231
ttp+1.145
 balloons+1.056
mingham+1.053
VERTISEMENT+1.010
Neg logit contributions
ature-1.937
onduct-1.896
arten-1.840
=]-1.829
arella-1.808
Token }
Token ID1782
Feature activation-1.20e+00

Pos logit contributions
agine+7.295
ttp+6.820
 execut+6.592
mingham+6.453
 balloons+6.385
Neg logit contributions
onduct-13.307
ature-12.892
=]-12.684
-12.615
arella-12.418
Token
Token ID198
Feature activation-4.41e-01

Pos logit contributions
agine+6.602
ttp+6.251
mingham+5.802
 balloons+5.680
 execut+5.666
Neg logit contributions
onduct-10.428
ature-10.228
-9.938
=]-9.919
arten-9.883
Token
Token ID198
Feature activation-6.65e-01

Pos logit contributions
agine+2.907
ttp+2.780
 balloons+2.582
mingham+2.535
 FB+2.480
Neg logit contributions
ature-3.768
onduct-3.740
arten-3.631
=]-3.546
arella-3.536
TokenIn
Token ID818
Feature activation-1.25e-01

Pos logit contributions
agine+4.645
ttp+4.559
mingham+4.107
 balloons+4.015
cknowled+3.968
Neg logit contributions
onduct-5.207
ature-5.178
 Shiv-4.997
arten-4.987
arella-4.910
Token order
Token ID1502
Feature activation-4.20e-01

Pos logit contributions
agine+0.899
ttp+0.835
 balloons+0.783
mingham+0.777
VERTISEMENT+0.746
Neg logit contributions
ature-1.043
onduct-1.024
arten-0.991
=]-0.987
 Shiv-0.959
Token steal
Token ID8711
Feature activation-4.97e-02

Pos logit contributions
ature+1.156
onduct+1.116
arten+1.050
=]+1.025
ores+1.014
Neg logit contributions
agine-2.505
ttp-2.400
 balloons-2.297
mingham-2.293
VERTISEMENT-2.256
Token dragon
Token ID10441
Feature activation-3.30e-01

Pos logit contributions
agine+0.318
ttp+0.287
 balloons+0.274
mingham+0.268
VERTISEMENT+0.257
Neg logit contributions
ature-0.455
onduct-0.452
arten-0.435
=]-0.431
ores-0.428
Token,
Token ID11
Feature activation-7.12e-01

Pos logit contributions
agine+2.101
ttp+1.980
 balloons+1.839
mingham+1.808
 FB+1.760
Neg logit contributions
ature-2.958
onduct-2.945
arten-2.850
arella-2.798
ores-2.785
Token cause
Token ID2728
Feature activation-4.61e-01

Pos logit contributions
agine+4.091
ttp+3.736
 balloons+3.590
mingham+3.397
 FB+3.375
Neg logit contributions
ature-6.721
onduct-6.597
arten-6.383
-6.268
arella-6.258
Token he
Token ID339
Feature activation-3.39e-01

Pos logit contributions
agine+2.567
ttp+2.448
 balloons+2.222
mingham+2.173
 FB+2.090
Neg logit contributions
ature-4.498
onduct-4.417
arten-4.275
ores-4.262
=]-4.242
Token's
Token ID338
Feature activation-1.51e+00

Pos logit contributions
agine+2.392
ttp+2.275
 balloons+2.099
mingham+2.086
 FB+2.009
Neg logit contributions
ature-2.811
onduct-2.800
arten-2.713
=]-2.647
arella-2.634
Token notorious
Token ID18192
Feature activation+5.17e-01

Pos logit contributions
ttp+3.461
agine+3.460
VERTISEMENT+3.067
mingham+2.998
 execut+2.876
Neg logit contributions
arten-16.985
onduct-16.655
acci-16.237
=]-15.803
ature-15.715
Token about
Token ID546
Feature activation-1.73e-02

Pos logit contributions
ature+3.277
onduct+3.119
ores+2.975
=]+2.967
 Shiv+2.964
Neg logit contributions
agine-4.723
ttp-4.466
VERTISEMENT-4.278
mingham-4.235
 balloons-4.193
Token stealing
Token ID16568
Feature activation+1.63e-01

Pos logit contributions
agine+0.177
ttp+0.169
 balloons+0.162
mingham+0.160
VERTISEMENT+0.157
Neg logit contributions
ature-0.093
onduct-0.089
arten-0.085
=]-0.082
ores-0.081
Token players
Token ID1938
Feature activation+2.78e-01

Pos logit contributions
ature+1.364
onduct+1.335
arten+1.292
=]+1.273
ores+1.262
Neg logit contributions
agine-1.178
ttp-1.104
 balloons-1.038
mingham-1.029
VERTISEMENT-1.001
Token from
Token ID422
Feature activation-1.47e-01

Pos logit contributions
ature+2.203
onduct+2.146
arten+2.070
=]+2.045
ores+2.034
Neg logit contributions
agine-2.128
ttp-2.005
mingham-1.879
 balloons-1.868
VERTISEMENT-1.847
Token <
Token ID1279
Feature activation+1.17e-01

Pos logit contributions
agine+3.157
ttp+3.046
mingham+2.609
 balloons+2.602
 FB+2.519
Neg logit contributions
onduct-7.262
ature-7.133
=]-7.056
arten-6.929
 Shiv-6.885
Token T
Token ID309
Feature activation-5.58e-02

Pos logit contributions
ature+0.825
onduct+0.803
arten+0.771
=]+0.759
ores+0.752
Neg logit contributions
agine-0.995
ttp-0.942
 balloons-0.892
mingham-0.890
VERTISEMENT-0.869
Token >
Token ID1875
Feature activation-9.41e-01

Pos logit contributions
agine+0.504
ttp+0.478
 balloons+0.453
mingham+0.453
VERTISEMENT+0.442
Neg logit contributions
ature-0.365
onduct-0.355
arten-0.340
=]-0.334
ores-0.331
Token {
Token ID1391
Feature activation-1.06e+00

Pos logit contributions
agine+4.855
ttp+4.629
 FB+4.263
 balloons+4.180
mingham+4.087
Neg logit contributions
ature-8.812
onduct-8.798
=]-8.570
arella-8.459
arten-8.338
Token pub
Token ID2240
Feature activation-7.99e-01

Pos logit contributions
agine+6.303
ttp+5.795
 execut+5.347
mingham+5.292
 balloons+5.252
Neg logit contributions
onduct-9.124
ature-8.818
-8.618
=]-8.600
arten-8.525
Token fn
Token ID24714
Feature activation-1.51e+00

Pos logit contributions
agine+4.741
ttp+4.585
mingham+4.208
 execut+4.076
 balloons+4.064
Neg logit contributions
onduct-7.089
ature-6.822
arten-6.736
=]-6.579
-6.519
Token load
Token ID3440
Feature activation-1.31e-01

Pos logit contributions
agine+8.054
 execut+7.639
ttp+7.631
 balloons+7.619
 FB+7.551
Neg logit contributions
onduct-12.320
ature-11.858
-11.798
arten-11.566
=]-11.518
Token <
Token ID1279
Feature activation+3.07e-01

Pos logit contributions
agine+0.813
ttp+0.758
mingham+0.699
 balloons+0.697
VERTISEMENT+0.672
Neg logit contributions
ature-1.216
onduct-1.201
arten-1.161
=]-1.150
 Shiv-1.139
Token '
Token ID705
Feature activation-4.37e-02

Pos logit contributions
ature+2.307
onduct+2.241
arten+2.158
=]+2.144
ores+2.113
Neg logit contributions
agine-2.462
ttp-2.325
mingham-2.195
 balloons-2.186
VERTISEMENT-2.138
Tokena
Token ID64
Feature activation+6.71e-01

Pos logit contributions
agine+0.346
ttp+0.329
mingham+0.307
 balloons+0.307
VERTISEMENT+0.296
Neg logit contributions
ature-0.331
onduct-0.325
arten-0.313
=]-0.307
ores-0.306
Token >
Token ID1875
Feature activation-4.57e-01

Pos logit contributions
ature+4.525
onduct+4.257
arten+4.170
=]+4.123
 Shiv+4.110
Neg logit contributions
agine-5.739
ttp-5.449
mingham-5.228
VERTISEMENT-5.184
 balloons-5.136
Token discern
Token ID22024
Feature activation-8.24e-01

Pos logit contributions
agine+1.697
ttp+1.582
mingham+1.475
 balloons+1.449
VERTISEMENT+1.419
Neg logit contributions
ature-2.318
onduct-2.232
arten-2.180
=]-2.163
arella-2.130
Token the
Token ID262
Feature activation-3.84e-01

Pos logit contributions
agine+4.385
ttp+4.200
 balloons+3.916
mingham+3.798
 FB+3.753
Neg logit contributions
onduct-7.648
ature-7.614
arten-7.526
=]-7.388
ores-7.297
Token size
Token ID2546
Feature activation+7.78e-02

Pos logit contributions
agine+3.042
ttp+2.860
 balloons+2.800
mingham+2.696
 FB+2.647
Neg logit contributions
onduct-2.815
ature-2.791
arten-2.715
=]-2.642
ores-2.616
Token of
Token ID286
Feature activation-7.13e-01

Pos logit contributions
ature+0.628
onduct+0.612
arten+0.590
=]+0.584
ores+0.579
Neg logit contributions
agine-0.584
ttp-0.548
mingham-0.514
 balloons-0.513
VERTISEMENT-0.501
Token individual
Token ID1981
Feature activation-7.48e-01

Pos logit contributions
agine+4.667
ttp+4.397
 balloons+4.301
 FB+3.985
mingham+3.946
Neg logit contributions
ature-5.970
arten-5.904
=]-5.881
onduct-5.837
ores-5.736
Token pixels
Token ID17848
Feature activation-1.50e+00

Pos logit contributions
agine+3.851
 balloons+3.735
ttp+3.656
 FB+3.266
mingham+3.189
Neg logit contributions
ature-7.220
onduct-7.129
arten-7.016
arella-6.847
=]-6.827
Token due
Token ID2233
Feature activation-6.09e-01

Pos logit contributions
agine+5.470
ttp+5.180
 balloons+4.882
mingham+4.709
 FB+4.590
Neg logit contributions
ature-15.046
arten-14.869
=]-14.756
onduct-14.515
ores-14.405
Token to
Token ID284
Feature activation-5.30e-01

Pos logit contributions
agine+3.969
ttp+3.818
 balloons+3.607
mingham+3.479
 FB+3.460
Neg logit contributions
ature-5.150
onduct-5.084
arten-5.006
ores-4.868
=]-4.842
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
agine+3.118
ttp+3.026
 balloons+2.822
mingham+2.753
 FB+2.667
Neg logit contributions
ature-4.864
onduct-4.833
arten-4.747
ores-4.592
=]-4.579
Token amount
Token ID2033
Feature activation+1.73e-01

Pos logit contributions
agine+1.592
ttp+1.495
 balloons+1.389
mingham+1.358
VERTISEMENT+1.276
Neg logit contributions
ature-2.817
onduct-2.777
arten-2.723
=]-2.674
ores-2.640
Token they
Token ID484
Feature activation+1.41e-01

Pos logit contributions
ature+1.461
onduct+1.430
arten+1.379
=]+1.364
ores+1.356
Neg logit contributions
agine-1.233
ttp-1.150
mingham-1.080
 balloons-1.071
VERTISEMENT-1.049
Token down
Token ID866
Feature activation-2.89e-01

Pos logit contributions
agine+1.315
ttp+1.216
 balloons+1.189
mingham+1.117
VERTISEMENT+1.080
Neg logit contributions
ature-1.529
onduct-1.518
=]-1.485
arten-1.473
 Shiv-1.429
Token every
Token ID790
Feature activation-1.35e-01

Pos logit contributions
agine+2.047
ttp+1.897
 balloons+1.866
mingham+1.739
VERTISEMENT+1.685
Neg logit contributions
ature-2.415
onduct-2.374
=]-2.335
arten-2.318
 Shiv-2.237
Token day
Token ID1110
Feature activation-2.24e-01

Pos logit contributions
agine+1.053
ttp+0.971
 balloons+0.939
mingham+0.914
VERTISEMENT+0.895
Neg logit contributions
onduct-1.047
ature-1.039
arten-0.998
=]-0.982
arella-0.968
Token and
Token ID290
Feature activation-3.17e-01

Pos logit contributions
agine+1.491
ttp+1.368
 balloons+1.318
mingham+1.235
VERTISEMENT+1.217
Neg logit contributions
ature-1.975
onduct-1.956
=]-1.925
arten-1.902
arella-1.837
Token then
Token ID788
Feature activation-5.47e-02

Pos logit contributions
agine+2.183
 balloons+2.053
ttp+2.020
mingham+1.869
VERTISEMENT+1.832
Neg logit contributions
onduct-2.652
ature-2.635
=]-2.580
arten-2.539
arella-2.511
Token mineral
Token ID18352
Feature activation-1.50e+00

Pos logit contributions
agine+0.398
ttp+0.371
 balloons+0.363
mingham+0.346
VERTISEMENT+0.338
Neg logit contributions
ature-0.447
onduct-0.444
=]-0.428
arten-0.423
arella-0.417
Tokenizes
Token ID4340
Feature activation-3.78e-01

Pos logit contributions
agine+6.228
 balloons+5.526
ttp+4.841
fy+4.307
cknowled+4.284
Neg logit contributions
onduct-14.511
arella-14.134
=]-14.117
 Shiv-14.087
-14.030
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
agine+2.575
ttp+2.383
 balloons+2.338
mingham+2.156
VERTISEMENT+2.130
Neg logit contributions
onduct-3.191
ature-3.188
=]-3.132
arten-3.096
 Shiv-2.990
Token forming
Token ID14583
Feature activation-6.04e-01

Pos logit contributions
agine+1.030
ttp+0.959
 balloons+0.926
mingham+0.885
VERTISEMENT+0.868
Neg logit contributions
ature-1.206
onduct-1.182
arten-1.149
=]-1.138
arella-1.111
Token a
Token ID257
Feature activation-8.44e-02

Pos logit contributions
agine+4.324
 balloons+3.976
ttp+3.818
mingham+3.609
VERTISEMENT+3.580
Neg logit contributions
onduct-4.851
ature-4.801
arten-4.714
=]-4.653
arella-4.591
Token hard
Token ID1327
Feature activation+8.51e-02

Pos logit contributions
agine+0.626
ttp+0.573
 balloons+0.549
mingham+0.540
VERTISEMENT+0.533
Neg logit contributions
ature-0.686
onduct-0.682
arten-0.662
=]-0.651
arella-0.640
Token among
Token ID1871
Feature activation+4.15e-02

Pos logit contributions
ature+0.599
onduct+0.589
arten+0.569
=]+0.559
ores+0.551
Neg logit contributions
agine-0.592
ttp-0.559
 balloons-0.527
mingham-0.526
VERTISEMENT-0.509
Token farmland
Token ID45723
Feature activation-3.38e-01

Pos logit contributions
ature+0.345
onduct+0.339
arten+0.328
=]+0.323
ores+0.319
Neg logit contributions
agine-0.299
ttp-0.280
 balloons-0.265
mingham-0.261
VERTISEMENT-0.255
Token contaminated
Token ID23543
Feature activation+3.99e-01

Pos logit contributions
agine+2.290
ttp+2.110
 balloons+2.028
mingham+1.952
VERTISEMENT+1.896
Neg logit contributions
ature-2.916
onduct-2.887
=]-2.777
arten-2.768
arella-2.697
Token by
Token ID416
Feature activation-2.44e-01

Pos logit contributions
ature+2.958
onduct+2.849
arten+2.764
ores+2.757
 Shiv+2.713
Neg logit contributions
agine-3.228
ttp-3.057
mingham-2.871
 balloons-2.819
VERTISEMENT-2.817
Token heavy
Token ID4334
Feature activation-2.88e-01

Pos logit contributions
agine+1.602
ttp+1.458
 balloons+1.438
mingham+1.350
VERTISEMENT+1.339
Neg logit contributions
ature-2.159
onduct-2.121
arten-2.092
=]-2.044
arella-2.006
Token metals
Token ID21782
Feature activation-1.49e+00

Pos logit contributions
agine+1.622
ttp+1.483
 balloons+1.474
mingham+1.379
VERTISEMENT+1.329
Neg logit contributions
ature-2.777
onduct-2.742
arten-2.690
=]-2.667
arella-2.603
Token used
Token ID973
Feature activation-4.54e-01

Pos logit contributions
agine+8.386
 balloons+7.862
ttp+7.031
 FB+7.026
VERTISEMENT+6.454
Neg logit contributions
=]-12.131
ature-12.081
arten-11.763
onduct-11.717
antam-11.479
Token to
Token ID284
Feature activation-3.15e-01

Pos logit contributions
agine+3.125
ttp+2.838
 balloons+2.810
mingham+2.680
VERTISEMENT+2.557
Neg logit contributions
ature-3.810
onduct-3.775
=]-3.696
arten-3.672
 Shiv-3.538
Token make
Token ID787
Feature activation-5.86e-01

Pos logit contributions
agine+2.198
ttp+1.964
 balloons+1.937
mingham+1.884
 FB+1.803
Neg logit contributions
ature-2.624
onduct-2.590
=]-2.547
arten-2.545
arella-2.474
Token batteries
Token ID13591
Feature activation-2.15e-01

Pos logit contributions
agine+3.837
 balloons+3.627
ttp+3.386
 FB+3.281
mingham+3.159
Neg logit contributions
ature-5.018
arten-4.903
onduct-4.900
=]-4.823
arella-4.674
Token,
Token ID11
Feature activation-3.96e-01

Pos logit contributions
agine+1.459
ttp+1.337
 balloons+1.288
mingham+1.244
VERTISEMENT+1.213
Neg logit contributions
ature-1.860
onduct-1.828
=]-1.789
arten-1.785
 Shiv-1.731
Token avoid
Token ID3368
Feature activation-6.57e-01

Pos logit contributions
agine+3.263
ttp+2.891
 balloons+2.678
 FB+2.659
mingham+2.432
Neg logit contributions
ature-7.346
onduct-7.220
arten-7.201
acci-6.885
arella-6.858
Token following
Token ID1708
Feature activation-5.32e-01

Pos logit contributions
agine+3.889
ttp+3.718
 balloons+3.396
mingham+3.367
 FB+3.366
Neg logit contributions
ature-6.013
arten-5.941
onduct-5.780
-5.589
arella-5.546
Token the
Token ID262
Feature activation-5.29e-01

Pos logit contributions
agine+3.054
ttp+3.002
 balloons+2.792
mingham+2.697
 FB+2.643
Neg logit contributions
ature-4.893
onduct-4.877
arten-4.750
arella-4.632
ores-4.583
Token commands
Token ID9729
Feature activation-7.22e-01

Pos logit contributions
agine+3.014
 balloons+2.863
ttp+2.827
 execut+2.574
VERTISEMENT+2.561
Neg logit contributions
ature-5.053
onduct-4.886
arten-4.823
-4.604
antam-4.589
Token in
Token ID287
Feature activation-1.45e+00

Pos logit contributions
agine+4.129
ttp+3.902
 balloons+3.726
 FB+3.626
mingham+3.602
Neg logit contributions
ature-6.528
onduct-6.499
arten-6.394
arella-6.256
antam-6.109
Token his
Token ID465
Feature activation-1.49e+00

Pos logit contributions
agine+5.082
ttp+4.705
mingham+4.447
 balloons+4.418
 FB+4.402
Neg logit contributions
onduct-14.855
=]-14.760
ature-14.680
arten-14.627
-14.567
Token head
Token ID1182
Feature activation-1.14e+00

Pos logit contributions
agine+6.187
 balloons+5.754
 FB+5.648
ttp+5.603
 font+5.372
Neg logit contributions
onduct-14.035
arten-13.776
arella-13.713
-13.651
ature-13.611
Token).
Token ID737
Feature activation+1.23e-01

Pos logit contributions
agine+4.052
ttp+3.982
mingham+3.468
 balloons+3.273
 FB+3.132
Neg logit contributions
ature-12.009
arten-11.887
onduct-11.785
arella-11.707
antam-11.435
Token Kid
Token ID16828
Feature activation-1.41e-01

Pos logit contributions
ature+0.918
onduct+0.898
arten+0.867
=]+0.849
ores+0.841
Neg logit contributions
agine-0.999
ttp-0.945
 balloons-0.895
mingham-0.890
VERTISEMENT-0.873
Tokenn
Token ID77
Feature activation+1.59e-01

Pos logit contributions
agine+1.032
ttp+0.964
 balloons+0.914
mingham+0.896
VERTISEMENT+0.882
Neg logit contributions
ature-1.149
onduct-1.127
arten-1.109
=]-1.094
arella-1.067
Tokenapping
Token ID5912
Feature activation-2.80e-01

Pos logit contributions
ature+1.127
onduct+1.087
arten+1.045
ores+1.024
=]+1.017
Neg logit contributions
agine-1.344
ttp-1.277
 balloons-1.214
mingham-1.209
VERTISEMENT-1.182
Token to
Token ID284
Feature activation-7.00e-01

Pos logit contributions
agine+3.018
ttp+2.865
 balloons+2.712
mingham+2.619
 FB+2.587
Neg logit contributions
ature-3.551
onduct-3.496
arten-3.448
=]-3.319
ores-3.297
Token avoid
Token ID3368
Feature activation-6.57e-01

Pos logit contributions
agine+3.263
ttp+2.891
 balloons+2.678
 FB+2.659
mingham+2.432
Neg logit contributions
ature-7.346
onduct-7.220
arten-7.201
acci-6.885
arella-6.858
Token following
Token ID1708
Feature activation-5.32e-01

Pos logit contributions
agine+3.889
ttp+3.718
 balloons+3.396
mingham+3.367
 FB+3.366
Neg logit contributions
ature-6.013
arten-5.941
onduct-5.780
-5.589
arella-5.546
Token the
Token ID262
Feature activation-5.29e-01

Pos logit contributions
agine+3.054
ttp+3.002
 balloons+2.792
mingham+2.697
 FB+2.643
Neg logit contributions
ature-4.893
onduct-4.877
arten-4.750
arella-4.632
ores-4.583
Token commands
Token ID9729
Feature activation-7.22e-01

Pos logit contributions
agine+3.014
 balloons+2.863
ttp+2.827
 execut+2.574
VERTISEMENT+2.561
Neg logit contributions
ature-5.053
onduct-4.886
arten-4.823
-4.604
antam-4.589
Token in
Token ID287
Feature activation-1.45e+00

Pos logit contributions
agine+4.129
ttp+3.902
 balloons+3.726
 FB+3.626
mingham+3.602
Neg logit contributions
ature-6.528
onduct-6.499
arten-6.394
arella-6.256
antam-6.109
Token his
Token ID465
Feature activation-1.49e+00

Pos logit contributions
agine+5.082
ttp+4.705
mingham+4.447
 balloons+4.418
 FB+4.402
Neg logit contributions
onduct-14.855
=]-14.760
ature-14.680
arten-14.627
-14.567
Token head
Token ID1182
Feature activation-1.14e+00

Pos logit contributions
agine+6.187
 balloons+5.754
 FB+5.648
ttp+5.603
 font+5.372
Neg logit contributions
onduct-14.035
arten-13.776
arella-13.713
-13.651
ature-13.611
Token).
Token ID737
Feature activation+1.23e-01

Pos logit contributions
agine+4.052
ttp+3.982
mingham+3.468
 balloons+3.273
 FB+3.132
Neg logit contributions
ature-12.009
arten-11.887
onduct-11.785
arella-11.707
antam-11.435
Token Kid
Token ID16828
Feature activation-1.41e-01

Pos logit contributions
ature+0.918
onduct+0.898
arten+0.867
=]+0.849
ores+0.841
Neg logit contributions
agine-0.999
ttp-0.945
 balloons-0.895
mingham-0.890
VERTISEMENT-0.873
Tokenn
Token ID77
Feature activation+1.59e-01

Pos logit contributions
agine+1.032
ttp+0.964
 balloons+0.914
mingham+0.896
VERTISEMENT+0.882
Neg logit contributions
ature-1.149
onduct-1.127
arten-1.109
=]-1.094
arella-1.067
Token Europe
Token ID2031
Feature activation-4.02e-01

Pos logit contributions
agine+2.566
ttp+2.383
 balloons+2.335
mingham+2.250
 FB+2.226
Neg logit contributions
ature-2.791
onduct-2.762
arten-2.651
=]-2.633
arella-2.561
Token had
Token ID550
Feature activation-5.39e-01

Pos logit contributions
agine+2.785
ttp+2.531
 balloons+2.477
mingham+2.374
VERTISEMENT+2.343
Neg logit contributions
ature-3.338
onduct-3.299
=]-3.252
arten-3.216
 Shiv-3.138
Token for
Token ID329
Feature activation-7.31e-01

Pos logit contributions
agine+3.824
 balloons+3.518
ttp+3.449
mingham+3.342
VERTISEMENT+3.271
Neg logit contributions
onduct-4.310
ature-4.285
=]-4.167
arten-4.144
arella-4.018
Token the
Token ID262
Feature activation-5.43e-01

Pos logit contributions
agine+5.131
ttp+4.627
 balloons+4.523
mingham+4.389
VERTISEMENT+4.331
Neg logit contributions
ature-5.689
onduct-5.675
arten-5.528
=]-5.440
 Shiv-5.337
Token first
Token ID717
Feature activation-4.54e-01

Pos logit contributions
agine+3.219
 balloons+2.828
ttp+2.822
mingham+2.692
 FB+2.542
Neg logit contributions
ature-5.100
onduct-4.986
arten-4.860
=]-4.792
arella-4.708
Token time
Token ID640
Feature activation-1.44e+00

Pos logit contributions
agine+3.931
ttp+3.689
 balloons+3.577
mingham+3.481
VERTISEMENT+3.411
Neg logit contributions
onduct-3.029
ature-2.981
arten-2.899
=]-2.790
arella-2.760
Token come
Token ID1282
Feature activation-6.75e-01

Pos logit contributions
agine+8.760
 balloons+8.325
mingham+7.537
ttp+7.466
 FB+7.390
Neg logit contributions
onduct-11.091
arten-10.908
ature-10.851
=]-10.811
arella-10.361
Token to
Token ID284
Feature activation-1.43e-02

Pos logit contributions
agine+4.543
ttp+4.022
 balloons+3.992
mingham+3.902
cknowled+3.734
Neg logit contributions
onduct-5.590
arten-5.539
ature-5.511
=]-5.402
 Shiv-5.211
Token systematically
Token ID25735
Feature activation-1.65e-01

Pos logit contributions
agine+0.109
ttp+0.101
 balloons+0.096
mingham+0.095
VERTISEMENT+0.092
Neg logit contributions
ature-0.114
onduct-0.112
arten-0.108
=]-0.106
ores-0.105
Token compare
Token ID8996
Feature activation-3.36e-01

Pos logit contributions
agine+1.295
ttp+1.182
 balloons+1.154
mingham+1.128
cknowled+1.095
Neg logit contributions
ature-1.268
onduct-1.244
arten-1.206
=]-1.194
arella-1.164
Token the
Token ID262
Feature activation+9.21e-02

Pos logit contributions
agine+2.576
ttp+2.388
 balloons+2.322
mingham+2.224
 FB+2.221
Neg logit contributions
ature-2.599
onduct-2.568
arten-2.479
=]-2.444
ores-2.373
Token here
Token ID994
Feature activation+4.62e-01

Pos logit contributions
ature+3.800
onduct+3.690
arten+3.554
ores+3.518
=]+3.491
Neg logit contributions
agine-3.814
ttp-3.610
mingham-3.368
 balloons-3.354
VERTISEMENT-3.322
Token but
Token ID475
Feature activation+4.41e-01

Pos logit contributions
ature+3.776
onduct+3.682
arten+3.542
ores+3.493
=]+3.480
Neg logit contributions
agine-3.395
ttp-3.196
mingham-2.974
 balloons-2.965
VERTISEMENT-2.926
Token will
Token ID481
Feature activation+4.49e-02

Pos logit contributions
ature+3.444
onduct+3.361
arten+3.227
=]+3.197
 Shiv+3.172
Neg logit contributions
agine-3.396
ttp-3.208
mingham-3.011
 balloons-2.991
VERTISEMENT-2.950
Token talk
Token ID1561
Feature activation+5.74e-01

Pos logit contributions
ature+0.359
onduct+0.351
arten+0.341
=]+0.334
ores+0.332
Neg logit contributions
agine-0.339
ttp-0.317
 balloons-0.301
mingham-0.298
VERTISEMENT-0.286
Token a
Token ID257
Feature activation+5.40e-01

Pos logit contributions
ature+3.924
onduct+3.806
arten+3.624
=]+3.600
 Shiv+3.583
Neg logit contributions
agine-4.920
ttp-4.689
mingham-4.407
VERTISEMENT-4.365
 balloons-4.364
Token bit
Token ID1643
Feature activation+7.59e-01

Pos logit contributions
ature+3.646
onduct+3.487
arten+3.334
=]+3.307
ores+3.287
Neg logit contributions
agine-4.704
ttp-4.464
 balloons-4.224
mingham-4.193
VERTISEMENT-4.142
Token about
Token ID546
Feature activation+1.99e-01

Pos logit contributions
ature+4.969
onduct+4.758
arten+4.589
ores+4.517
 Shiv+4.495
Neg logit contributions
agine-6.675
ttp-6.342
VERTISEMENT-5.974
mingham-5.936
 balloons-5.895
Token its
Token ID663
Feature activation+3.80e-01

Pos logit contributions
ature+1.591
onduct+1.554
arten+1.501
=]+1.478
ores+1.466
Neg logit contributions
agine-1.513
ttp-1.422
 balloons-1.338
mingham-1.333
VERTISEMENT-1.297
Token operation
Token ID4905
Feature activation+6.62e-01

Pos logit contributions
ature+3.013
onduct+2.948
arten+2.820
ores+2.794
=]+2.793
Neg logit contributions
agine-2.880
ttp-2.715
mingham-2.543
 balloons-2.532
VERTISEMENT-2.471
Token on
Token ID319
Feature activation-5.27e-02

Pos logit contributions
ature+5.165
onduct+5.015
arten+4.800
ores+4.744
 Shiv+4.737
Neg logit contributions
agine-5.091
ttp-4.805
mingham-4.462
 balloons-4.436
VERTISEMENT-4.371
Token the
Token ID262
Feature activation-3.52e-01

Pos logit contributions
agine+0.388
ttp+0.362
 balloons+0.346
mingham+0.339
VERTISEMENT+0.328
Neg logit contributions
ature-0.428
onduct-0.421
arten-0.408
=]-0.401
 Shiv-0.395
Token are
Token ID389
Feature activation+3.26e-01

Pos logit contributions
ature+0.644
onduct+0.631
arten+0.608
=]+0.600
 Shiv+0.592
Neg logit contributions
agine-0.620
ttp-0.579
 balloons-0.552
mingham-0.545
VERTISEMENT-0.526
Token H
Token ID367
Feature activation-1.68e-02

Pos logit contributions
ature+2.548
onduct+2.487
arten+2.397
=]+2.364
ores+2.346
Neg logit contributions
agine-2.528
ttp-2.384
mingham-2.238
 balloons-2.237
VERTISEMENT-2.179
TokenVM
Token ID15996
Feature activation+2.54e-01

Pos logit contributions
agine+0.150
ttp+0.142
 balloons+0.135
mingham+0.135
VERTISEMENT+0.132
Neg logit contributions
ature-0.112
onduct-0.108
arten-0.104
=]-0.102
ores-0.101
Token with
Token ID351
Feature activation+1.51e-01

Pos logit contributions
ature+2.020
onduct+1.974
arten+1.906
=]+1.878
ores+1.863
Neg logit contributions
agine-1.930
ttp-1.815
 balloons-1.708
mingham-1.701
VERTISEMENT-1.656
Token PV
Token ID31392
Feature activation+4.51e-01

Pos logit contributions
ature+1.159
onduct+1.132
arten+1.092
=]+1.076
ores+1.063
Neg logit contributions
agine-1.195
ttp-1.127
 balloons-1.069
mingham-1.054
VERTISEMENT-1.032
TokenH
Token ID39
Feature activation+8.01e-01

Pos logit contributions
ature+3.604
onduct+3.519
arten+3.371
ores+3.331
=]+3.328
Neg logit contributions
agine-3.409
ttp-3.200
mingham-3.007
 balloons-2.989
VERTISEMENT-2.916
TokenVM
Token ID15996
Feature activation+2.18e-01

Pos logit contributions
ature+4.711
onduct+4.522
arten+4.274
ores+4.242
=]+4.236
Neg logit contributions
agine-7.603
ttp-6.970
mingham-6.901
 balloons-6.845
VERTISEMENT-6.663
Token drivers
Token ID6643
Feature activation+3.41e-01

Pos logit contributions
ature+1.816
onduct+1.776
arten+1.720
=]+1.695
ores+1.680
Neg logit contributions
agine-1.570
ttp-1.472
 balloons-1.382
mingham-1.375
VERTISEMENT-1.337
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
ature+2.860
onduct+2.792
arten+2.695
=]+2.660
ores+2.650
Neg logit contributions
agine-2.441
ttp-2.288
mingham-2.137
 balloons-2.134
VERTISEMENT-2.075
Token
Token ID198
Feature activation-3.27e-01

Pos logit contributions
ature+0.142
onduct+0.140
arten+0.135
=]+0.132
ores+0.131
Neg logit contributions
agine-0.135
ttp-0.127
 balloons-0.121
mingham-0.118
 FB-0.116
Token
Token ID198
Feature activation-4.49e-01

Pos logit contributions
agine+2.243
ttp+2.143
 balloons+1.981
mingham+1.960
 FB+1.906
Neg logit contributions
ature-2.759
onduct-2.738
arten-2.653
=]-2.580
arella-2.576
Token data
Token ID1366
Feature activation-5.19e-01

Pos logit contributions
agine+0.311
ttp+0.292
 balloons+0.273
mingham+0.270
VERTISEMENT+0.265
Neg logit contributions
ature-0.347
onduct-0.347
arten-0.333
=]-0.326
arella-0.323
Token structure
Token ID4645
Feature activation+3.95e-02

Pos logit contributions
agine+3.641
ttp+3.352
 balloons+3.188
mingham+3.166
VERTISEMENT+3.067
Neg logit contributions
onduct-4.296
ature-4.239
arten-4.075
=]-4.071
 Shiv-4.001
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
ature+0.345
onduct+0.342
arten+0.330
=]+0.328
arella+0.322
Neg logit contributions
agine-0.266
ttp-0.248
 balloons-0.231
mingham-0.229
VERTISEMENT-0.223
Token
Token ID198
Feature activation-7.44e-02

Pos logit contributions
agine+1.746
ttp+1.631
 balloons+1.562
mingham+1.501
 FB+1.499
Neg logit contributions
onduct-1.826
ature-1.826
arten-1.730
arella-1.699
=]-1.698
Token
Token ID198
Feature activation-2.56e-01

Pos logit contributions
agine+0.556
ttp+0.527
 balloons+0.493
mingham+0.490
VERTISEMENT+0.472
Neg logit contributions
ature-0.596
onduct-0.585
arten-0.565
=]-0.555
ores-0.550
TokenSh
Token ID2484
Feature activation+8.20e-01

Pos logit contributions
agine+1.836
ttp+1.729
mingham+1.611
 balloons+1.603
VERTISEMENT+1.565
Neg logit contributions
ature-2.123
onduct-2.085
arten-2.016
=]-1.989
 Shiv-1.969
Tokenared
Token ID1144
Feature activation+2.95e-01

Pos logit contributions
ature+4.690
onduct+4.358
ores+4.355
arten+4.234
arella+4.036
Neg logit contributions
agine-7.872
 balloons-7.403
ttp-7.393
mingham-7.292
VERTISEMENT-7.245
Token<
Token ID27
Feature activation+1.94e-01

Pos logit contributions
ature+2.858
onduct+2.804
arten+2.723
=]+2.692
ores+2.675
Neg logit contributions
agine-1.734
ttp-1.602
 balloons-1.474
mingham-1.469
VERTISEMENT-1.417
Token'
Token ID6
Feature activation+4.35e-02

Pos logit contributions
ature+1.628
onduct+1.600
arten+1.546
=]+1.516
ores+1.510
Neg logit contributions
agine-1.390
ttp-1.305
 balloons-1.220
mingham-1.213
VERTISEMENT-1.184
Tokena
Token ID64
Feature activation+6.98e-01

Pos logit contributions
ature+0.328
onduct+0.323
arten+0.312
arella+0.303
ores+0.303
Neg logit contributions
agine-0.344
ttp-0.327
 balloons-0.305
mingham-0.305
VERTISEMENT-0.298
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
ature+4.971
onduct+4.734
=]+4.614
arten+4.602
 Shiv+4.517
Neg logit contributions
agine-5.799
ttp-5.505
mingham-5.251
 balloons-5.193
VERTISEMENT-5.063
Token.
Token ID13
Feature activation+4.74e-01

Pos logit contributions
ature+0.398
onduct+0.389
arten+0.375
=]+0.370
ores+0.368
Neg logit contributions
agine-0.329
ttp-0.308
 balloons-0.288
mingham-0.286
VERTISEMENT-0.277
Token Here
Token ID3423
Feature activation+2.44e-01

Pos logit contributions
ature+2.964
onduct+2.918
arten+2.799
 Shiv+2.780
arella+2.695
Neg logit contributions
agine-4.443
ttp-4.005
 balloons-3.973
VERTISEMENT-3.827
 execut-3.761
Token is
Token ID318
Feature activation+6.64e-01

Pos logit contributions
ature+1.922
onduct+1.903
arten+1.844
 Shiv+1.791
=]+1.783
Neg logit contributions
agine-1.855
ttp-1.707
mingham-1.614
 balloons-1.606
VERTISEMENT-1.575
Token the
Token ID262
Feature activation+7.58e-01

Pos logit contributions
ature+4.840
onduct+4.729
arten+4.494
ores+4.410
arella+4.404
Neg logit contributions
agine-5.420
ttp-5.075
 balloons-4.899
VERTISEMENT-4.735
mingham-4.689
Token link
Token ID2792
Feature activation+5.25e-01

Pos logit contributions
ature+5.511
onduct+5.292
 Shiv+5.098
arten+5.065
ores+4.794
Neg logit contributions
agine-6.311
ttp-5.677
 balloons-5.556
VERTISEMENT-5.480
mingham-5.175
Token for
Token ID329
Feature activation+8.23e-01

Pos logit contributions
ature+3.554
onduct+3.395
arten+3.221
 Shiv+3.187
=]+3.137
Neg logit contributions
agine-4.650
ttp-4.293
 balloons-4.193
VERTISEMENT-4.148
mingham-4.119
Token buying
Token ID7067
Feature activation+6.37e-01

Pos logit contributions
ature+3.787
onduct+3.670
 Shiv+3.586
ores+3.399
+3.327
Neg logit contributions
agine-8.567
 balloons-7.997
ttp-7.996
mingham-7.680
VERTISEMENT-7.669
Token the
Token ID262
Feature activation+5.15e-01

Pos logit contributions
ature+4.384
arten+4.160
onduct+4.157
antam+3.940
ores+3.887
Neg logit contributions
agine-5.446
ttp-5.158
mingham-4.854
 balloons-4.848
VERTISEMENT-4.698
Token second
Token ID1218
Feature activation+3.49e-01

Pos logit contributions
ature+3.556
onduct+3.407
ores+3.207
arten+3.181
shit+3.116
Neg logit contributions
agine-4.556
ttp-4.197
 balloons-4.094
mingham-3.945
VERTISEMENT-3.894
Token edition
Token ID8313
Feature activation-6.00e-02

Pos logit contributions
ature+1.866
arten+1.681
onduct+1.673
ores+1.581
antam+1.530
Neg logit contributions
agine-3.634
ttp-3.424
 balloons-3.360
mingham-3.244
cknowled-3.216
Token of
Token ID286
Feature activation+1.49e-01

Pos logit contributions
agine+0.435
ttp+0.410
 balloons+0.384
mingham+0.383
VERTISEMENT+0.371
Neg logit contributions
ature-0.497
onduct-0.486
arten-0.471
=]-0.465
ores-0.460
Token current
Token ID1459
Feature activation-9.13e-02

Pos logit contributions
agine+2.342
ttp+2.221
 balloons+2.136
mingham+2.098
 FB+2.068
Neg logit contributions
onduct-2.585
ature-2.576
arten-2.486
=]-2.420
arella-2.395
Token wallpaper
Token ID39328
Feature activation-1.99e-03

Pos logit contributions
agine+0.620
ttp+0.585
 balloons+0.548
mingham+0.544
VERTISEMENT+0.529
Neg logit contributions
ature-0.787
onduct-0.780
arten-0.753
=]-0.743
ores-0.731
Token $
Token ID720
Feature activation+1.19e-01

Pos logit contributions
agine+0.014
ttp+0.013
 balloons+0.012
mingham+0.012
VERTISEMENT+0.012
Neg logit contributions
ature-0.017
onduct-0.017
arten-0.016
=]-0.016
ores-0.016
Token($
Token ID16763
Feature activation+8.99e-02

Pos logit contributions
ature+0.879
onduct+0.858
arten+0.825
=]+0.811
ores+0.804
Neg logit contributions
agine-0.971
ttp-0.919
 balloons-0.866
mingham-0.865
VERTISEMENT-0.844
Tokenw
Token ID86
Feature activation+6.13e-01

Pos logit contributions
ature+0.681
onduct+0.666
arten+0.641
=]+0.630
 Shiv+0.625
Neg logit contributions
agine-0.717
ttp-0.677
 balloons-0.637
mingham-0.636
VERTISEMENT-0.621
Tokenpath
Token ID6978
Feature activation+7.74e-01

Pos logit contributions
ature+2.274
onduct+2.094
arten+1.964
ores+1.914
=]+1.911
Neg logit contributions
agine-7.135
ttp-6.835
 balloons-6.712
mingham-6.611
VERTISEMENT-6.580
Token)"
Token ID16725
Feature activation+4.93e-01

Pos logit contributions
ature+6.552
onduct+6.324
=]+6.131
arten+5.998
ores+5.990
Neg logit contributions
agine-5.268
ttp-4.866
mingham-4.647
 balloons-4.536
VERTISEMENT-4.455
Token break
Token ID2270
Feature activation+3.90e-01

Pos logit contributions
ature+4.196
onduct+4.091
arten+3.928
=]+3.908
 Shiv+3.902
Neg logit contributions
agine-3.448
ttp-3.192
mingham-3.007
 balloons-2.986
VERTISEMENT-2.911
Token }
Token ID1782
Feature activation-2.78e-01

Pos logit contributions
ature+3.475
onduct+3.395
arten+3.293
=]+3.256
ores+3.236
Neg logit contributions
agine-2.568
ttp-2.391
mingham-2.224
 balloons-2.221
VERTISEMENT-2.142
Token }
Token ID1782
Feature activation-2.06e-01

Pos logit contributions
agine+1.638
ttp+1.532
 balloons+1.427
mingham+1.388
VERTISEMENT+1.376
Neg logit contributions
ature-2.632
onduct-2.589
arten-2.515
=]-2.460
ores-2.437
Token else
Token ID2073
Feature activation+1.74e-01

Pos logit contributions
agine+1.295
ttp+1.217
 balloons+1.134
mingham+1.109
VERTISEMENT+1.097
Neg logit contributions
ature-1.876
onduct-1.838
arten-1.785
=]-1.746
arella-1.735
Token qualifier
Token ID39265
Feature activation-4.85e-01

Pos logit contributions
ature+1.014
onduct+0.999
arten+0.965
=]+0.957
arella+0.946
Neg logit contributions
agine-0.836
ttp-0.785
 balloons-0.740
mingham-0.729
VERTISEMENT-0.705
Token where
Token ID810
Feature activation-8.23e-01

Pos logit contributions
agine+3.232
ttp+3.063
 balloons+3.041
mingham+2.840
 FB+2.784
Neg logit contributions
onduct-4.000
ature-3.954
=]-3.857
arella-3.812
arten-3.806
Token they
Token ID484
Feature activation-2.41e-01

Pos logit contributions
agine+6.032
ttp+5.648
 balloons+5.557
 FB+5.502
mingham+5.174
Neg logit contributions
ature-6.096
onduct-5.946
arten-5.696
arella-5.695
=]-5.605
Token secured
Token ID13659
Feature activation-3.93e-02

Pos logit contributions
agine+1.720
ttp+1.582
 balloons+1.519
mingham+1.491
 FB+1.458
Neg logit contributions
ature-1.982
onduct-1.946
arten-1.897
=]-1.870
 Shiv-1.842
Token their
Token ID511
Feature activation+1.55e-01

Pos logit contributions
agine+0.289
ttp+0.269
 balloons+0.257
mingham+0.252
 FB+0.244
Neg logit contributions
ature-0.320
onduct-0.314
arten-0.303
arella-0.300
=]-0.299
Token spot
Token ID4136
Feature activation+7.96e-02

Pos logit contributions
ature+1.331
onduct+1.310
arten+1.265
=]+1.249
arella+1.236
Neg logit contributions
agine-1.080
ttp-1.010
 balloons-0.949
mingham-0.940
VERTISEMENT-0.905
Token for
Token ID329
Feature activation-1.25e-01

Pos logit contributions
ature+0.667
onduct+0.656
arten+0.633
=]+0.624
arella+0.616
Neg logit contributions
agine-0.568
ttp-0.537
 balloons-0.505
mingham-0.501
VERTISEMENT-0.485
Token the
Token ID262
Feature activation-3.25e-01

Pos logit contributions
agine+0.914
ttp+0.853
 balloons+0.806
mingham+0.791
 FB+0.779
Neg logit contributions
ature-1.014
onduct-1.000
arten-0.963
=]-0.951
arella-0.949
Token major
Token ID1688
Feature activation-2.73e-02

Pos logit contributions
agine+2.396
ttp+2.252
 balloons+2.160
 FB+2.087
mingham+2.085
Neg logit contributions
ature-2.562
onduct-2.542
arten-2.453
=]-2.414
arella-2.407
Token is
Token ID318
Feature activation+2.30e-01

Pos logit contributions
agine+0.194
ttp+0.183
 balloons+0.174
mingham+0.171
VERTISEMENT+0.165
Neg logit contributions
ature-0.229
onduct-0.227
arten-0.217
=]-0.214
arella-0.213
Token of
Token ID286
Feature activation+7.54e-01

Pos logit contributions
ature+1.817
onduct+1.775
arten+1.712
=]+1.691
ores+1.668
Neg logit contributions
agine-1.770
ttp-1.665
 balloons-1.571
mingham-1.566
VERTISEMENT-1.520
Token meeting
Token ID3249
Feature activation+1.54e-01

Pos logit contributions
ature+0.704
onduct+0.690
arten+0.665
=]+0.657
ores+0.649
Neg logit contributions
agine-0.615
ttp-0.578
 balloons-0.547
mingham-0.541
VERTISEMENT-0.523
Token room
Token ID2119
Feature activation+4.44e-01

Pos logit contributions
ature+1.181
onduct+1.158
arten+1.109
=]+1.103
ores+1.083
Neg logit contributions
agine-1.212
ttp-1.150
 balloons-1.101
mingham-1.077
VERTISEMENT-1.054
Token internet
Token ID5230
Feature activation+5.08e-01

Pos logit contributions
ature+3.552
onduct+3.454
arten+3.346
ores+3.292
=]+3.281
Neg logit contributions
agine-3.365
ttp-3.147
mingham-2.951
 balloons-2.924
VERTISEMENT-2.859
Token at
Token ID379
Feature activation+3.17e-02

Pos logit contributions
ature+4.300
onduct+4.207
arten+4.096
=]+4.024
ores+4.020
Neg logit contributions
agine-3.547
ttp-3.311
mingham-3.101
 balloons-3.023
VERTISEMENT-2.977
Token the
Token ID262
Feature activation+5.16e-01

Pos logit contributions
ature+0.249
onduct+0.245
arten+0.235
=]+0.233
arella+0.230
Neg logit contributions
agine-0.243
ttp-0.230
 balloons-0.216
mingham-0.212
VERTISEMENT-0.207
Token West
Token ID2688
Feature activation+5.52e-01

Pos logit contributions
ature+4.133
onduct+4.023
arten+3.891
=]+3.843
 Shiv+3.834
Neg logit contributions
agine-3.847
ttp-3.617
mingham-3.398
 balloons-3.361
VERTISEMENT-3.318
Tokenin
Token ID259
Feature activation+2.40e-01

Pos logit contributions
ature+4.130
onduct+4.021
arten+3.894
ores+3.836
 Shiv+3.812
Neg logit contributions
agine-4.366
ttp-4.097
mingham-3.889
 balloons-3.866
VERTISEMENT-3.776
Token cut
Token ID2005
Feature activation+7.98e-01

Pos logit contributions
ature+1.873
onduct+1.837
arten+1.764
=]+1.747
ores+1.724
Neg logit contributions
agine-1.866
ttp-1.760
 balloons-1.657
mingham-1.647
VERTISEMENT-1.601
Token out
Token ID503
Feature activation+1.54e-01

Pos logit contributions
ature+6.036
onduct+5.848
arten+5.726
=]+5.643
 Shiv+5.609
Neg logit contributions
agine-6.132
ttp-5.693
mingham-5.482
VERTISEMENT-5.322
 balloons-5.304
Token (
Token ID357
Feature activation+3.34e-01

Pos logit contributions
ature+1.278
onduct+1.251
arten+1.207
=]+1.193
ores+1.182
Neg logit contributions
agine-1.110
ttp-1.047
 balloons-0.984
mingham-0.974
VERTISEMENT-0.946
Tokenas
Token ID292
Feature activation+1.24e-01

Pos logit contributions
ature+2.642
onduct+2.579
arten+2.488
=]+2.454
ores+2.436
Neg logit contributions
agine-2.551
ttp-2.398
 balloons-2.255
mingham-2.251
VERTISEMENT-2.192
Token that
Token ID326
Feature activation+3.83e-02

Pos logit contributions
agine+0.510
ttp+0.474
 balloons+0.450
mingham+0.445
VERTISEMENT+0.432
Neg logit contributions
ature-0.590
onduct-0.577
arten-0.561
=]-0.551
ores-0.547
Token the
Token ID262
Feature activation-6.93e-02

Pos logit contributions
ature+0.316
onduct+0.310
arten+0.300
=]+0.295
ores+0.292
Neg logit contributions
agine-0.280
ttp-0.262
 balloons-0.247
mingham-0.244
VERTISEMENT-0.237
Token coalition
Token ID9906
Feature activation+1.30e-01

Pos logit contributions
agine+0.504
ttp+0.470
 balloons+0.453
mingham+0.443
 FB+0.428
Neg logit contributions
ature-0.568
onduct-0.561
arten-0.543
=]-0.529
ores-0.525
Token was
Token ID373
Feature activation-4.86e-02

Pos logit contributions
ature+1.067
onduct+1.053
arten+1.015
=]+1.004
ores+0.991
Neg logit contributions
agine-0.957
ttp-0.894
 balloons-0.849
mingham-0.837
VERTISEMENT-0.815
Token illegitimate
Token ID41368
Feature activation+4.21e-01

Pos logit contributions
agine+0.351
ttp+0.323
 balloons+0.311
mingham+0.307
VERTISEMENT+0.294
Neg logit contributions
ature-0.398
onduct-0.398
arten-0.384
=]-0.379
arella-0.375
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
ature+3.414
onduct+3.323
arten+3.197
ores+3.149
=]+3.141
Neg logit contributions
agine-3.133
ttp-2.952
mingham-2.754
 balloons-2.745
VERTISEMENT-2.679
Token divisive
Token ID29656
Feature activation+1.84e-01

Pos logit contributions
ature+0.099
onduct+0.098
arten+0.095
=]+0.094
arella+0.093
Neg logit contributions
agine-0.080
ttp-0.074
 balloons-0.071
mingham-0.069
VERTISEMENT-0.067
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
ature+1.535
onduct+1.502
arten+1.453
=]+1.434
ores+1.422
Neg logit contributions
agine-1.329
ttp-1.246
 balloons-1.169
mingham-1.165
VERTISEMENT-1.132
Token unstable
Token ID21354
Feature activation+2.24e-01

Pos logit contributions
ature+1.290
onduct+1.271
arten+1.228
=]+1.214
ores+1.199
Neg logit contributions
agine-1.161
ttp-1.083
 balloons-1.033
mingham-1.020
VERTISEMENT-0.989
Token and
Token ID290
Feature activation+1.84e-01

Pos logit contributions
ature+1.870
onduct+1.829
arten+1.768
=]+1.744
ores+1.731
Neg logit contributions
agine-1.621
ttp-1.519
 balloons-1.423
mingham-1.420
VERTISEMENT-1.379
Token,
Token ID11
Feature activation+2.20e-01

Pos logit contributions
ature+1.482
onduct+1.460
arten+1.411
=]+1.393
ores+1.374
Neg logit contributions
agine-1.369
ttp-1.277
 balloons-1.218
mingham-1.202
VERTISEMENT-1.167
Token and
Token ID290
Feature activation+5.33e-01

Pos logit contributions
ature+0.607
onduct+0.593
arten+0.569
ores+0.562
=]+0.558
Neg logit contributions
agine-0.585
ttp-0.553
mingham-0.521
 balloons-0.517
VERTISEMENT-0.509
Token explore
Token ID7301
Feature activation+6.52e-01

Pos logit contributions
onduct+2.599
ature+2.590
ores+2.402
=]+2.299
 Shiv+2.266
Neg logit contributions
agine-5.425
ttp-5.312
VERTISEMENT-5.145
mingham-5.143
 balloons-4.969
Token the
Token ID262
Feature activation+5.23e-01

Pos logit contributions
ature+4.435
onduct+4.403
ores+4.211
 Shiv+4.183
arten+4.081
Neg logit contributions
agine-5.397
ttp-5.022
mingham-4.896
 balloons-4.837
VERTISEMENT-4.812
Token world
Token ID995
Feature activation+5.56e-01

Pos logit contributions
ature+3.410
onduct+3.362
ores+3.326
 Shiv+3.266
arten+3.216
Neg logit contributions
agine-4.332
ttp-4.159
mingham-4.001
VERTISEMENT-3.832
 balloons-3.825
Token with
Token ID351
Feature activation+4.26e-01

Pos logit contributions
ature+3.561
onduct+3.455
ores+3.374
arten+3.353
 Shiv+3.312
Neg logit contributions
agine-4.910
ttp-4.701
mingham-4.462
VERTISEMENT-4.450
 balloons-4.401
Token kindred
Token ID46449
Feature activation-1.26e-01

Pos logit contributions
ature+3.343
onduct+3.195
 Shiv+3.069
ores+3.037
=]+2.969
Neg logit contributions
agine-3.211
ttp-3.074
mingham-2.946
VERTISEMENT-2.854
cknowled-2.761
Token spirits
Token ID13747
Feature activation+7.22e-02

Pos logit contributions
agine+0.894
ttp+0.836
 balloons+0.783
mingham+0.780
VERTISEMENT+0.756
Neg logit contributions
ature-1.074
onduct-1.050
arten-1.017
=]-1.003
ores-0.995
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
ature+0.609
onduct+0.597
arten+0.576
ores+0.566
 Shiv+0.563
Neg logit contributions
agine-0.514
ttp-0.482
 balloons-0.454
mingham-0.453
VERTISEMENT-0.441
Token Be
Token ID1355
Feature activation+1.91e-02

Pos logit contributions
ature+2.258
onduct+2.198
arten+2.127
 Shiv+2.116
=]+2.102
Neg logit contributions
agine-1.805
ttp-1.680
 balloons-1.598
mingham-1.596
VERTISEMENT-1.550
Token the
Token ID262
Feature activation-3.62e-01

Pos logit contributions
ature+0.153
onduct+0.150
arten+0.145
=]+0.142
ores+0.142
Neg logit contributions
agine-0.142
ttp-0.134
 balloons-0.126
mingham-0.126
VERTISEMENT-0.123
Token first
Token ID717
Feature activation+1.66e-01

Pos logit contributions
agine+2.413
ttp+2.222
 balloons+2.106
mingham+2.069
VERTISEMENT+1.955
Neg logit contributions
ature-3.196
onduct-3.143
arten-3.008
=]-3.004
ores-2.991
Token the
Token ID262
Feature activation-2.69e-01

Pos logit contributions
agine+3.463
ttp+3.261
 balloons+3.111
 FB+3.057
mingham+2.996
Neg logit contributions
ature-3.920
onduct-3.883
arten-3.828
=]-3.709
ores-3.646
Token UL
Token ID44475
Feature activation-2.28e-01

Pos logit contributions
agine+2.057
ttp+1.949
 balloons+1.844
mingham+1.802
 FB+1.795
Neg logit contributions
ature-2.062
onduct-2.034
arten-1.994
=]-1.922
ores-1.899
TokenMB
Token ID10744
Feature activation-1.77e-01

Pos logit contributions
agine+1.741
ttp+1.623
 balloons+1.509
mingham+1.493
VERTISEMENT+1.470
Neg logit contributions
ature-1.773
onduct-1.737
arten-1.707
=]-1.663
arella-1.652
Token stro
Token ID9660
Feature activation+6.30e-02

Pos logit contributions
agine+1.321
ttp+1.264
 balloons+1.156
mingham+1.146
VERTISEMENT+1.140
Neg logit contributions
ature-1.382
onduct-1.364
arten-1.330
=]-1.310
 Shiv-1.291
Tokenbed
Token ID3077
Feature activation-1.99e-01

Pos logit contributions
ature+0.533
onduct+0.522
arten+0.508
=]+0.501
 Shiv+0.496
Neg logit contributions
agine-0.446
ttp-0.418
mingham-0.389
 balloons-0.388
VERTISEMENT-0.373
Token back
Token ID736
Feature activation-1.70e-02

Pos logit contributions
agine+1.492
ttp+1.413
 balloons+1.348
mingham+1.306
 FB+1.299
Neg logit contributions
ature-1.535
onduct-1.531
arten-1.504
=]-1.470
arella-1.441
Tokenlight
Token ID2971
Feature activation+3.44e-02

Pos logit contributions
agine+0.129
ttp+0.122
 balloons+0.115
mingham+0.115
VERTISEMENT+0.111
Neg logit contributions
ature-0.134
onduct-0.131
arten-0.128
=]-0.125
 Shiv-0.124
Token as
Token ID355
Feature activation+2.01e-01

Pos logit contributions
ature+0.292
onduct+0.288
arten+0.281
=]+0.276
arella+0.272
Neg logit contributions
agine-0.240
ttp-0.224
 balloons-0.212
mingham-0.209
VERTISEMENT-0.203
Token well
Token ID880
Feature activation-2.37e-01

Pos logit contributions
ature+1.606
onduct+1.568
arten+1.515
=]+1.492
ores+1.480
Neg logit contributions
agine-1.526
ttp-1.435
 balloons-1.349
mingham-1.345
VERTISEMENT-1.309
Token if
Token ID611
Feature activation-1.37e-01

Pos logit contributions
agine+1.634
ttp+1.536
 balloons+1.447
mingham+1.429
VERTISEMENT+1.376
Neg logit contributions
ature-2.011
onduct-1.973
arten-1.933
=]-1.918
arella-1.873
Token you
Token ID345
Feature activation+3.78e-02

Pos logit contributions
agine+1.014
ttp+0.952
 balloons+0.901
mingham+0.886
VERTISEMENT+0.861
Neg logit contributions
ature-1.104
onduct-1.088
arten-1.056
=]-1.034
arella-1.021
Tokenopus
Token ID25790
Feature activation+2.19e-01

Pos logit contributions
ature+3.842
onduct+3.669
ores+3.334
arten+3.296
arella+3.216
Neg logit contributions
agine-8.464
ttp-8.199
 balloons-7.951
VERTISEMENT-7.927
mingham-7.895
Token comment
Token ID2912
Feature activation+1.02e-02

Pos logit contributions
ature+1.591
onduct+1.552
arten+1.494
=]+1.465
ores+1.457
Neg logit contributions
agine-1.822
ttp-1.721
 balloons-1.634
mingham-1.623
VERTISEMENT-1.583
Token]
Token ID60
Feature activation+3.43e-02

Pos logit contributions
ature+0.072
onduct+0.071
arten+0.069
=]+0.067
arella+0.066
Neg logit contributions
agine-0.086
ttp-0.081
 balloons-0.077
mingham-0.077
VERTISEMENT-0.074
Token went
Token ID1816
Feature activation-3.60e-01

Pos logit contributions
ature+0.282
onduct+0.276
arten+0.267
=]+0.263
ores+0.260
Neg logit contributions
agine-0.251
ttp-0.236
 balloons-0.225
mingham-0.219
VERTISEMENT-0.214
Token quite
Token ID2407
Feature activation-3.20e-01

Pos logit contributions
agine+2.788
ttp+2.668
 balloons+2.577
mingham+2.472
VERTISEMENT+2.460
Neg logit contributions
ature-2.719
onduct-2.656
arten-2.572
=]-2.518
arella-2.489
Token big
Token ID1263
Feature activation-2.97e-01

Pos logit contributions
agine+2.271
ttp+2.184
 balloons+2.121
mingham+2.018
 FB+1.968
Neg logit contributions
ature-2.589
onduct-2.537
arten-2.477
=]-2.451
arella-2.432
Token!
Token ID0
Feature activation-7.21e-02

Pos logit contributions
agine+1.959
ttp+1.868
 balloons+1.806
mingham+1.717
 FB+1.647
Neg logit contributions
ature-2.538
onduct-2.530
arten-2.455
=]-2.454
ores-2.382
Token It
Token ID632
Feature activation-9.71e-02

Pos logit contributions
agine+0.527
ttp+0.503
 balloons+0.478
mingham+0.460
 FB+0.456
Neg logit contributions
ature-0.584
onduct-0.579
arten-0.558
=]-0.546
ores-0.544
Token was
Token ID373
Feature activation-3.54e-01

Pos logit contributions
agine+0.693
ttp+0.643
 balloons+0.632
mingham+0.598
VERTISEMENT+0.582
Neg logit contributions
ature-0.809
onduct-0.801
arten-0.773
=]-0.764
arella-0.756
Token just
Token ID655
Feature activation-3.40e-01

Pos logit contributions
agine+2.554
 balloons+2.360
ttp+2.336
 FB+2.193
mingham+2.154
Neg logit contributions
ature-2.904
onduct-2.876
arten-2.768
=]-2.739
arella-2.723
Token a
Token ID257
Feature activation-4.28e-01

Pos logit contributions
agine+2.476
 balloons+2.325
ttp+2.295
 FB+2.141
mingham+2.107
Neg logit contributions
ature-2.744
onduct-2.734
arten-2.611
arella-2.594
=]-2.594
Token variation
Token ID12291
Feature activation-6.24e-02

Pos logit contributions
agine+3.261
 balloons+3.078
ttp+3.075
mingham+2.892
 FB+2.828
Neg logit contributions
onduct-3.696
ature-3.667
arten-3.602
=]-3.548
 Shiv-3.470
Token as
Token ID355
Feature activation-1.46e-01

Pos logit contributions
agine+0.434
ttp+0.406
 balloons+0.390
mingham+0.380
VERTISEMENT+0.366
Neg logit contributions
ature-0.527
onduct-0.520
arten-0.505
=]-0.502
 Shiv-0.490
Token both
Token ID1111
Feature activation+5.70e-02

Pos logit contributions
agine+1.085
ttp+1.011
 balloons+0.971
mingham+0.952
VERTISEMENT+0.935
Neg logit contributions
ature-1.177
onduct-1.144
arten-1.121
=]-1.109
arella-1.088
Token cameras
Token ID9073
Feature activation+1.42e-01

Pos logit contributions
ature+0.466
onduct+0.457
arten+0.443
=]+0.437
ores+0.429
Neg logit contributions
agine-0.417
ttp-0.393
 balloons-0.373
mingham-0.367
VERTISEMENT-0.358
Token had
Token ID550
Feature activation-1.87e-01

Pos logit contributions
ature+1.100
onduct+1.078
arten+1.044
=]+1.029
 Shiv+1.011
Neg logit contributions
agine-1.100
ttp-1.031
 balloons-0.977
mingham-0.970
VERTISEMENT-0.942
Token near
Token ID1474
Feature activation-5.09e-01

Pos logit contributions
agine+1.383
ttp+1.296
 balloons+1.240
mingham+1.211
VERTISEMENT+1.188
Neg logit contributions
ature-1.495
onduct-1.462
arten-1.428
=]-1.413
arella-1.384
Token identical
Token ID10411
Feature activation-1.02e-01

Pos logit contributions
agine+3.941
ttp+3.729
 balloons+3.583
mingham+3.494
 FB+3.462
Neg logit contributions
onduct-3.690
ature-3.664
arten-3.558
=]-3.495
 Shiv-3.409
Token optical
Token ID18480
Feature activation+1.95e-01

Pos logit contributions
agine+0.696
ttp+0.650
 balloons+0.620
mingham+0.604
VERTISEMENT+0.591
Neg logit contributions
ature-0.874
onduct-0.859
arten-0.840
=]-0.824
 Shiv-0.808
Token performance
Token ID2854
Feature activation+9.96e-02

Pos logit contributions
ature+1.594
onduct+1.558
arten+1.508
=]+1.486
ores+1.473
Neg logit contributions
agine-1.436
ttp-1.348
 balloons-1.266
mingham-1.260
VERTISEMENT-1.225
Token.
Token ID13
Feature activation+2.43e-02

Pos logit contributions
ature+0.847
onduct+0.833
arten+0.808
=]+0.801
 Shiv+0.788
Neg logit contributions
agine-0.694
ttp-0.652
 balloons-0.617
mingham-0.609
VERTISEMENT-0.594
Token
Token ID198
Feature activation+9.93e-02

Pos logit contributions
ature+0.193
onduct+0.191
arten+0.184
=]+0.181
ores+0.179
Neg logit contributions
agine-0.183
ttp-0.173
 balloons-0.163
mingham-0.161
VERTISEMENT-0.159
Token he
Token ID339
Feature activation-6.11e-02

Pos logit contributions
agine+3.329
ttp+3.140
 balloons+3.065
 FB+2.844
mingham+2.835
Neg logit contributions
ature-4.321
onduct-4.277
arten-4.186
=]-4.151
arella-4.081
Token would
Token ID561
Feature activation-1.29e-01

Pos logit contributions
agine+0.434
ttp+0.405
 balloons+0.387
mingham+0.376
VERTISEMENT+0.363
Neg logit contributions
ature-0.513
onduct-0.504
arten-0.487
=]-0.483
ores-0.474
Token submit
Token ID9199
Feature activation-2.48e-01

Pos logit contributions
agine+0.956
ttp+0.879
 balloons+0.847
mingham+0.825
 FB+0.799
Neg logit contributions
ature-1.050
onduct-1.018
arten-0.999
=]-0.980
ores-0.963
Token a
Token ID257
Feature activation+1.47e-01

Pos logit contributions
agine+1.750
ttp+1.634
 balloons+1.594
mingham+1.517
 FB+1.484
Neg logit contributions
ature-2.063
onduct-2.018
=]-1.969
arten-1.963
ores-1.941
Token bill
Token ID2855
Feature activation+1.08e-01

Pos logit contributions
ature+1.155
onduct+1.135
arten+1.099
=]+1.081
ores+1.073
Neg logit contributions
agine-1.128
ttp-1.060
 balloons-1.006
mingham-0.996
VERTISEMENT-0.971
Token proposing
Token ID24634
Feature activation-3.30e-01

Pos logit contributions
ature+0.851
onduct+0.832
arten+0.802
=]+0.792
ores+0.784
Neg logit contributions
agine-0.833
ttp-0.784
 balloons-0.739
mingham-0.734
VERTISEMENT-0.714
Token to
Token ID284
Feature activation-1.40e-01

Pos logit contributions
agine+2.347
ttp+2.196
 balloons+2.115
mingham+2.013
 FB+1.995
Neg logit contributions
ature-2.709
onduct-2.640
=]-2.606
arten-2.586
ores-2.511
Token criminal
Token ID4301
Feature activation-5.65e-01

Pos logit contributions
agine+0.986
ttp+0.917
 balloons+0.879
mingham+0.853
 FB+0.834
Neg logit contributions
ature-1.175
onduct-1.145
arten-1.123
=]-1.113
arella-1.086
Tokenize
Token ID1096
Feature activation-1.44e-01

Pos logit contributions
agine+4.236
ttp+3.849
 balloons+3.773
mingham+3.631
 FB+3.533
Neg logit contributions
ature-4.234
onduct-4.153
arella-4.059
arten-4.059
=]-4.057
Token ritual
Token ID12146
Feature activation-1.53e-01

Pos logit contributions
agine+1.034
ttp+0.971
 balloons+0.925
mingham+0.895
VERTISEMENT+0.877
Neg logit contributions
ature-1.184
onduct-1.167
arten-1.136
=]-1.124
arella-1.106
Token circumcision
Token ID25513
Feature activation+3.71e-01

Pos logit contributions
agine+1.434
ttp+1.368
 balloons+1.308
mingham+1.293
VERTISEMENT+1.270
Neg logit contributions
ature-0.928
onduct-0.906
arten-0.871
=]-0.856
ores-0.836
Token policies
Token ID4788
Feature activation+3.45e-01

Pos logit contributions
ature+2.656
onduct+2.588
arten+2.490
=]+2.454
ores+2.447
Neg logit contributions
agine-2.600
ttp-2.454
mingham-2.300
 balloons-2.287
VERTISEMENT-2.240
Token.
Token ID13
Feature activation+3.76e-01

Pos logit contributions
ature+2.826
onduct+2.762
arten+2.663
ores+2.622
=]+2.619
Neg logit contributions
agine-2.531
ttp-2.382
mingham-2.232
 balloons-2.220
VERTISEMENT-2.163
Token That
Token ID1320
Feature activation-1.56e-01

Pos logit contributions
ature+2.852
onduct+2.772
arten+2.672
=]+2.634
 Shiv+2.618
Neg logit contributions
agine-3.002
ttp-2.829
 balloons-2.667
mingham-2.666
VERTISEMENT-2.591
Token is
Token ID318
Feature activation+1.02e-01

Pos logit contributions
agine+1.112
ttp+1.044
 balloons+0.995
mingham+0.960
VERTISEMENT+0.958
Neg logit contributions
ature-1.305
onduct-1.284
=]-1.226
arten-1.222
arella-1.214
Token not
Token ID407
Feature activation-2.11e-01

Pos logit contributions
ature+0.818
onduct+0.799
arten+0.769
=]+0.765
ores+0.754
Neg logit contributions
agine-0.773
ttp-0.721
 balloons-0.683
mingham-0.674
VERTISEMENT-0.661
Token even
Token ID772
Feature activation-1.73e-01

Pos logit contributions
agine+1.561
ttp+1.439
 balloons+1.400
mingham+1.337
VERTISEMENT+1.334
Neg logit contributions
ature-1.703
onduct-1.670
=]-1.628
arten-1.597
arella-1.592
Token the
Token ID262
Feature activation-7.34e-02

Pos logit contributions
agine+1.310
ttp+1.209
 balloons+1.171
mingham+1.133
VERTISEMENT+1.128
Neg logit contributions
ature-1.375
onduct-1.342
=]-1.302
arten-1.301
ores-1.268
Token worst
Token ID5290
Feature activation-1.15e-01

Pos logit contributions
agine+0.522
ttp+0.489
 balloons+0.472
mingham+0.454
VERTISEMENT+0.445
Neg logit contributions
ature-0.611
onduct-0.597
arten-0.577
=]-0.576
ores-0.567
Token of
Token ID286
Feature activation+8.86e-02

Pos logit contributions
agine+0.772
ttp+0.729
 balloons+0.691
mingham+0.680
VERTISEMENT+0.667
Neg logit contributions
ature-1.000
onduct-0.984
arten-0.946
=]-0.945
ores-0.927
Token it
Token ID340
Feature activation-1.44e-01

Pos logit contributions
ature+0.697
onduct+0.677
arten+0.655
=]+0.648
ores+0.640
Neg logit contributions
agine-0.683
ttp-0.644
 balloons-0.613
mingham-0.602
VERTISEMENT-0.591
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
agine+0.933
ttp+0.869
 balloons+0.816
mingham+0.800
VERTISEMENT+0.777
Neg logit contributions
ature-1.289
onduct-1.268
=]-1.231
arten-1.228
arella-1.199
Token them
Token ID606
Feature activation-2.36e-01

Pos logit contributions
agine+0.001
ttp+0.001
 balloons+0.001
mingham+0.001
VERTISEMENT+0.001
Neg logit contributions
ature-0.001
onduct-0.001
arten-0.001
=]-0.001
ores-0.001
Token access
Token ID1895
Feature activation-1.51e-01

Pos logit contributions
agine+1.754
ttp+1.628
 balloons+1.595
VERTISEMENT+1.517
 FB+1.505
Neg logit contributions
ature-1.896
onduct-1.844
=]-1.794
arten-1.781
ores-1.740
Token to
Token ID284
Feature activation-1.35e-02

Pos logit contributions
agine+1.212
ttp+1.146
 balloons+1.083
mingham+1.078
VERTISEMENT+1.052
Neg logit contributions
ature-1.129
onduct-1.099
arten-1.060
=]-1.047
ores-1.032
Token all
Token ID477
Feature activation+1.21e-02

Pos logit contributions
agine+0.100
ttp+0.094
 balloons+0.089
mingham+0.087
VERTISEMENT+0.084
Neg logit contributions
ature-0.111
onduct-0.108
arten-0.105
=]-0.104
ores-0.102
Token the
Token ID262
Feature activation-3.59e-02

Pos logit contributions
ature+0.098
onduct+0.096
arten+0.093
=]+0.092
ores+0.091
Neg logit contributions
agine-0.089
ttp-0.084
 balloons-0.079
mingham-0.077
VERTISEMENT-0.076
Token evidence
Token ID2370
Feature activation-2.50e-01

Pos logit contributions
agine+0.264
ttp+0.249
 balloons+0.240
mingham+0.229
VERTISEMENT+0.224
Neg logit contributions
ature-0.292
onduct-0.286
arten-0.278
=]-0.275
ores-0.270
Token still
Token ID991
Feature activation+4.82e-02

Pos logit contributions
agine+1.733
ttp+1.604
 balloons+1.553
mingham+1.452
 FB+1.444
Neg logit contributions
ature-2.136
onduct-2.094
arten-2.021
=]-2.009
arella-1.964
Token outstanding
Token ID11660
Feature activation-4.23e-01

Pos logit contributions
ature+0.398
onduct+0.391
arten+0.379
=]+0.375
 Shiv+0.368
Neg logit contributions
agine-0.351
ttp-0.326
 balloons-0.310
mingham-0.299
VERTISEMENT-0.295
Token so
Token ID523
Feature activation-5.63e-02

Pos logit contributions
agine+2.814
ttp+2.592
 balloons+2.478
mingham+2.328
 FB+2.307
Neg logit contributions
ature-3.624
onduct-3.539
arten-3.460
=]-3.457
 Shiv-3.377
Token they
Token ID484
Feature activation-1.08e-01

Pos logit contributions
agine+0.378
ttp+0.358
 balloons+0.333
mingham+0.327
VERTISEMENT+0.316
Neg logit contributions
ature-0.498
onduct-0.485
arten-0.469
=]-0.467
ores-0.459
Token can
Token ID460
Feature activation-5.72e-02

Pos logit contributions
agine+0.771
ttp+0.702
 balloons+0.674
mingham+0.659
 FB+0.627
Neg logit contributions
ature-0.906
onduct-0.883
arten-0.858
=]-0.850
 Shiv-0.834
Tokenbind
Token ID21653
Feature activation-3.99e-01

Pos logit contributions
agine+1.212
ttp+1.163
 balloons+1.110
mingham+1.103
VERTISEMENT+1.082
Neg logit contributions
ature-0.410
onduct-0.400
arten-0.366
=]-0.357
 Shiv-0.351
Token directive
Token ID22644
Feature activation-2.79e-01

Pos logit contributions
agine+2.777
ttp+2.653
 balloons+2.486
mingham+2.406
VERTISEMENT+2.404
Neg logit contributions
onduct-3.322
ature-3.235
arten-3.151
=]-3.127
arella-3.114
Token:
Token ID25
Feature activation-4.32e-01

Pos logit contributions
agine+1.922
ttp+1.780
 balloons+1.707
mingham+1.632
 FB+1.595
Neg logit contributions
onduct-2.371
ature-2.359
arten-2.290
=]-2.278
arella-2.216
Token
Token ID198
Feature activation-6.47e-01

Pos logit contributions
agine+3.209
ttp+2.991
 balloons+2.813
mingham+2.781
VERTISEMENT+2.720
Neg logit contributions
ature-3.482
onduct-3.424
arten-3.300
=]-3.257
ores-3.226
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
agine+3.875
ttp+3.722
 balloons+3.379
mingham+3.337
 FB+3.322
Neg logit contributions
onduct-5.766
ature-5.749
arten-5.597
arella-5.439
=]-5.433
Token<
Token ID27
Feature activation-1.16e+00

Pos logit contributions
agine+6.812
ttp+6.544
mingham+5.724
fy+5.679
tml+5.635
Neg logit contributions
onduct-8.262
ature-8.257
arella-7.919
 Shiv-7.918
arten-7.907
Tokenbody
Token ID2618
Feature activation-4.89e-01

Pos logit contributions
agine+9.199
ttp+9.027
tml+8.156
mingham+7.978
 balloons+7.900
Neg logit contributions
onduct-7.403
ature-7.207
arella-7.201
arten-7.111
=]-6.921
Token ng
Token ID23370
Feature activation+1.21e-01

Pos logit contributions
agine+2.258
ttp+2.033
 balloons+1.787
mingham+1.753
VERTISEMENT+1.708
Neg logit contributions
ature-5.231
onduct-5.207
arten-5.024
arella-5.018
=]-4.982
Token-
Token ID12
Feature activation-3.53e-01

Pos logit contributions
ature+0.927
onduct+0.906
arten+0.872
=]+0.859
ores+0.852
Neg logit contributions
agine-0.954
ttp-0.900
 balloons-0.846
mingham-0.844
VERTISEMENT-0.822
Tokencontroller
Token ID36500
Feature activation+2.89e-01

Pos logit contributions
agine+3.739
ttp+3.567
mingham+3.347
 balloons+3.342
 FB+3.232
Neg logit contributions
ature-1.724
onduct-1.700
arten-1.586
=]-1.558
 Shiv-1.545
Token="
Token ID2625
Feature activation-7.94e-02

Pos logit contributions
ature+0.967
onduct+0.889
arten+0.840
=]+0.829
ores+0.768
Neg logit contributions
agine-3.500
ttp-3.386
 balloons-3.272
mingham-3.267
VERTISEMENT-3.200
Tokenqa
Token ID20402
Feature activation+9.11e-02

Pos logit contributions
ature+0.683
onduct+0.670
arten+0.643
=]+0.636
 Shiv+0.628
Neg logit contributions
agine-0.713
ttp-0.671
 balloons-0.632
mingham-0.631
VERTISEMENT-0.613
Token,
Token ID11
Feature activation-4.25e-01

Pos logit contributions
ature+0.796
onduct+0.781
arten+0.757
=]+0.748
ores+0.739
Neg logit contributions
agine-0.620
ttp-0.578
 balloons-0.540
mingham-0.537
VERTISEMENT-0.521
Token for
Token ID329
Feature activation-1.64e-01

Pos logit contributions
agine+3.219
ttp+3.038
 balloons+2.902
mingham+2.818
VERTISEMENT+2.744
Neg logit contributions
ature-3.266
onduct-3.232
arten-3.122
=]-3.064
arella-3.026
Token men
Token ID1450
Feature activation-2.78e-01

Pos logit contributions
agine+1.235
ttp+1.161
 balloons+1.106
mingham+1.087
VERTISEMENT+1.058
Neg logit contributions
ature-1.292
onduct-1.284
arten-1.233
=]-1.206
arella-1.202
Token),
Token ID828
Feature activation-1.95e-02

Pos logit contributions
agine+1.749
ttp+1.606
 balloons+1.522
mingham+1.475
VERTISEMENT+1.388
Neg logit contributions
onduct-2.493
ature-2.487
arten-2.415
=]-2.390
arella-2.389
Token iron
Token ID6953
Feature activation-1.69e+00

Pos logit contributions
agine+0.142
ttp+0.133
 balloons+0.127
mingham+0.125
VERTISEMENT+0.122
Neg logit contributions
ature-0.160
onduct-0.156
arten-0.151
=]-0.149
ores-0.147
Token (
Token ID357
Feature activation+1.71e-02

Pos logit contributions
agine+9.919
 balloons+9.226
mingham+8.872
ttp+8.802
VERTISEMENT+8.390
Neg logit contributions
onduct-12.337
=]-12.075
arella-12.054
arten-11.977
ature-11.691
Tokentem
Token ID11498
Feature activation-1.41e-01

Pos logit contributions
ature+0.130
onduct+0.127
arten+0.122
=]+0.121
 Shiv+0.120
Neg logit contributions
agine-0.136
ttp-0.128
mingham-0.121
 balloons-0.120
VERTISEMENT-0.116
Tokenür
Token ID25151
Feature activation-2.76e-01

Pos logit contributions
agine+1.124
ttp+1.051
mingham+0.988
 balloons+0.987
VERTISEMENT+0.943
Neg logit contributions
ature-1.059
onduct-1.046
=]-1.007
arten-1.004
 Shiv-0.987
Token),
Token ID828
Feature activation+2.35e-03

Pos logit contributions
agine+1.961
ttp+1.830
mingham+1.713
 balloons+1.713
VERTISEMENT+1.632
Neg logit contributions
ature-2.275
onduct-2.267
arten-2.189
=]-2.168
 Shiv-2.139
Token steel
Token ID7771
Feature activation-9.95e-01

Pos logit contributions
ature+0.019
onduct+0.019
arten+0.018
=]+0.018
ores+0.018
Neg logit contributions
agine-0.017
ttp-0.016
 balloons-0.015
mingham-0.015
VERTISEMENT-0.015
Token
Token ID564
Feature activation-2.93e-01

Pos logit contributions
agine+0.488
ttp+0.455
 balloons+0.437
mingham+0.424
VERTISEMENT+0.414
Neg logit contributions
ature-0.549
onduct-0.538
arten-0.522
=]-0.514
arella-0.506
Token
Token ID250
Feature activation-1.76e-01

Pos logit contributions
agine+2.348
ttp+2.237
 balloons+2.109
mingham+2.062
VERTISEMENT+2.049
Neg logit contributions
ature-2.175
onduct-2.104
arten-2.039
=]-2.003
arella-1.991
Tokenwas
Token ID9776
Feature activation+9.77e-02

Pos logit contributions
agine+1.472
ttp+1.400
mingham+1.311
 balloons+1.308
cknowled+1.268
Neg logit contributions
ature-1.251
onduct-1.218
arten-1.179
 Shiv-1.155
=]-1.153
Token po
Token ID745
Feature activation-6.04e-01

Pos logit contributions
ature+0.800
onduct+0.783
arten+0.759
=]+0.747
arella+0.738
Neg logit contributions
agine-0.721
ttp-0.675
 balloons-0.634
mingham-0.632
VERTISEMENT-0.614
Tokenin
Token ID259
Feature activation+3.23e-01

Pos logit contributions
agine+3.767
ttp+3.478
 balloons+3.311
fy+3.155
mingham+3.134
Neg logit contributions
ature-5.314
=]-5.148
onduct-5.138
arten-5.094
arella-4.931
Token­
Token ID3907
Feature activation-1.13e+00

Pos logit contributions
ature+2.585
onduct+2.521
arten+2.434
=]+2.397
ores+2.387
Neg logit contributions
agine-2.440
ttp-2.294
 balloons-2.157
mingham-2.155
VERTISEMENT-2.100
Tokented
Token ID1513
Feature activation+3.32e-03

Pos logit contributions
agine+8.518
ttp+7.778
fy+7.432
mingham+7.353
 balloons+7.208
Neg logit contributions
 Shiv-7.710
onduct-7.566
=]-7.563
-7.559
ature-7.525
Tokenly
Token ID306
Feature activation+2.18e-01

Pos logit contributions
ature+0.027
onduct+0.026
arten+0.026
=]+0.025
 Shiv+0.025
Neg logit contributions
agine-0.025
ttp-0.023
 balloons-0.022
mingham-0.022
VERTISEMENT-0.021
Token denied
Token ID6699
Feature activation+2.00e-01

Pos logit contributions
ature+1.796
onduct+1.759
arten+1.700
=]+1.676
ores+1.659
Neg logit contributions
agine-1.594
ttp-1.494
 balloons-1.405
mingham-1.397
VERTISEMENT-1.358
Token a
Token ID257
Feature activation+2.91e-01

Pos logit contributions
ature+1.609
onduct+1.572
arten+1.517
=]+1.496
ores+1.484
Neg logit contributions
agine-1.506
ttp-1.416
 balloons-1.330
mingham-1.326
VERTISEMENT-1.291
Token spot
Token ID4136
Feature activation-2.88e-01

Pos logit contributions
ature+2.381
onduct+2.319
arten+2.235
=]+2.210
ores+2.201
Neg logit contributions
agine-2.151
ttp-2.019
mingham-1.891
 balloons-1.888
VERTISEMENT-1.837
Token
Token ID198
Feature activation-5.10e-01

Pos logit contributions
agine+0.011
ttp+0.010
 balloons+0.010
mingham+0.010
VERTISEMENT+0.009
Neg logit contributions
ature-0.011
onduct-0.011
arten-0.011
=]-0.011
ores-0.011
Token
Token ID198
Feature activation-8.42e-01

Pos logit contributions
agine+3.317
ttp+3.157
 balloons+2.909
mingham+2.864
 FB+2.824
Neg logit contributions
ature-4.398
onduct-4.396
arten-4.223
arella-4.139
ores-4.130
TokenFlag
Token ID34227
Feature activation-2.73e-01

Pos logit contributions
agine+2.893
ttp+2.877
mingham+2.358
VERTISEMENT+2.163
 balloons+2.155
Neg logit contributions
onduct-9.423
arella-9.200
ature-9.198
arten-9.101
 Shiv-9.056
Token Reply
Token ID14883
Feature activation-1.08e-01

Pos logit contributions
agine+2.054
ttp+1.932
 balloons+1.832
mingham+1.818
 FB+1.775
Neg logit contributions
ature-2.135
onduct-2.118
arten-2.051
=]-2.009
arella-2.006
Token
Token ID198
Feature activation-6.09e-01

Pos logit contributions
agine+0.812
ttp+0.765
 balloons+0.717
mingham+0.711
VERTISEMENT+0.688
Neg logit contributions
ature-0.858
onduct-0.844
arten-0.813
=]-0.800
ores-0.796
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
agine+3.771
ttp+3.591
 balloons+3.281
 FB+3.233
mingham+3.201
Neg logit contributions
onduct-5.375
ature-5.350
arten-5.158
arella-5.102
ores-5.045
Token27
Token ID1983
Feature activation-1.05e-01

Pos logit contributions
ttp+6.090
agine+6.024
 FB+5.221
VERTISEMENT+5.174
 balloons+5.123
Neg logit contributions
onduct-10.715
arella-10.416
arten-10.332
ature-10.196
ores-9.953
Token Recommend
Token ID30361
Feature activation+5.81e-02

Pos logit contributions
agine+0.632
ttp+0.586
 balloons+0.538
mingham+0.534
VERTISEMENT+0.524
Neg logit contributions
ature-0.986
onduct-0.978
arten-0.952
=]-0.930
arella-0.927
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
ature+0.448
onduct+0.438
arten+0.422
=]+0.415
ores+0.412
Neg logit contributions
agine-0.455
ttp-0.429
 balloons-0.404
mingham-0.403
VERTISEMENT-0.392
Token
Token ID198
Feature activation-5.87e-01

Pos logit contributions
agine+1.682
ttp+1.595
 balloons+1.486
mingham+1.467
 FB+1.417
Neg logit contributions
ature-1.933
onduct-1.921
arten-1.847
=]-1.809
ores-1.802
TokenRecommend
Token ID41248
Feature activation-9.30e-02

Pos logit contributions
agine+3.039
ttp+2.940
VERTISEMENT+2.536
mingham+2.445
 balloons+2.389
Neg logit contributions
onduct-5.754
ature-5.637
arten-5.602
arella-5.489
 Shiv-5.444
Token Europe
Token ID2031
Feature activation-4.02e-01

Pos logit contributions
agine+2.566
ttp+2.383
 balloons+2.335
mingham+2.250
 FB+2.226
Neg logit contributions
ature-2.791
onduct-2.762
arten-2.651
=]-2.633
arella-2.561
Token had
Token ID550
Feature activation-5.39e-01

Pos logit contributions
agine+2.785
ttp+2.531
 balloons+2.477
mingham+2.374
VERTISEMENT+2.343
Neg logit contributions
ature-3.338
onduct-3.299
=]-3.252
arten-3.216
 Shiv-3.138
Token for
Token ID329
Feature activation-7.31e-01

Pos logit contributions
agine+3.824
 balloons+3.518
ttp+3.449
mingham+3.342
VERTISEMENT+3.271
Neg logit contributions
onduct-4.310
ature-4.285
=]-4.167
arten-4.144
arella-4.018
Token the
Token ID262
Feature activation-5.43e-01

Pos logit contributions
agine+5.131
ttp+4.627
 balloons+4.523
mingham+4.389
VERTISEMENT+4.331
Neg logit contributions
ature-5.689
onduct-5.675
arten-5.528
=]-5.440
 Shiv-5.337
Token first
Token ID717
Feature activation-4.54e-01

Pos logit contributions
agine+3.219
 balloons+2.828
ttp+2.822
mingham+2.692
 FB+2.542
Neg logit contributions
ature-5.100
onduct-4.986
arten-4.860
=]-4.792
arella-4.708
Token time
Token ID640
Feature activation-1.44e+00

Pos logit contributions
agine+3.931
ttp+3.689
 balloons+3.577
mingham+3.481
VERTISEMENT+3.411
Neg logit contributions
onduct-3.029
ature-2.981
arten-2.899
=]-2.790
arella-2.760
Token come
Token ID1282
Feature activation-6.75e-01

Pos logit contributions
agine+8.760
 balloons+8.325
mingham+7.537
ttp+7.466
 FB+7.390
Neg logit contributions
onduct-11.091
arten-10.908
ature-10.851
=]-10.811
arella-10.361
Token to
Token ID284
Feature activation-1.43e-02

Pos logit contributions
agine+4.543
ttp+4.022
 balloons+3.992
mingham+3.902
cknowled+3.734
Neg logit contributions
onduct-5.590
arten-5.539
ature-5.511
=]-5.402
 Shiv-5.211
Token systematically
Token ID25735
Feature activation-1.65e-01

Pos logit contributions
agine+0.109
ttp+0.101
 balloons+0.096
mingham+0.095
VERTISEMENT+0.092
Neg logit contributions
ature-0.114
onduct-0.112
arten-0.108
=]-0.106
ores-0.105
Token compare
Token ID8996
Feature activation-3.36e-01

Pos logit contributions
agine+1.295
ttp+1.182
 balloons+1.154
mingham+1.128
cknowled+1.095
Neg logit contributions
ature-1.268
onduct-1.244
arten-1.206
=]-1.194
arella-1.164
Token the
Token ID262
Feature activation+9.21e-02

Pos logit contributions
agine+2.576
ttp+2.388
 balloons+2.322
mingham+2.224
 FB+2.221
Neg logit contributions
ature-2.599
onduct-2.568
arten-2.479
=]-2.444
ores-2.373