TOP ACTIVATIONS
MAX = 1.855

out at http :// w ashington beer . com / w
nearly five days after the f ission process was stopped ,
mar Berg man , and F . Scott Fitzgerald .
one issued on Wednesday by F itch Ratings .
about a place with " f ir kin " in the
Z Y BE AR and F ANC Y BE AR for
talk THE FANT AST IC F OUR ! Follow
list , r ah in ah ib rahim , r ai
- February 9 , 2010 R ipe for M ST 3
- Time Strategy - Rated : Everyone H omew
I can re - watch F ars cape . ( Just
him . <|endoftext|> S AC RAM ENT O Thousands of
roph ages at the site of inoc ulation and lymph nodes
Boston . ( Wa ub ges hig Rice / CBC )
Ad elson - funded Washington Free Beacon leading the charge ,
of Alabama at Birmingham School of Medicine . Views expressed are
t believe the citizens of F ayette ville would want males
assing , or simply allowed to drift out . This was
Memory 4 66 284 4 64 406 Mem c py Reading
Gov . Robert F . McDonnell ( R )

MIN ACTIVATIONS
MIN = -1.396

beats other vendors by leaps and bounds . There are custom
will receive occasional promotional offers for programs that support The Nation
9 Russian Federation 18 . 7 10 United Arab Emirates 19
the Token , you cannot Normal or Special Summon monsters ,
x . x . x . 85 114 16 21 x
original image from disk and res izes it to have a
a 2 . 5 per cent increase in the first year
reached a preliminary understanding to normal ize relations , including the
removed and turn the V itus into a fixed gear bike
international treaties . Any reproduction , copying , or redistribution (
said she risked severe infection and scar ring if she didn
to fully enter the fast ed state . When
number of steps planned to normal ize relations .
. x . x . 80 106 27 66 x .
of a missing 1982 V itus road bike .
chooses to go alone to Mord or , but Sam guesses
s weak coalition of Social Democrats and Greens , and
and shudder . [ 19 ] Myth os became
K AND AP AC HE T OC RE P ORTS 100
are getting less than the recommended 8 1 / 2 to

INTERVAL 1.042 - 1.855
CONTAINS 0.027%

Pre y ." " Rating : 9 / 10 "
unstable and like a house of cards can come crashing down
Sign Up : Stay on top of the latest
says , the state Board of Equal ization slapped a l
Game Spot gave the game a ' Ter rible ' score

INTERVAL 0.230 - 1.042
CONTAINS 17.274%

ing . rect angle f ( 0 , 0 , ($
Project DI va X update is in . S
members . But with a change to its policies at the
on the other end of the phone . This is certainly
, Today independent of appearance , genital ia

INTERVAL -0.583 - 0.230
CONTAINS 81.338%

matters most in geop olitics it is plain to see
. This is one area where Power BI beats other vendors
from the top . I took pictures of where I pri
of Trump that there s a grown - up
own the game and have a broadband Internet connection can play

INTERVAL -1.396 - -0.583
CONTAINS 1.361%

of our old Pont iac Bon ne ville . Sally Ye
H ints on Et iquette and the Us
cv 2 . M OR PH _ RECT , ( 21
de coup d ' E t at , les mut ins
ve believed in faith that something was going to happen ,
Token out
Token ID503
Feature activation+2.49e-01

Pos logit contributions
icult+0.709
orm+0.689
+0.685
awar+0.672
Dub+0.663
Neg logit contributions
 Nose-0.847
aspers-0.833
ertodd-0.818
 bluff-0.805
itiz-0.801
Token at
Token ID379
Feature activation+1.32e-01

Pos logit contributions
 Nose+2.052
aspers+1.986
 bluff+1.931
itiz+1.917
ertodd+1.915
Neg logit contributions
icult-2.334
awar-2.247
orm-2.245
-2.233
Dub-2.198
Token http
Token ID2638
Feature activation-1.85e-01

Pos logit contributions
 Nose+1.228
aspers+1.193
 bluff+1.166
ertodd+1.162
   +1.153
Neg logit contributions
icult-1.103
orm-1.063
awar-1.053
-1.048
nown-1.029
Token://
Token ID1378
Feature activation+2.29e-01

Pos logit contributions
icult+1.182
orm+1.181
+1.152
aj+1.148
Dub+1.128
Neg logit contributions
 Nose-2.058
aspers-2.036
ertodd-2.016
 bluff-2.011
itiz-1.961
Tokenw
Token ID86
Feature activation+1.58e-01

Pos logit contributions
 Nose+1.836
aspers+1.818
itiz+1.773
ertodd+1.759
 bluff+1.735
Neg logit contributions
icult-2.155
-2.078
orm-2.069
awar-2.047
 iceberg-2.047
Tokenashington
Token ID2542
Feature activation+1.85e+00

Pos logit contributions
aspers+1.621
 Nose+1.608
ertodd+1.562
itiz+1.560
 bluff+1.556
Neg logit contributions
icult-1.147
-1.124
orm-1.087
 iceberg-1.082
awar-1.079
Tokenbeer
Token ID42428
Feature activation+2.03e-01

Pos logit contributions
itiz+12.161
aspers+11.792
irts+11.405
cle+11.334
ethe+11.246
Neg logit contributions
 Jinn-14.020
 Asgard-13.972
-13.690
 Hallow-13.685
 iceberg-13.100
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
 Nose+1.497
aspers+1.480
ertodd+1.433
itiz+1.429
 bluff+1.420
Neg logit contributions
icult-2.038
-2.009
awar-1.960
orm-1.952
 Asgard-1.945
Tokencom
Token ID785
Feature activation+1.49e-01

Pos logit contributions
icult+1.754
orm+1.710
awar+1.670
+1.657
aj+1.652
Neg logit contributions
 Nose-2.089
aspers-2.042
ertodd-1.997
 bluff-1.989
   -1.962
Token/
Token ID14
Feature activation-3.26e-02

Pos logit contributions
 Nose+1.269
aspers+1.231
 bluff+1.194
ertodd+1.191
   +1.188
Neg logit contributions
icult-1.368
orm-1.319
awar-1.310
-1.304
Dub-1.291
Tokenw
Token ID86
Feature activation+3.65e-02

Pos logit contributions
icult+0.295
orm+0.287
+0.284
awar+0.282
Dub+0.278
Neg logit contributions
 Nose-0.281
aspers-0.275
ertodd-0.268
 bluff-0.266
itiz-0.264
Token nearly
Token ID3016
Feature activation-5.72e-02

Pos logit contributions
icult+0.586
orm+0.569
+0.560
awar+0.560
aj+0.549
Neg logit contributions
 Nose-0.640
aspers-0.627
ertodd-0.615
 bluff-0.605
itiz-0.605
Token five
Token ID1936
Feature activation+1.70e-01

Pos logit contributions
icult+0.481
orm+0.469
+0.459
awar+0.459
Dub+0.452
Neg logit contributions
 Nose-0.527
aspers-0.520
ertodd-0.508
 bluff-0.500
itiz-0.499
Token days
Token ID1528
Feature activation-4.10e-01

Pos logit contributions
 Nose+1.538
aspers+1.501
 bluff+1.476
ertodd+1.458
itiz+1.458
Neg logit contributions
icult-1.454
-1.402
orm-1.389
awar-1.380
nown-1.371
Token after
Token ID706
Feature activation+3.56e-01

Pos logit contributions
icult+3.060
orm+3.053
 iceberg+2.964
awar+2.959
+2.958
Neg logit contributions
 Nose-4.059
ertodd-3.979
aspers-3.978
 bluff-3.784
itiz-3.781
Token the
Token ID262
Feature activation+2.01e-01

Pos logit contributions
 Nose+2.747
aspers+2.585
   +2.568
 bluff+2.559
itiz+2.521
Neg logit contributions
icult-3.540
-3.400
orm-3.382
awar-3.354
nown-3.320
Token f
Token ID277
Feature activation+1.69e+00

Pos logit contributions
 Nose+1.610
aspers+1.537
 bluff+1.516
   +1.491
ertodd+1.487
Neg logit contributions
icult-1.974
-1.906
orm-1.900
awar-1.874
nown-1.855
Tokenission
Token ID1480
Feature activation+3.47e-01

Pos logit contributions
irts+10.170
ath+10.083
cle+9.952
   +9.757
lier+9.706
Neg logit contributions
-15.526
 lett-14.836
luaj-14.476
nown-14.143
 Bulg-13.806
Token process
Token ID1429
Feature activation+5.98e-02

Pos logit contributions
 Nose+2.992
aspers+2.874
 bluff+2.862
   +2.835
ertodd+2.792
Neg logit contributions
icult-3.124
-3.053
orm-2.987
awar-2.960
Dub-2.952
Token was
Token ID373
Feature activation+2.04e-02

Pos logit contributions
 Nose+0.543
aspers+0.532
ertodd+0.518
 bluff+0.516
itiz+0.512
Neg logit contributions
icult-0.514
orm-0.498
-0.493
awar-0.490
Dub-0.482
Token stopped
Token ID5025
Feature activation+1.89e-01

Pos logit contributions
 Nose+0.185
aspers+0.182
ertodd+0.177
 bluff+0.175
itiz+0.175
Neg logit contributions
icult-0.175
orm-0.171
awar-0.168
-0.167
Dub-0.165
Token,
Token ID11
Feature activation-3.77e-02

Pos logit contributions
 Nose+1.563
aspers+1.520
 bluff+1.480
ertodd+1.470
   +1.462
Neg logit contributions
icult-1.769
-1.705
orm-1.703
awar-1.693
Dub-1.672
Tokenmar
Token ID3876
Feature activation+1.49e-01

Pos logit contributions
icult+1.734
orm+1.723
aj+1.645
awar+1.644
Dub+1.625
Neg logit contributions
 Nose-2.006
ertodd-1.976
aspers-1.970
 bluff-1.932
itiz-1.906
Token Berg
Token ID24626
Feature activation+9.69e-02

Pos logit contributions
 Nose+1.130
aspers+1.099
 bluff+1.055
ertodd+1.048
   +1.041
Neg logit contributions
icult-1.505
orm-1.461
awar-1.458
-1.456
nown-1.431
Tokenman
Token ID805
Feature activation+2.11e-02

Pos logit contributions
 Nose+0.827
aspers+0.818
 bluff+0.782
ertodd+0.780
itiz+0.780
Neg logit contributions
icult-0.881
awar-0.850
orm-0.848
-0.847
nown-0.833
Token,
Token ID11
Feature activation-1.05e-01

Pos logit contributions
 Nose+0.171
aspers+0.167
ertodd+0.161
 bluff+0.160
itiz+0.160
Neg logit contributions
icult-0.202
orm-0.195
awar-0.195
-0.195
Dub-0.191
Token and
Token ID290
Feature activation+1.29e-01

Pos logit contributions
icult+0.884
orm+0.857
+0.846
awar+0.841
Dub+0.829
Neg logit contributions
 Nose-0.965
aspers-0.947
ertodd-0.927
 bluff-0.919
itiz-0.913
Token F
Token ID376
Feature activation+1.45e+00

Pos logit contributions
 Nose+1.206
aspers+1.171
 bluff+1.143
   +1.130
itiz+1.129
Neg logit contributions
icult-1.084
orm-1.043
awar-1.041
-1.041
nown-1.016
Token.
Token ID13
Feature activation+4.34e-01

Pos logit contributions
 Nose+12.916
aspers+12.724
irts+12.309
itiz+12.255
ath+12.108
Neg logit contributions
luaj-9.499
 Asgard-9.006
icult-8.658
 lett-8.654
Dub-8.586
Token Scott
Token ID4746
Feature activation+3.79e-02

Pos logit contributions
 Nose+4.149
aspers+3.920
 bluff+3.910
   +3.888
itiz+3.796
Neg logit contributions
icult-3.549
-3.410
nown-3.407
awar-3.385
orm-3.364
Token Fitzgerald
Token ID28397
Feature activation-4.07e-02

Pos logit contributions
 Nose+0.404
aspers+0.395
 bluff+0.385
itiz+0.384
   +0.384
Neg logit contributions
icult-0.267
-0.256
orm-0.255
awar-0.253
nown-0.249
Token.
Token ID13
Feature activation+1.78e-02

Pos logit contributions
icult+0.394
orm+0.382
+0.380
awar+0.378
Dub+0.372
Neg logit contributions
 Nose-0.327
aspers-0.319
ertodd-0.309
 bluff-0.308
itiz-0.306
Token
Token ID198
Feature activation+1.78e-01

Pos logit contributions
 Nose+0.165
aspers+0.162
ertodd+0.158
 bluff+0.157
itiz+0.156
Neg logit contributions
icult-0.150
orm-0.145
-0.143
awar-0.143
Dub-0.140
Token one
Token ID530
Feature activation+2.45e-01

Pos logit contributions
 Nose+1.663
aspers+1.591
 bluff+1.577
ertodd+1.553
itiz+1.547
Neg logit contributions
icult-1.727
-1.670
orm-1.669
awar-1.655
nown-1.628
Token issued
Token ID4884
Feature activation+1.34e-01

Pos logit contributions
 Nose+2.071
aspers+1.991
 bluff+1.978
itiz+1.943
ertodd+1.938
Neg logit contributions
icult-2.263
-2.203
orm-2.184
awar-2.172
nown-2.145
Token on
Token ID319
Feature activation+2.05e-01

Pos logit contributions
 Nose+1.149
aspers+1.124
 bluff+1.102
ertodd+1.091
itiz+1.085
Neg logit contributions
icult-1.219
orm-1.175
-1.170
awar-1.163
Dub-1.143
Token Wednesday
Token ID3583
Feature activation-1.28e-01

Pos logit contributions
 Nose+1.695
aspers+1.627
 bluff+1.607
ertodd+1.580
itiz+1.578
Neg logit contributions
icult-1.949
orm-1.883
-1.872
awar-1.854
nown-1.831
Token by
Token ID416
Feature activation+2.23e-01

Pos logit contributions
icult+1.120
orm+1.089
+1.072
awar+1.070
aj+1.058
Neg logit contributions
 Nose-1.132
aspers-1.113
ertodd-1.084
 bluff-1.066
   -1.065
Token F
Token ID376
Feature activation+1.45e+00

Pos logit contributions
 Nose+1.973
aspers+1.883
 bluff+1.832
itiz+1.825
ertodd+1.821
Neg logit contributions
icult-2.000
-1.943
orm-1.941
awar-1.916
nown-1.888
Tokenitch
Token ID2007
Feature activation-2.61e-01

Pos logit contributions
itiz+8.771
aspers+8.413
 Nose+8.261
ath+7.657
irts+7.493
Neg logit contributions
luaj-13.787
 Jinn-13.505
 Asgard-13.353
 Bulg-13.261
 Gutenberg-13.085
Token Ratings
Token ID36826
Feature activation-4.83e-01

Pos logit contributions
icult+2.432
orm+2.357
awar+2.320
aj+2.291
+2.277
Neg logit contributions
 Nose-2.157
aspers-2.132
ertodd-2.122
 bluff-2.073
   -2.052
Token.
Token ID13
Feature activation-1.86e-01

Pos logit contributions
icult+3.985
orm+3.933
aj+3.827
awar+3.805
 Asgard+3.754
Neg logit contributions
 Nose-4.279
aspers-4.253
ertodd-4.240
 bluff-4.136
   -4.100
Token
Token ID198
Feature activation-7.99e-03

Pos logit contributions
icult+1.670
orm+1.623
+1.602
awar+1.595
Dub+1.575
Neg logit contributions
 Nose-1.604
aspers-1.576
ertodd-1.532
 bluff-1.528
itiz-1.513
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
icult+0.065
orm+0.064
Dub+0.062
aj+0.062
awar+0.062
Neg logit contributions
 Nose-0.075
aspers-0.075
ertodd-0.073
 bluff-0.073
itiz-0.072
Token about
Token ID546
Feature activation+1.80e-01

Pos logit contributions
 Nose+0.866
aspers+0.844
 bluff+0.825
ertodd+0.816
itiz+0.808
Neg logit contributions
icult-0.956
orm-0.923
-0.923
awar-0.917
nown-0.899
Token a
Token ID257
Feature activation+4.01e-01

Pos logit contributions
 Nose+1.582
aspers+1.504
 bluff+1.497
itiz+1.472
   +1.460
Neg logit contributions
icult-1.629
orm-1.572
-1.562
awar-1.554
nown-1.542
Token place
Token ID1295
Feature activation-1.67e-01

Pos logit contributions
 Nose+3.525
 bluff+3.343
aspers+3.335
itiz+3.287
   +3.208
Neg logit contributions
icult-3.569
nown-3.440
awar-3.436
-3.427
orm-3.414
Token with
Token ID351
Feature activation-1.33e-01

Pos logit contributions
icult+1.441
orm+1.406
awar+1.378
+1.374
Dub+1.364
Neg logit contributions
 Nose-1.476
aspers-1.463
ertodd-1.435
 bluff-1.404
   -1.398
Token "
Token ID366
Feature activation+1.24e-01

Pos logit contributions
icult+1.175
orm+1.149
+1.124
awar+1.123
 iceberg+1.116
Neg logit contributions
 Nose-1.158
aspers-1.145
ertodd-1.123
 bluff-1.097
itiz-1.094
Tokenf
Token ID69
Feature activation+1.45e+00

Pos logit contributions
 Nose+1.033
aspers+1.023
itiz+0.979
 bluff+0.979
ertodd+0.973
Neg logit contributions
icult-1.150
-1.108
orm-1.106
awar-1.104
nown-1.084
Tokenir
Token ID343
Feature activation+4.37e-02

Pos logit contributions
lier+10.296
irts+10.226
aspers+10.210
itiz+10.160
 Nose+9.883
Neg logit contributions
-11.760
 Asgard-11.473
 Jinn-11.316
luaj-11.110
 Ames-10.988
Tokenkin
Token ID5116
Feature activation+2.15e-01

Pos logit contributions
 Nose+0.487
aspers+0.477
 bluff+0.469
ertodd+0.466
itiz+0.466
Neg logit contributions
icult-0.280
-0.270
orm-0.268
awar-0.264
Dub-0.262
Token"
Token ID1
Feature activation+1.91e-01

Pos logit contributions
 Nose+1.822
aspers+1.770
 bluff+1.721
itiz+1.700
   +1.677
Neg logit contributions
icult-1.979
-1.922
awar-1.899
orm-1.897
nown-1.885
Token in
Token ID287
Feature activation+4.40e-01

Pos logit contributions
 Nose+1.700
aspers+1.649
 bluff+1.611
itiz+1.596
ertodd+1.589
Neg logit contributions
icult-1.687
orm-1.614
-1.611
awar-1.600
nown-1.583
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
 Nose+3.364
itiz+3.170
aspers+3.160
 bluff+3.141
   +3.055
Neg logit contributions
icult-4.449
nown-4.227
-4.224
orm-4.212
awar-4.210
TokenZ
Token ID57
Feature activation+3.80e-01

Pos logit contributions
aspers+4.002
 Nose+3.904
 bluff+3.757
   +3.680
ertodd+3.668
Neg logit contributions
icult-3.862
awar-3.709
-3.623
orm-3.581
 iceberg-3.556
TokenY
Token ID56
Feature activation+3.78e-01

Pos logit contributions
 Nose+3.496
aspers+3.428
 bluff+3.279
   +3.224
itiz+3.224
Neg logit contributions
icult-3.257
awar-3.088
-3.056
orm-3.033
nown-3.017
Token BE
Token ID9348
Feature activation+1.65e-01

Pos logit contributions
 Nose+3.308
aspers+3.227
 bluff+3.122
ertodd+3.023
   +3.020
Neg logit contributions
icult-3.416
-3.237
awar-3.232
orm-3.231
nown-3.193
TokenAR
Token ID1503
Feature activation-1.16e-02

Pos logit contributions
 Nose+1.524
aspers+1.492
 bluff+1.434
itiz+1.431
   +1.430
Neg logit contributions
icult-1.412
orm-1.339
awar-1.327
-1.321
nown-1.317
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
icult+0.103
orm+0.100
+0.099
awar+0.099
nown+0.097
Neg logit contributions
 Nose-0.103
aspers-0.100
ertodd-0.097
 bluff-0.097
itiz-0.096
Token F
Token ID376
Feature activation+1.44e+00

Pos logit contributions
 Nose+1.346
aspers+1.310
 bluff+1.270
ertodd+1.257
   +1.254
Neg logit contributions
icult-1.343
-1.287
orm-1.287
awar-1.272
nown-1.256
TokenANC
Token ID20940
Feature activation-1.41e-01

Pos logit contributions
aspers+12.381
 Nose+11.773
irts+11.232
lier+11.146
ath+11.143
Neg logit contributions
icult-9.779
 lett-9.522
 Jinn-9.476
luaj-9.431
 iceberg-9.273
TokenY
Token ID56
Feature activation+4.09e-01

Pos logit contributions
icult+0.619
orm+0.584
+0.570
awar+0.564
Dub+0.547
Neg logit contributions
 Nose-1.869
aspers-1.844
ertodd-1.814
 bluff-1.807
itiz-1.798
Token BE
Token ID9348
Feature activation+2.96e-01

Pos logit contributions
 Nose+3.321
aspers+3.185
 bluff+3.097
   +3.009
ertodd+2.985
Neg logit contributions
icult-3.952
-3.757
orm-3.731
awar-3.706
nown-3.679
TokenAR
Token ID1503
Feature activation-8.53e-03

Pos logit contributions
 Nose+2.804
aspers+2.727
   +2.641
 bluff+2.628
ertodd+2.574
Neg logit contributions
icult-2.464
orm-2.296
-2.276
nown-2.272
awar-2.258
Token for
Token ID329
Feature activation+3.01e-01

Pos logit contributions
icult+0.081
orm+0.078
+0.078
awar+0.078
Dub+0.076
Neg logit contributions
 Nose-0.071
aspers-0.069
ertodd-0.067
 bluff-0.067
itiz-0.066
Token talk
Token ID1561
Feature activation+2.96e-01

Pos logit contributions
 Nose+0.530
aspers+0.519
 bluff+0.506
ertodd+0.505
itiz+0.501
Neg logit contributions
icult-0.483
orm-0.466
-0.461
awar-0.459
nown-0.453
Token THE
Token ID3336
Feature activation-1.10e-02

Pos logit contributions
 Nose+2.575
aspers+2.460
 bluff+2.453
   +2.411
itiz+2.405
Neg logit contributions
icult-2.684
orm-2.553
awar-2.538
-2.530
nown-2.521
Token FANT
Token ID29250
Feature activation+3.67e-01

Pos logit contributions
icult+0.096
orm+0.093
+0.092
awar+0.091
nown+0.090
Neg logit contributions
 Nose-0.099
aspers-0.097
ertodd-0.094
 bluff-0.094
itiz-0.093
TokenAST
Token ID11262
Feature activation-4.26e-02

Pos logit contributions
 Nose+2.220
aspers+2.131
   +2.030
 bluff+1.996
ertodd+1.992
Neg logit contributions
icult-4.138
-4.050
nown-4.032
awar-3.996
 iceberg-3.974
TokenIC
Token ID2149
Feature activation+3.76e-01

Pos logit contributions
icult+0.335
orm+0.324
+0.320
awar+0.318
Dub+0.313
Neg logit contributions
 Nose-0.418
aspers-0.410
ertodd-0.401
 bluff-0.399
itiz-0.396
Token F
Token ID376
Feature activation+1.41e+00

Pos logit contributions
 Nose+3.307
aspers+3.151
 bluff+3.137
   +3.102
itiz+3.101
Neg logit contributions
icult-3.319
awar-3.187
-3.166
nown-3.141
orm-3.090
TokenOUR
Token ID11698
Feature activation+2.40e-01

Pos logit contributions
 Nose+9.931
   +9.735
aspers+9.490
irts+9.317
·+9.149
Neg logit contributions
luaj-11.565
icult-11.424
 lett-11.388
nown-11.227
awar-11.055
Token!
Token ID0
Feature activation+1.31e-01

Pos logit contributions
 Nose+2.098
aspers+2.013
 bluff+1.988
   +1.969
ertodd+1.944
Neg logit contributions
icult-2.140
orm-2.051
awar-2.050
-2.046
nown-2.015
Token
Token ID198
Feature activation-9.69e-02

Pos logit contributions
 Nose+0.997
aspers+0.956
ertodd+0.933
   +0.930
 bluff+0.929
Neg logit contributions
icult-1.324
orm-1.272
awar-1.263
-1.263
nown-1.250
Token
Token ID198
Feature activation-2.96e-02

Pos logit contributions
icult+0.751
orm+0.747
aj+0.730
Dub+0.730
awar+0.723
Neg logit contributions
aspers-0.940
 Nose-0.938
ertodd-0.919
 bluff-0.910
itiz-0.897
TokenFollow
Token ID7155
Feature activation-2.40e-01

Pos logit contributions
icult+0.268
orm+0.260
+0.257
awar+0.256
Dub+0.252
Neg logit contributions
 Nose-0.255
aspers-0.250
ertodd-0.243
 bluff-0.242
itiz-0.240
Token list
Token ID1351
Feature activation-7.11e-02

Pos logit contributions
 Nose+4.232
 bluff+4.094
itiz+4.078
aspers+4.034
ertodd+3.939
Neg logit contributions
icult-5.469
-5.302
awar-5.159
nown-5.158
orm-5.130
Token,
Token ID11
Feature activation-2.22e-01

Pos logit contributions
icult+0.669
orm+0.650
+0.644
awar+0.641
Dub+0.631
Neg logit contributions
 Nose-0.588
aspers-0.575
ertodd-0.559
 bluff-0.556
itiz-0.552
Token r
Token ID374
Feature activation+5.10e-01

Pos logit contributions
icult+1.879
orm+1.837
awar+1.806
+1.795
Dub+1.785
Neg logit contributions
 Nose-1.980
aspers-1.970
ertodd-1.932
itiz-1.889
 bluff-1.884
Tokenah
Token ID993
Feature activation+3.84e-01

Pos logit contributions
 Nose+5.400
aspers+5.366
 bluff+5.256
itiz+5.250
   +5.077
Neg logit contributions
icult-3.347
-3.328
awar-3.181
orm-3.151
Dub-3.108
Tokenin
Token ID259
Feature activation+6.53e-01

Pos logit contributions
 Nose+3.525
aspers+3.460
itiz+3.450
ertodd+3.392
 bluff+3.355
Neg logit contributions
-3.091
icult-3.042
 Asgard-2.883
 lett-2.880
orm-2.871
Tokenah
Token ID993
Feature activation+1.40e+00

Pos logit contributions
itiz+4.300
 Nose+4.281
aspers+4.177
 bluff+4.100
ertodd+4.053
Neg logit contributions
icult-6.581
-6.454
Dub-6.440
nown-6.295
 Asgard-6.282
Token ib
Token ID24283
Feature activation+2.97e-01

Pos logit contributions
 Nose+10.057
 bluff+9.975
aspers+9.851
itiz+9.837
ertodd+9.627
Neg logit contributions
icult-10.881
-10.541
 Bulg-10.267
 Wol-10.263
orm-10.259
Tokenrahim
Token ID26922
Feature activation+6.76e-02

Pos logit contributions
 Nose+2.065
aspers+2.013
itiz+1.957
 bluff+1.945
   +1.915
Neg logit contributions
-3.103
icult-3.096
orm-3.046
 iceberg-2.966
Dub-2.966
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
 Nose+0.530
aspers+0.511
ertodd+0.499
 bluff+0.498
itiz+0.493
Neg logit contributions
icult-0.669
orm-0.648
-0.643
awar-0.641
nown-0.635
Token r
Token ID374
Feature activation+2.14e-01

Pos logit contributions
icult+1.004
orm+0.979
awar+0.965
+0.963
Dub+0.950
Neg logit contributions
 Nose-1.010
aspers-1.000
ertodd-0.978
 bluff-0.961
itiz-0.959
Tokenai
Token ID1872
Feature activation+6.18e-01

Pos logit contributions
 Nose+2.360
aspers+2.336
 bluff+2.279
itiz+2.279
ertodd+2.270
Neg logit contributions
icult-1.390
-1.352
orm-1.317
Dub-1.292
awar-1.291
Token -
Token ID532
Feature activation-4.08e-02

Pos logit contributions
 Nose+3.550
aspers+3.267
   +3.265
 bluff+3.174
itiz+3.145
Neg logit contributions
icult-3.838
orm-3.682
-3.677
awar-3.663
nown-3.636
Token February
Token ID3945
Feature activation-2.70e-01

Pos logit contributions
icult+0.323
orm+0.318
awar+0.315
Dub+0.313
+0.307
Neg logit contributions
 Nose-0.389
aspers-0.389
ertodd-0.379
itiz-0.377
 bluff-0.374
Token 9
Token ID860
Feature activation-1.30e-01

Pos logit contributions
icult+1.069
orm+1.051
aj+1.026
 Wol+0.978
awar+0.978
Neg logit contributions
aspers-3.613
ertodd-3.595
 Nose-3.545
 bluff-3.496
��-3.465
Token,
Token ID11
Feature activation-6.73e-03

Pos logit contributions
icult+1.058
orm+1.046
Dub+1.030
aj+1.029
+1.012
Neg logit contributions
aspers-1.217
 Nose-1.211
ertodd-1.196
 bluff-1.175
itiz-1.154
Token 2010
Token ID3050
Feature activation+3.31e-01

Pos logit contributions
icult+0.064
orm+0.062
awar+0.062
+0.062
Dub+0.061
Neg logit contributions
aspers-0.054
 Nose-0.053
ertodd-0.052
 bluff-0.051
itiz-0.051
TokenR
Token ID49
Feature activation+1.40e+00

Pos logit contributions
 Nose+2.517
aspers+2.470
   +2.394
itiz+2.372
ertodd+2.346
Neg logit contributions
icult-3.308
awar-3.174
orm-3.153
-3.141
 iceberg-3.138
Tokenipe
Token ID3757
Feature activation+3.45e-01

Pos logit contributions
itiz+6.013
aspers+5.846
 Nose+5.679
 bluff+5.287
cle+5.279
Neg logit contributions
-16.599
 Asgard-16.034
 Jinn-15.902
icult-15.864
 lett-15.833
Token for
Token ID329
Feature activation-4.90e-01

Pos logit contributions
 Nose+2.657
 bluff+2.508
   +2.480
aspers+2.450
ertodd+2.448
Neg logit contributions
icult-3.346
awar-3.285
-3.250
orm-3.215
 iceberg-3.183
Token M
Token ID337
Feature activation-4.45e-02

Pos logit contributions
icult+4.579
orm+4.527
+4.431
awar+4.411
aj+4.388
Neg logit contributions
 Nose-3.846
aspers-3.839
ertodd-3.750
 bluff-3.691
itiz-3.673
TokenST
Token ID2257
Feature activation+4.39e-02

Pos logit contributions
icult+0.375
orm+0.373
+0.363
Dub+0.358
aj+0.358
Neg logit contributions
 Nose-0.414
aspers-0.398
ertodd-0.395
 bluff-0.394
itiz-0.385
Token3
Token ID18
Feature activation-2.93e-01

Pos logit contributions
 Nose+0.391
aspers+0.381
ertodd+0.375
 bluff+0.371
itiz+0.367
Neg logit contributions
icult-0.384
orm-0.380
-0.370
awar-0.367
Dub-0.367
Token-
Token ID12
Feature activation-3.68e-01

Pos logit contributions
icult+1.455
orm+1.413
awar+1.386
+1.384
Dub+1.374
Neg logit contributions
 Nose-1.578
aspers-1.569
ertodd-1.537
 bluff-1.510
   -1.498
TokenTime
Token ID7575
Feature activation-3.10e-02

Pos logit contributions
icult+2.813
orm+2.756
Dub+2.697
awar+2.671
+2.665
Neg logit contributions
 Nose-3.573
aspers-3.564
ertodd-3.556
 bluff-3.435
itiz-3.431
Token Strategy
Token ID20561
Feature activation+3.02e-02

Pos logit contributions
icult+0.210
orm+0.202
awar+0.198
+0.198
Dub+0.194
Neg logit contributions
 Nose-0.337
aspers-0.334
ertodd-0.327
 bluff-0.323
itiz-0.323
Token -
Token ID532
Feature activation+6.44e-02

Pos logit contributions
 Nose+0.271
aspers+0.265
ertodd+0.258
 bluff+0.258
itiz+0.256
Neg logit contributions
icult-0.262
orm-0.254
-0.252
awar-0.250
nown-0.246
Token Rated
Token ID49949
Feature activation+3.11e-01

Pos logit contributions
 Nose+0.607
aspers+0.591
 bluff+0.577
ertodd+0.574
itiz+0.570
Neg logit contributions
icult-0.534
orm-0.515
-0.513
awar-0.507
nown-0.501
Token:
Token ID25
Feature activation+1.39e+00

Pos logit contributions
 Nose+2.472
 bluff+2.330
   +2.324
aspers+2.306
itiz+2.258
Neg logit contributions
icult-3.028
-2.929
nown-2.922
orm-2.915
awar-2.901
Token Everyone
Token ID11075
Feature activation+1.06e+00

Pos logit contributions
 Nose+9.868
   +9.454
 bluff+8.783
 Voters+8.646
 ●+8.600
Neg logit contributions
nown-12.750
icult-11.978
-11.850
 lett-11.496
awar-11.434
Token
Token ID198
Feature activation+1.97e-01

Pos logit contributions
 Nose+7.881
   +7.279
 bluff+7.149
aspers+6.994
ertodd+6.714
Neg logit contributions
nown-9.671
icult-9.625
-9.279
awar-9.063
 iceberg-8.980
Token
Token ID198
Feature activation+4.79e-01

Pos logit contributions
 Nose+1.715
aspers+1.675
ertodd+1.630
 bluff+1.623
itiz+1.612
Neg logit contributions
icult-1.761
orm-1.705
-1.693
awar-1.681
nown-1.656
TokenH
Token ID39
Feature activation+2.60e-01

Pos logit contributions
 Nose+4.129
   +4.023
aspers+4.006
itiz+3.887
 bluff+3.845
Neg logit contributions
icult-4.179
nown-3.986
awar-3.983
orm-3.956
 iceberg-3.936
Tokenomew
Token ID28030
Feature activation+3.47e-01

Pos logit contributions
aspers+1.225
 Nose+1.206
ertodd+1.134
itiz+1.098
 bluff+1.087
Neg logit contributions
icult-3.278
-3.226
orm-3.176
nown-3.174
Dub-3.161
Token I
Token ID314
Feature activation-3.88e-01

Pos logit contributions
 Nose+1.219
aspers+1.183
 bluff+1.157
itiz+1.153
ertodd+1.142
Neg logit contributions
icult-1.277
orm-1.235
awar-1.231
-1.230
Dub-1.208
Token can
Token ID460
Feature activation-1.52e-01

Pos logit contributions
icult+3.169
orm+3.140
aj+3.068
awar+3.053
 iceberg+2.999
Neg logit contributions
 Nose-3.579
aspers-3.492
ertodd-3.422
itiz-3.350
 bluff-3.300
Token re
Token ID302
Feature activation+8.69e-02

Pos logit contributions
icult+1.324
orm+1.296
awar+1.264
+1.259
 iceberg+1.255
Neg logit contributions
 Nose-1.354
aspers-1.329
ertodd-1.298
itiz-1.273
 bluff-1.250
Token-
Token ID12
Feature activation-6.17e-02

Pos logit contributions
 Nose+0.637
aspers+0.622
ertodd+0.601
 bluff+0.600
itiz+0.594
Neg logit contributions
icult-0.896
-0.871
orm-0.868
awar-0.860
nown-0.852
Tokenwatch
Token ID8340
Feature activation-1.59e-01

Pos logit contributions
icult+0.727
orm+0.712
awar+0.703
+0.702
Dub+0.695
Neg logit contributions
 Nose-0.365
aspers-0.350
ertodd-0.339
 bluff-0.335
itiz-0.330
Token F
Token ID376
Feature activation+1.39e+00

Pos logit contributions
icult+1.434
orm+1.401
+1.371
awar+1.364
 iceberg+1.351
Neg logit contributions
 Nose-1.366
aspers-1.351
ertodd-1.331
 bluff-1.297
itiz-1.286
Tokenars
Token ID945
Feature activation-2.15e-01

Pos logit contributions
aspers+11.825
 Nose+11.628
itiz+11.574
irts+11.513
   +11.163
Neg logit contributions
luaj-9.320
 Bulg-8.705
icult-8.686
 lett-8.585
 Jinn-8.536
Tokencape
Token ID36435
Feature activation-1.59e-01

Pos logit contributions
icult+2.068
orm+2.033
awar+1.988
+1.988
aj+1.967
Neg logit contributions
 Nose-1.716
aspers-1.696
ertodd-1.667
 bluff-1.636
itiz-1.613
Token.
Token ID13
Feature activation-1.80e-01

Pos logit contributions
icult+1.357
orm+1.323
+1.298
awar+1.294
 iceberg+1.277
Neg logit contributions
 Nose-1.438
aspers-1.419
ertodd-1.394
 bluff-1.369
itiz-1.361
Token (
Token ID357
Feature activation+3.98e-02

Pos logit contributions
icult+1.495
orm+1.458
+1.438
awar+1.427
Dub+1.422
Neg logit contributions
aspers-1.645
 Nose-1.643
ertodd-1.613
 bluff-1.597
itiz-1.569
TokenJust
Token ID5703
Feature activation+8.27e-02

Pos logit contributions
 Nose+0.351
aspers+0.344
 bluff+0.332
ertodd+0.332
itiz+0.331
Neg logit contributions
icult-0.354
orm-0.341
-0.338
awar-0.337
nown-0.331
Token him
Token ID683
Feature activation-1.65e-01

Pos logit contributions
icult+3.614
orm+3.523
awar+3.498
+3.471
 iceberg+3.463
Neg logit contributions
aspers-3.869
ertodd-3.860
 Nose-3.790
 bluff-3.708
itiz-3.693
Token.
Token ID13
Feature activation-2.20e-01

Pos logit contributions
icult+1.501
orm+1.467
+1.445
awar+1.439
aj+1.416
Neg logit contributions
 Nose-1.397
aspers-1.372
ertodd-1.340
 bluff-1.328
itiz-1.312
Token<|endoftext|>
Token ID50256
Feature activation+2.52e-03

Pos logit contributions
icult+1.957
+1.906
orm+1.902
awar+1.881
Dub+1.868
Neg logit contributions
aspers-1.880
 Nose-1.878
 bluff-1.830
ertodd-1.828
itiz-1.803
TokenS
Token ID50
Feature activation+1.95e-01

Pos logit contributions
 Nose+0.022
aspers+0.022
ertodd+0.021
 bluff+0.021
itiz+0.021
Neg logit contributions
icult-0.022
orm-0.021
-0.021
awar-0.021
nown-0.021
TokenAC
Token ID2246
Feature activation+6.75e-01

Pos logit contributions
 Nose+1.829
aspers+1.811
ertodd+1.751
 bluff+1.735
   +1.731
Neg logit contributions
icult-1.593
-1.532
orm-1.509
awar-1.490
Dub-1.483
TokenRAM
Token ID24115
Feature activation+1.35e+00

Pos logit contributions
 Nose+4.861
aspers+4.737
 bluff+4.615
   +4.457
itiz+4.417
Neg logit contributions
icult-6.836
-6.612
nown-6.442
awar-6.419
orm-6.327
TokenENT
Token ID3525
Feature activation+3.61e-01

Pos logit contributions
 Nose+5.647
   +5.178
 bluff+5.136
aspers+5.016
ath+4.569
Neg logit contributions
luaj-17.034
-16.395
awar-16.104
Reviewer-16.064
icult-15.917
TokenO
Token ID46
Feature activation+7.87e-01

Pos logit contributions
 Nose+3.570
aspers+3.474
   +3.391
 bluff+3.391
itiz+3.353
Neg logit contributions
icult-2.796
-2.697
orm-2.686
awar-2.656
nown-2.619
Token
Token ID851
Feature activation+2.73e-01

Pos logit contributions
 Nose+6.431
aspers+6.107
   +5.958
 bluff+5.858
itiz+5.810
Neg logit contributions
icult-6.972
awar-6.803
nown-6.712
-6.705
luaj-6.658
Token Thousands
Token ID30405
Feature activation-4.19e-01

Pos logit contributions
 Nose+2.464
aspers+2.332
   +2.287
ertodd+2.255
 bluff+2.253
Neg logit contributions
icult-2.421
orm-2.343
-2.326
awar-2.292
nown-2.282
Token of
Token ID286
Feature activation+2.12e-03

Pos logit contributions
icult+3.627
orm+3.533
awar+3.438
+3.432
aj+3.420
Neg logit contributions
 Nose-3.709
aspers-3.632
itiz-3.547
ertodd-3.539
 bluff-3.484
Tokenroph
Token ID10051
Feature activation+5.97e-01

Pos logit contributions
 Nose+5.177
aspers+5.085
 bluff+4.967
itiz+4.896
ertodd+4.794
Neg logit contributions
-5.260
icult-5.039
 Asgard-4.982
Dub-4.971
awar-4.904
Tokenages
Token ID1095
Feature activation+2.88e-02

Pos logit contributions
aspers+4.383
 Nose+4.379
itiz+4.320
ertodd+4.016
   +3.996
Neg logit contributions
-6.220
icult-5.749
Dub-5.684
 iceberg-5.663
 lett-5.610
Token at
Token ID379
Feature activation+5.73e-01

Pos logit contributions
 Nose+0.251
aspers+0.246
ertodd+0.239
 bluff+0.238
itiz+0.236
Neg logit contributions
icult-0.259
orm-0.251
-0.249
awar-0.247
Dub-0.243
Token the
Token ID262
Feature activation+5.39e-01

Pos logit contributions
 Nose+4.763
aspers+4.527
 bluff+4.413
   +4.380
itiz+4.296
Neg logit contributions
icult-5.312
-5.198
awar-5.081
orm-4.976
Dub-4.949
Token site
Token ID2524
Feature activation+7.39e-01

Pos logit contributions
 Nose+4.191
aspers+3.923
 bluff+3.889
   +3.788
itiz+3.758
Neg logit contributions
icult-5.405
-5.270
orm-5.138
awar-5.134
Dub-5.089
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
 Nose+4.894
itiz+4.594
 bluff+4.546
aspers+4.514
   +4.383
Neg logit contributions
icult-7.683
-7.559
Dub-7.527
orm-7.436
awar-7.408
Token inoc
Token ID49027
Feature activation-5.13e-02

Pos logit contributions
 Nose+9.601
 bluff+8.407
   +8.391
itiz+8.281
aspers+8.155
Neg logit contributions
icult-12.352
-12.211
luaj-11.853
nown-11.766
Dub-11.751
Tokenulation
Token ID1741
Feature activation+1.82e-01

Pos logit contributions
icult+0.485
orm+0.471
+0.465
awar+0.464
Dub+0.457
Neg logit contributions
 Nose-0.422
aspers-0.413
ertodd-0.402
 bluff-0.399
itiz-0.396
Token and
Token ID290
Feature activation+3.99e-01

Pos logit contributions
 Nose+1.476
aspers+1.427
 bluff+1.401
ertodd+1.384
   +1.383
Neg logit contributions
icult-1.738
-1.681
orm-1.678
awar-1.661
Dub-1.641
Token lymph
Token ID28837
Feature activation-8.24e-02

Pos logit contributions
 Nose+3.527
aspers+3.383
 bluff+3.300
   +3.279
itiz+3.250
Neg logit contributions
icult-3.574
-3.466
orm-3.397
awar-3.386
Dub-3.354
Token nodes
Token ID13760
Feature activation+3.77e-01

Pos logit contributions
icult+0.572
orm+0.556
+0.543
awar+0.542
aj+0.529
Neg logit contributions
 Nose-0.881
aspers-0.866
ertodd-0.851
 bluff-0.844
itiz-0.837
Token Boston
Token ID6182
Feature activation+7.82e-02

Pos logit contributions
 Nose+4.151
 bluff+3.914
aspers+3.748
   +3.726
itiz+3.716
Neg logit contributions
icult-6.334
orm-6.053
-5.918
awar-5.903
nown-5.884
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
 Nose+0.665
aspers+0.642
 bluff+0.628
itiz+0.624
ertodd+0.622
Neg logit contributions
icult-0.720
orm-0.694
-0.693
awar-0.688
Dub-0.673
Token (
Token ID357
Feature activation-6.49e-01

Pos logit contributions
icult+0.930
orm+0.904
+0.892
awar+0.891
Dub+0.879
Neg logit contributions
 Nose-0.995
aspers-0.986
ertodd-0.962
 bluff-0.955
itiz-0.945
TokenWa
Token ID33484
Feature activation+4.89e-02

Pos logit contributions
Dub+4.895
orm+4.762
+4.741
aj+4.740
icult+4.732
Neg logit contributions
 Nose-6.344
aspers-6.230
 bluff-6.100
ertodd-6.082
itiz-5.974
Tokenub
Token ID549
Feature activation+2.12e-01

Pos logit contributions
 Nose+0.448
aspers+0.438
 bluff+0.428
ertodd+0.427
   +0.423
Neg logit contributions
icult-0.419
orm-0.408
awar-0.403
Dub-0.395
-0.394
Tokenges
Token ID3212
Feature activation+1.34e+00

Pos logit contributions
 Nose+1.914
aspers+1.881
ertodd+1.830
itiz+1.820
 bluff+1.813
Neg logit contributions
icult-1.822
orm-1.767
-1.766
awar-1.743
 iceberg-1.713
Tokenhig
Token ID25196
Feature activation+2.45e-01

Pos logit contributions
ertodd+3.651
 Nose+3.353
aspers+3.310
irts+3.102
itiz+3.060
Neg logit contributions
-17.767
Dub-17.333
 lett-17.324
 Asgard-17.263
 iceberg-17.094
Token Rice
Token ID13823
Feature activation+5.45e-02

Pos logit contributions
 Nose+1.594
aspers+1.524
ertodd+1.472
 bluff+1.467
   +1.457
Neg logit contributions
icult-2.748
orm-2.668
-2.664
awar-2.645
nown-2.612
Token/
Token ID14
Feature activation+2.72e-01

Pos logit contributions
 Nose+0.485
aspers+0.481
ertodd+0.470
 bluff+0.465
itiz+0.462
Neg logit contributions
icult-0.472
orm-0.464
awar-0.454
-0.453
Dub-0.449
TokenCBC
Token ID29208
Feature activation+8.59e-02

Pos logit contributions
 Nose+2.842
aspers+2.795
ertodd+2.735
   +2.718
 bluff+2.714
Neg logit contributions
icult-1.960
orm-1.863
-1.846
awar-1.839
nown-1.803
Token)
Token ID8
Feature activation-1.95e-01

Pos logit contributions
 Nose+0.638
aspers+0.609
ertodd+0.603
 bluff+0.596
itiz+0.589
Neg logit contributions
icult-0.877
orm-0.853
-0.852
awar-0.840
nown-0.836
Token Ad
Token ID1215
Feature activation-3.34e-02

Pos logit contributions
 Nose+4.201
aspers+4.030
 bluff+3.993
   +3.860
itiz+3.827
Neg logit contributions
icult-4.836
-4.696
orm-4.634
awar-4.605
Dub-4.586
Tokenelson
Token ID10151
Feature activation+2.68e-01

Pos logit contributions
icult+0.305
orm+0.296
awar+0.292
+0.291
aj+0.286
Neg logit contributions
 Nose-0.285
aspers-0.279
ertodd-0.272
 bluff-0.270
itiz-0.268
Token-
Token ID12
Feature activation+2.08e-01

Pos logit contributions
 Nose+2.331
aspers+2.258
 bluff+2.214
ertodd+2.195
itiz+2.186
Neg logit contributions
icult-2.403
-2.345
orm-2.321
awar-2.306
nown-2.275
Tokenfunded
Token ID18246
Feature activation+3.50e-01

Pos logit contributions
 Nose+1.727
aspers+1.715
itiz+1.654
 bluff+1.651
ertodd+1.649
Neg logit contributions
icult-1.914
-1.845
orm-1.837
awar-1.833
 iceberg-1.808
Token Washington
Token ID2669
Feature activation+4.68e-01

Pos logit contributions
 Nose+3.196
aspers+3.058
 bluff+3.040
itiz+2.960
   +2.953
Neg logit contributions
icult-2.953
-2.909
orm-2.858
nown-2.839
awar-2.823
Token Free
Token ID3232
Feature activation+1.34e+00

Pos logit contributions
 Nose+4.384
aspers+4.210
itiz+4.165
 bluff+4.099
   +4.046
Neg logit contributions
icult-3.751
-3.735
orm-3.627
awar-3.604
nown-3.565
Token Beacon
Token ID29729
Feature activation+1.28e-01

Pos logit contributions
 Nose+4.678
itiz+4.491
irts+4.204
aspers+4.192
   +3.847
Neg logit contributions
icult-16.865
nown-16.632
-16.568
awar-15.934
Dub-15.887
Token leading
Token ID3756
Feature activation+7.36e-02

Pos logit contributions
 Nose+1.089
aspers+1.062
 bluff+1.042
ertodd+1.029
   +1.020
Neg logit contributions
icult-1.176
orm-1.134
-1.131
awar-1.124
Dub-1.104
Token the
Token ID262
Feature activation+1.56e-01

Pos logit contributions
 Nose+0.626
aspers+0.611
 bluff+0.592
itiz+0.589
ertodd+0.588
Neg logit contributions
icult-0.674
orm-0.655
-0.651
awar-0.646
nown-0.640
Token charge
Token ID3877
Feature activation-8.07e-02

Pos logit contributions
 Nose+1.101
aspers+1.058
 bluff+1.038
ertodd+1.017
itiz+1.014
Neg logit contributions
icult-1.662
orm-1.620
-1.611
awar-1.596
nown-1.592
Token,
Token ID11
Feature activation+9.00e-02

Pos logit contributions
icult+0.727
orm+0.706
+0.699
awar+0.695
Dub+0.685
Neg logit contributions
 Nose-0.698
aspers-0.684
ertodd-0.667
 bluff-0.660
itiz-0.656
Token of
Token ID286
Feature activation+1.16e-01

Pos logit contributions
 Nose+0.635
aspers+0.632
ertodd+0.623
 bluff+0.611
itiz+0.606
Neg logit contributions
icult-0.646
orm-0.634
awar-0.622
-0.620
Dub-0.619
Token Alabama
Token ID9266
Feature activation+2.08e-01

Pos logit contributions
 Nose+1.086
aspers+1.049
 bluff+1.023
   +1.018
ertodd+1.011
Neg logit contributions
icult-0.979
orm-0.941
-0.940
awar-0.928
nown-0.918
Token at
Token ID379
Feature activation+2.27e-03

Pos logit contributions
 Nose+1.748
aspers+1.682
 bluff+1.643
   +1.629
itiz+1.618
Neg logit contributions
icult-1.936
orm-1.878
-1.873
awar-1.861
nown-1.831
Token Birmingham
Token ID18899
Feature activation+1.03e-01

Pos logit contributions
 Nose+0.021
aspers+0.021
ertodd+0.021
 bluff+0.020
itiz+0.020
Neg logit contributions
icult-0.019
orm-0.018
-0.018
awar-0.018
Dub-0.017
Token School
Token ID3961
Feature activation-1.87e-01

Pos logit contributions
 Nose+0.827
aspers+0.799
 bluff+0.772
   +0.770
ertodd+0.770
Neg logit contributions
icult-0.989
orm-0.962
-0.956
awar-0.952
nown-0.940
Token of
Token ID286
Feature activation+1.34e+00

Pos logit contributions
icult+1.511
orm+1.495
aj+1.475
awar+1.442
Dub+1.438
Neg logit contributions
aspers-1.748
 Nose-1.723
ertodd-1.710
 bluff-1.681
itiz-1.647
Token Medicine
Token ID11558
Feature activation+2.13e-01

Pos logit contributions
 Nose+7.248
 Pharm+5.945
   +5.754
 Voters+5.511
itiz+5.321
Neg logit contributions
-15.355
icult-14.473
nown-14.465
awar-14.286
 iceberg-14.088
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
 Nose+1.626
aspers+1.561
   +1.518
ertodd+1.513
itiz+1.504
Neg logit contributions
icult-2.129
orm-2.062
-2.055
awar-2.050
nown-2.028
Token Views
Token ID29978
Feature activation-2.32e-01

Pos logit contributions
icult+0.100
orm+0.097
+0.096
awar+0.096
nown+0.094
Neg logit contributions
 Nose-0.088
aspers-0.086
ertodd-0.083
 bluff-0.083
itiz-0.082
Token expressed
Token ID6241
Feature activation-6.76e-02

Pos logit contributions
icult+1.296
orm+1.265
awar+1.199
aj+1.196
+1.193
Neg logit contributions
 Nose-2.758
aspers-2.711
ertodd-2.708
 bluff-2.662
itiz-2.655
Token are
Token ID389
Feature activation-3.33e-01

Pos logit contributions
icult+0.637
orm+0.619
+0.612
awar+0.609
Dub+0.601
Neg logit contributions
 Nose-0.558
aspers-0.545
ertodd-0.530
 bluff-0.527
itiz-0.523
Tokent
Token ID83
Feature activation+5.08e-02

Pos logit contributions
 Nose+2.038
aspers+1.995
 bluff+1.924
ertodd+1.924
itiz+1.921
Neg logit contributions
icult-2.399
orm-2.323
-2.315
awar-2.307
nown-2.278
Token believe
Token ID1975
Feature activation+9.09e-02

Pos logit contributions
 Nose+0.466
aspers+0.457
ertodd+0.445
 bluff+0.443
itiz+0.440
Neg logit contributions
icult-0.431
orm-0.418
-0.413
awar-0.411
Dub-0.404
Token the
Token ID262
Feature activation-9.07e-02

Pos logit contributions
 Nose+0.780
aspers+0.757
 bluff+0.742
   +0.737
itiz+0.736
Neg logit contributions
icult-0.830
orm-0.798
-0.796
awar-0.793
nown-0.780
Token citizens
Token ID4290
Feature activation+1.33e-01

Pos logit contributions
icult+0.765
orm+0.747
+0.735
awar+0.729
Dub+0.721
Neg logit contributions
 Nose-0.833
aspers-0.821
ertodd-0.802
 bluff-0.788
itiz-0.784
Token of
Token ID286
Feature activation+6.70e-02

Pos logit contributions
 Nose+1.051
aspers+1.023
 bluff+1.003
   +0.997
ertodd+0.993
Neg logit contributions
icult-1.288
orm-1.240
awar-1.234
-1.232
Dub-1.212
Token F
Token ID376
Feature activation+1.34e+00

Pos logit contributions
 Nose+0.591
aspers+0.574
 bluff+0.560
   +0.556
ertodd+0.555
Neg logit contributions
icult-0.597
orm-0.576
-0.572
awar-0.569
nown-0.561
Tokenayette
Token ID27067
Feature activation+2.97e-01

Pos logit contributions
aspers+8.359
   +8.011
itiz+7.996
 Nose+7.990
irts+7.829
Neg logit contributions
luaj-11.900
 Asgard-11.884
 Jinn-11.877
 Bulg-11.851
 lett-11.832
Tokenville
Token ID4244
Feature activation+4.84e-02

Pos logit contributions
 Nose+2.409
aspers+2.300
 bluff+2.283
   +2.278
itiz+2.245
Neg logit contributions
icult-2.835
orm-2.724
awar-2.706
-2.684
 iceberg-2.668
Token would
Token ID561
Feature activation-1.49e-01

Pos logit contributions
 Nose+0.421
aspers+0.412
 bluff+0.400
ertodd+0.399
itiz+0.396
Neg logit contributions
icult-0.435
orm-0.420
-0.417
awar-0.414
Dub-0.408
Token want
Token ID765
Feature activation-1.44e-02

Pos logit contributions
icult+1.303
orm+1.291
awar+1.251
aj+1.239
+1.237
Neg logit contributions
 Nose-1.314
aspers-1.293
ertodd-1.263
itiz-1.237
 bluff-1.210
Token males
Token ID10835
Feature activation-3.23e-01

Pos logit contributions
icult+0.134
orm+0.130
+0.128
awar+0.128
nown+0.126
Neg logit contributions
 Nose-0.121
aspers-0.118
ertodd-0.114
 bluff-0.114
itiz-0.113
Tokenassing
Token ID19696
Feature activation+5.28e-01

Pos logit contributions
 Nose+3.229
aspers+3.186
itiz+3.094
ertodd+3.042
 bluff+3.038
Neg logit contributions
icult-3.470
-3.427
orm-3.289
Dub-3.282
awar-3.272
Token,
Token ID11
Feature activation+1.59e-01

Pos logit contributions
 Nose+4.195
 bluff+3.982
itiz+3.932
aspers+3.890
   +3.880
Neg logit contributions
icult-5.017
-4.966
awar-4.801
orm-4.765
nown-4.743
Token or
Token ID393
Feature activation+5.58e-01

Pos logit contributions
 Nose+1.385
aspers+1.345
 bluff+1.319
ertodd+1.308
itiz+1.304
Neg logit contributions
icult-1.426
orm-1.374
-1.370
awar-1.356
nown-1.336
Token simply
Token ID2391
Feature activation+6.15e-01

Pos logit contributions
 Nose+4.680
 bluff+4.504
aspers+4.433
itiz+4.390
   +4.316
Neg logit contributions
icult-5.063
-4.966
orm-4.861
awar-4.837
nown-4.763
Token allowed
Token ID3142
Feature activation+9.20e-01

Pos logit contributions
 Nose+5.098
 bluff+5.026
aspers+4.834
itiz+4.829
   +4.775
Neg logit contributions
icult-5.516
-5.440
awar-5.328
orm-5.269
nown-5.235
Token to
Token ID284
Feature activation+1.33e+00

Pos logit contributions
 Nose+5.594
aspers+5.542
itiz+5.536
 bluff+5.492
   +5.220
Neg logit contributions
icult-9.566
awar-9.212
luaj-9.212
nown-9.195
-9.028
Token drift
Token ID24260
Feature activation+5.18e-01

Pos logit contributions
 bluff+9.666
aspers+9.207
 Nose+9.143
   +9.065
ertodd+8.701
Neg logit contributions
icult-11.228
Dub-11.120
nown-10.975
-10.923
luaj-10.856
Token out
Token ID503
Feature activation+5.19e-01

Pos logit contributions
 Nose+4.385
 bluff+4.291
aspers+4.168
itiz+4.153
   +4.134
Neg logit contributions
icult-4.658
-4.588
awar-4.463
orm-4.419
luaj-4.399
Token.
Token ID13
Feature activation+1.16e-02

Pos logit contributions
 Nose+3.792
aspers+3.740
itiz+3.684
 bluff+3.681
   +3.612
Neg logit contributions
icult-5.135
-4.957
awar-4.940
Dub-4.874
orm-4.853
Token This
Token ID770
Feature activation-8.65e-02

Pos logit contributions
 Nose+0.107
aspers+0.105
ertodd+0.102
 bluff+0.102
itiz+0.101
Neg logit contributions
icult-0.098
orm-0.095
-0.094
awar-0.094
Dub-0.092
Token was
Token ID373
Feature activation-2.08e-03

Pos logit contributions
icult+0.743
orm+0.722
+0.707
awar+0.707
 iceberg+0.704
Neg logit contributions
 Nose-0.781
aspers-0.772
ertodd-0.755
 bluff-0.735
itiz-0.734
TokenMemory
Token ID30871
Feature activation-1.21e-02

Pos logit contributions
orm+0.789
icult+0.785
Dub+0.774
aj+0.763
awar+0.758
Neg logit contributions
 Nose-1.030
aspers-1.005
 bluff-0.988
ertodd-0.988
itiz-0.964
Token 4
Token ID604
Feature activation+5.51e-02

Pos logit contributions
icult+0.106
orm+0.102
+0.101
awar+0.101
nown+0.100
Neg logit contributions
 Nose-0.108
aspers-0.106
ertodd-0.103
 bluff-0.103
   -0.102
Token66
Token ID2791
Feature activation+4.37e-01

Pos logit contributions
 Nose+0.478
aspers+0.470
ertodd+0.459
 bluff+0.457
itiz+0.452
Neg logit contributions
icult-0.492
orm-0.482
awar-0.474
-0.474
aj-0.468
Token284
Token ID30336
Feature activation+2.31e-01

Pos logit contributions
aspers+3.640
 Nose+3.638
ertodd+3.513
   +3.408
 bluff+3.407
Neg logit contributions
icult-4.041
-3.881
orm-3.847
awar-3.834
 lett-3.814
Token 4
Token ID604
Feature activation+1.09e-01

Pos logit contributions
 Nose+2.108
aspers+2.064
ertodd+2.011
 bluff+2.002
itiz+1.988
Neg logit contributions
icult-1.967
orm-1.904
-1.885
awar-1.874
Dub-1.843
Token64
Token ID2414
Feature activation+1.32e+00

Pos logit contributions
 Nose+0.963
aspers+0.943
ertodd+0.918
 bluff+0.916
itiz+0.908
Neg logit contributions
icult-0.963
orm-0.941
-0.926
awar-0.923
Dub-0.915
Token406
Token ID29703
Feature activation-4.67e-01

Pos logit contributions
ertodd+5.233
   +4.927
itiz+4.924
 Nose+4.901
·+4.754
Neg logit contributions
icult-15.829
 lett-15.762
 Bulg-15.125
-15.099
awar-15.054
Token Mem
Token ID4942
Feature activation-3.54e-01

Pos logit contributions
orm+2.578
aj+2.500
Dub+2.389
icult+2.361
 Wol+2.360
Neg logit contributions
aspers-5.500
ertodd-5.416
 bluff-5.258
itiz-5.256
 Nose-5.155
Tokenc
Token ID66
Feature activation+1.66e-01

Pos logit contributions
orm+3.162
aj+3.085
icult+3.077
awar+2.975
buff+2.921
Neg logit contributions
 Nose-3.171
aspers-2.964
 bluff-2.957
ertodd-2.881
itiz-2.818
Tokenpy
Token ID9078
Feature activation+4.07e-01

Pos logit contributions
 Nose+1.299
aspers+1.264
ertodd+1.227
 bluff+1.220
itiz+1.208
Neg logit contributions
icult-1.643
orm-1.601
-1.580
awar-1.577
Dub-1.554
TokenReading
Token ID36120
Feature activation+3.73e-02

Pos logit contributions
 Nose+1.707
   +1.634
aspers+1.598
ertodd+1.551
 bluff+1.511
Neg logit contributions
icult-5.442
awar-5.250
orm-5.236
nown-5.197
-5.194
Token
Token ID198
Feature activation+8.93e-02

Pos logit contributions
 Nose+3.044
aspers+2.903
   +2.870
ertodd+2.830
itiz+2.800
Neg logit contributions
icult-3.728
orm-3.608
awar-3.603
-3.572
nown-3.561
Token
Token ID198
Feature activation+2.88e-01

Pos logit contributions
 Nose+0.807
aspers+0.794
ertodd+0.775
 bluff+0.770
itiz+0.763
Neg logit contributions
icult-0.768
orm-0.749
awar-0.734
-0.733
Dub-0.726
TokenGov
Token ID23774
Feature activation+4.80e-01

Pos logit contributions
 Nose+2.327
aspers+2.306
   +2.261
itiz+2.225
ertodd+2.224
Neg logit contributions
icult-2.721
awar-2.616
orm-2.608
-2.557
nown-2.551
Token.
Token ID13
Feature activation+2.71e-01

Pos logit contributions
 Nose+3.167
aspers+3.090
itiz+2.956
   +2.931
ertodd+2.917
Neg logit contributions
icult-5.190
-5.100
 lett-4.934
 iceberg-4.926
awar-4.903
Token Robert
Token ID5199
Feature activation-5.57e-03

Pos logit contributions
 Nose+2.497
aspers+2.395
itiz+2.340
   +2.336
 bluff+2.312
Neg logit contributions
icult-2.352
-2.235
nown-2.206
orm-2.180
Dub-2.172
Token F
Token ID376
Feature activation+1.29e+00

Pos logit contributions
icult+0.043
orm+0.042
+0.041
awar+0.041
nown+0.040
Neg logit contributions
 Nose-0.056
aspers-0.054
ertodd-0.053
 bluff-0.053
itiz-0.053
Token.
Token ID13
Feature activation+7.74e-01

Pos logit contributions
aspers+6.884
 Nose+6.840
itiz+6.543
irts+6.479
   +6.302
Neg logit contributions
-13.954
 lett-13.894
icult-13.690
luaj-13.671
 iceberg-13.434
Token McDonnell
Token ID39441
Feature activation+5.67e-02

Pos logit contributions
 Nose+4.543
   +3.931
 bluff+3.920
itiz+3.878
aspers+3.850
Neg logit contributions
icult-9.125
nown-8.958
-8.953
awar-8.949
orm-8.918
Token (
Token ID357
Feature activation-1.69e-02

Pos logit contributions
 Nose+0.478
aspers+0.466
ertodd+0.453
 bluff+0.453
itiz+0.450
Neg logit contributions
icult-0.525
orm-0.508
-0.505
awar-0.504
Dub-0.495
TokenR
Token ID49
Feature activation+2.35e-01

Pos logit contributions
icult+0.154
orm+0.149
+0.148
awar+0.148
nown+0.145
Neg logit contributions
 Nose-0.145
aspers-0.142
ertodd-0.138
 bluff-0.137
itiz-0.137
Token)
Token ID8
Feature activation+2.70e-01

Pos logit contributions
 Nose+1.691
aspers+1.652
 bluff+1.583
itiz+1.567
ertodd+1.567
Neg logit contributions
icult-2.421
awar-2.345
-2.328
Dub-2.321
orm-2.317
Token beats
Token ID17825
Feature activation-1.95e-01

Pos logit contributions
icult+1.217
orm+1.191
awar+1.163
 iceberg+1.156
Dub+1.155
Neg logit contributions
 Nose-1.127
aspers-1.111
ertodd-1.094
 bluff-1.072
   -1.060
Token other
Token ID584
Feature activation-1.71e-01

Pos logit contributions
icult+1.740
orm+1.698
awar+1.651
 iceberg+1.648
Dub+1.644
Neg logit contributions
 Nose-1.674
aspers-1.655
ertodd-1.638
 bluff-1.596
itiz-1.592
Token vendors
Token ID17192
Feature activation-2.18e-01

Pos logit contributions
icult+1.557
orm+1.514
 iceberg+1.477
awar+1.469
aj+1.462
Neg logit contributions
 Nose-1.454
aspers-1.420
ertodd-1.418
 bluff-1.377
itiz-1.375
Token by
Token ID416
Feature activation-3.69e-01

Pos logit contributions
icult+1.828
orm+1.789
 iceberg+1.720
aj+1.717
awar+1.716
Neg logit contributions
 Nose-1.972
aspers-1.939
ertodd-1.920
itiz-1.866
 bluff-1.865
Token leaps
Token ID37312
Feature activation-3.71e-01

Pos logit contributions
icult+3.084
orm+3.078
 iceberg+2.990
Dub+2.972
 lett+2.952
Neg logit contributions
 Nose-3.274
aspers-3.265
ertodd-3.235
itiz-3.077
 bluff-3.074
Token and
Token ID290
Feature activation-1.40e+00

Pos logit contributions
icult+3.069
orm+2.974
+2.918
awar+2.900
 iceberg+2.856
Neg logit contributions
 Nose-3.473
aspers-3.397
ertodd-3.340
 bluff-3.298
itiz-3.269
Token bounds
Token ID22303
Feature activation-1.11e-01

Pos logit contributions
 iceberg+3.239
 lett+2.824
 Asgard+2.794
icult+2.785
 Wol+2.595
Neg logit contributions
ertodd-19.136
 Nose-18.702
thora-18.126
aspers-17.933
��-17.824
Token.
Token ID13
Feature activation+1.93e-02

Pos logit contributions
icult+1.038
orm+1.010
+0.994
awar+0.992
Dub+0.978
Neg logit contributions
 Nose-0.929
aspers-0.910
ertodd-0.884
 bluff-0.878
itiz-0.871
Token There
Token ID1318
Feature activation-1.80e-01

Pos logit contributions
 Nose+0.178
aspers+0.175
ertodd+0.171
 bluff+0.170
itiz+0.169
Neg logit contributions
icult-0.162
orm-0.157
-0.155
awar-0.154
Dub-0.152
Token are
Token ID389
Feature activation-3.84e-02

Pos logit contributions
icult+1.714
orm+1.676
+1.649
awar+1.633
aj+1.617
Neg logit contributions
 Nose-1.469
aspers-1.427
ertodd-1.397
 bluff-1.388
itiz-1.376
Token custom
Token ID2183
Feature activation+3.69e-02

Pos logit contributions
icult+0.334
orm+0.326
+0.319
awar+0.318
Dub+0.314
Neg logit contributions
 Nose-0.344
aspers-0.337
ertodd-0.330
 bluff-0.327
itiz-0.325
Token will
Token ID481
Feature activation-7.05e-02

Pos logit contributions
aj+2.622
orm+2.580
icult+2.579
+2.501
nown+2.466
Neg logit contributions
ertodd-3.059
 Nose-2.956
aspers-2.884
itiz-2.857
 bluff-2.776
Token receive
Token ID3328
Feature activation-4.70e-01

Pos logit contributions
orm+0.662
icult+0.644
aj+0.642
awar+0.631
 iceberg+0.630
Neg logit contributions
aspers-0.590
ertodd-0.573
 Nose-0.569
 bluff-0.559
itiz-0.549
Token occasional
Token ID12209
Feature activation-2.21e-01

Pos logit contributions
aj+2.943
orm+2.926
icult+2.872
 iceberg+2.806
nown+2.800
Neg logit contributions
aspers-5.244
ertodd-5.149
itiz-4.964
 Nose-4.956
thora-4.878
Token promotional
Token ID18767
Feature activation-3.74e-01

Pos logit contributions
icult+1.145
orm+1.067
aj+1.051
 iceberg+0.986
 lett+0.974
Neg logit contributions
 Nose-2.818
aspers-2.762
ertodd-2.672
itiz-2.607
 bluff-2.597
Token offers
Token ID4394
Feature activation-3.94e-01

Pos logit contributions
icult+2.126
orm+2.057
 iceberg+2.026
aj+1.989
 Asgard+1.952
Neg logit contributions
 Nose-4.340
ertodd-4.280
aspers-4.223
��-4.055
itiz-4.052
Token for
Token ID329
Feature activation-1.27e+00

Pos logit contributions
aj+2.631
orm+2.607
icult+2.580
 iceberg+2.455
Dub+2.453
Neg logit contributions
aspers-4.201
 Nose-4.112
ertodd-4.055
itiz-3.920
 bluff-3.901
Token programs
Token ID4056
Feature activation+5.00e-02

Pos logit contributions
orm+3.312
aj+3.276
 iceberg+3.237
icult+2.960
nown+2.797
Neg logit contributions
ertodd-17.183
aspers-16.477
 Nose-16.400
thora-16.175
 bluff-15.233
Token that
Token ID326
Feature activation-4.63e-01

Pos logit contributions
 Nose+0.458
aspers+0.454
ertodd+0.441
 bluff+0.434
itiz+0.433
Neg logit contributions
icult-0.423
orm-0.415
awar-0.404
aj-0.401
-0.399
Token support
Token ID1104
Feature activation-2.64e-01

Pos logit contributions
orm+3.642
aj+3.598
icult+3.459
awar+3.376
 Asgard+3.371
Neg logit contributions
 Nose-4.393
aspers-4.255
ertodd-4.172
itiz-4.113
 bluff-4.072
Token The
Token ID383
Feature activation+1.28e-01

Pos logit contributions
icult+1.810
orm+1.799
aj+1.759
+1.747
Dub+1.743
Neg logit contributions
aspers-2.767
ertodd-2.697
 Nose-2.692
 bluff-2.677
itiz-2.662
Token Nation
Token ID8741
Feature activation-5.90e-02

Pos logit contributions
 Nose+0.858
aspers+0.847
ertodd+0.815
 bluff+0.809
itiz+0.798
Neg logit contributions
icult-1.396
orm-1.368
-1.350
awar-1.346
Dub-1.334
Token 9
Token ID860
Feature activation-4.77e-02

Pos logit contributions
 iceberg+3.488
 Asgard+3.445
aj+3.310
 Alm+3.239
orm+3.110
Neg logit contributions
ertodd-13.339
 bluff-13.273
aspers-13.032
��-12.837
itiz-12.834
Token Russian
Token ID3394
Feature activation-1.43e-01

Pos logit contributions
icult+0.397
orm+0.386
awar+0.380
+0.380
Dub+0.377
Neg logit contributions
 Nose-0.438
aspers-0.434
ertodd-0.427
 bluff-0.422
itiz-0.419
Token Federation
Token ID11937
Feature activation-5.82e-01

Pos logit contributions
icult+1.415
orm+1.383
+1.370
awar+1.360
 iceberg+1.344
Neg logit contributions
 Nose-1.094
aspers-1.076
ertodd-1.068
itiz-1.040
 bluff-1.037
Token 18
Token ID1248
Feature activation-6.39e-01

Pos logit contributions
icult+3.531
aj+3.525
orm+3.515
 Asgard+3.491
Dub+3.431
Neg logit contributions
ertodd-6.313
aspers-6.187
 bluff-6.094
 Nose-6.081
itiz-6.076
Token.
Token ID13
Feature activation-7.18e-03

Pos logit contributions
icult+5.399
orm+5.257
+5.239
aj+5.209
awar+5.155
Neg logit contributions
 Nose-5.452
aspers-5.431
 bluff-5.372
ertodd-5.316
itiz-5.308
Token7
Token ID22
Feature activation-1.26e+00

Pos logit contributions
icult+0.069
orm+0.067
+0.067
awar+0.066
 iceberg+0.065
Neg logit contributions
 Nose-0.058
aspers-0.056
ertodd-0.055
 bluff-0.054
   -0.054
Token 10
Token ID838
Feature activation-5.51e-02

Pos logit contributions
icult+6.612
 iceberg+6.532
aj+6.213
orm+6.182
+6.123
Neg logit contributions
aspers-13.716
 bluff-13.274
 Nose-13.113
itiz-13.110
ertodd-12.957
Token United
Token ID1578
Feature activation+1.02e-01

Pos logit contributions
icult+0.466
orm+0.454
awar+0.447
+0.446
Dub+0.444
Neg logit contributions
 Nose-0.497
aspers-0.493
ertodd-0.486
 bluff-0.479
itiz-0.477
Token Arab
Token ID4498
Feature activation-1.19e-01

Pos logit contributions
 Nose+0.978
aspers+0.954
ertodd+0.925
   +0.917
itiz+0.916
Neg logit contributions
icult-0.827
-0.799
orm-0.788
awar-0.783
nown-0.776
Token Emirates
Token ID24880
Feature activation-2.70e-01

Pos logit contributions
icult+0.695
orm+0.692
+0.672
Dub+0.661
aj+0.659
Neg logit contributions
 Nose-1.376
ertodd-1.362
aspers-1.359
 bluff-1.337
itiz-1.319
Token 19
Token ID678
Feature activation-3.71e-01

Pos logit contributions
icult+1.863
orm+1.844
aj+1.808
Dub+1.787
awar+1.783
Neg logit contributions
aspers-2.779
ertodd-2.775
 Nose-2.763
itiz-2.710
 bluff-2.707
Token the
Token ID262
Feature activation-3.81e-02

Pos logit contributions
icult+1.163
orm+1.140
awar+1.113
+1.110
 iceberg+1.095
Neg logit contributions
 Nose-1.191
aspers-1.174
ertodd-1.156
 bluff-1.132
itiz-1.123
Token Token
Token ID29130
Feature activation-4.67e-01

Pos logit contributions
icult+0.309
orm+0.300
+0.295
awar+0.294
nown+0.289
Neg logit contributions
 Nose-0.364
aspers-0.357
ertodd-0.349
 bluff-0.346
itiz-0.344
Token,
Token ID11
Feature activation+7.89e-02

Pos logit contributions
orm+3.883
icult+3.845
awar+3.713
+3.712
aj+3.698
Neg logit contributions
ertodd-4.171
aspers-4.169
 Nose-4.152
 bluff-3.910
itiz-3.901
Token you
Token ID345
Feature activation-1.46e-01

Pos logit contributions
 Nose+0.745
aspers+0.729
 bluff+0.712
ertodd+0.705
   +0.705
Neg logit contributions
icult-0.653
orm-0.627
-0.624
awar-0.617
Dub-0.610
Token cannot
Token ID2314
Feature activation-3.57e-03

Pos logit contributions
icult+1.311
orm+1.290
awar+1.266
+1.258
aj+1.242
Neg logit contributions
 Nose-1.263
aspers-1.230
ertodd-1.222
itiz-1.191
 bluff-1.186
Token Normal
Token ID14435
Feature activation-1.26e+00

Pos logit contributions
icult+0.031
orm+0.030
+0.030
awar+0.030
Dub+0.029
Neg logit contributions
 Nose-0.032
aspers-0.031
ertodd-0.031
 bluff-0.030
itiz-0.030
Token or
Token ID393
Feature activation-1.25e-01

Pos logit contributions
orm+5.584
aj+5.344
+5.130
buff+5.050
awar+4.999
Neg logit contributions
ertodd-15.342
 Nose-14.214
aspers-14.201
��-13.633
irts-13.597
Token Special
Token ID6093
Feature activation-8.93e-01

Pos logit contributions
icult+0.954
orm+0.928
awar+0.908
+0.902
aj+0.890
Neg logit contributions
 Nose-1.242
aspers-1.226
ertodd-1.209
itiz-1.181
 bluff-1.180
Token Summon
Token ID19515
Feature activation-1.78e-01

Pos logit contributions
orm+4.301
icult+4.093
aj+4.046
+3.970
buff+3.792
Neg logit contributions
ertodd-10.992
 Nose-10.503
aspers-10.403
��-9.888
 bluff-9.874
Token monsters
Token ID10963
Feature activation-1.48e-02

Pos logit contributions
icult+1.525
orm+1.507
+1.468
awar+1.467
 iceberg+1.450
Neg logit contributions
 Nose-1.568
aspers-1.551
ertodd-1.539
 bluff-1.493
itiz-1.478
Token,
Token ID11
Feature activation+1.84e-01

Pos logit contributions
icult+0.131
orm+0.127
+0.126
awar+0.125
nown+0.123
Neg logit contributions
 Nose-0.131
aspers-0.129
ertodd-0.126
 bluff-0.124
itiz-0.124
Token x
Token ID2124
Feature activation+3.86e-02

Pos logit contributions
icult+0.383
orm+0.375
awar+0.363
Dub+0.360
+0.360
Neg logit contributions
aspers-0.572
 Nose-0.568
ertodd-0.558
itiz-0.553
 bluff-0.551
Token.
Token ID13
Feature activation-3.42e-02

Pos logit contributions
 Nose+0.323
aspers+0.318
ertodd+0.310
 bluff+0.309
itiz+0.304
Neg logit contributions
icult-0.357
orm-0.351
awar-0.343
-0.342
aj-0.341
Tokenx
Token ID87
Feature activation+2.01e-01

Pos logit contributions
icult+0.342
orm+0.336
awar+0.329
aj+0.328
Dub+0.326
Neg logit contributions
 Nose-0.263
aspers-0.257
 bluff-0.251
ertodd-0.250
itiz-0.243
Token.
Token ID13
Feature activation-2.74e-02

Pos logit contributions
 Nose+1.579
aspers+1.540
ertodd+1.494
 bluff+1.486
itiz+1.476
Neg logit contributions
icult-1.976
orm-1.919
-1.906
awar-1.894
nown-1.868
Tokenx
Token ID87
Feature activation-1.72e-01

Pos logit contributions
icult+0.276
orm+0.271
awar+0.265
aj+0.264
Dub+0.263
Neg logit contributions
 Nose-0.210
aspers-0.205
 bluff-0.200
ertodd-0.199
itiz-0.194
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
icult+1.462
orm+1.455
aj+1.438
awar+1.422
Dub+1.414
Neg logit contributions
 Nose-1.534
aspers-1.520
ertodd-1.497
 bluff-1.492
itiz-1.461
Token85
Token ID5332
Feature activation-7.62e-01

Pos logit contributions
aj+4.536
buff+4.213
awar+3.911
icult+3.888
oof+3.738
Neg logit contributions
 Nose-15.957
ertodd-15.579
 bluff-15.235
itiz-15.065
��-15.061
Token 114
Token ID17342
Feature activation-1.32e-02

Pos logit contributions
aj+3.871
 Asgard+3.828
orm+3.811
icult+3.798
 iceberg+3.749
Neg logit contributions
ertodd-8.837
aspers-8.829
 bluff-8.618
itiz-8.450
 Nose-8.388
Token16
Token ID1433
Feature activation+1.65e-02

Pos logit contributions
icult+0.120
orm+0.116
+0.115
awar+0.115
Dub+0.113
Neg logit contributions
 Nose-0.113
aspers-0.111
ertodd-0.108
 bluff-0.107
itiz-0.107
Token21
Token ID2481
Feature activation-6.66e-02

Pos logit contributions
 Nose+0.145
aspers+0.142
ertodd+0.138
 bluff+0.137
itiz+0.136
Neg logit contributions
icult-0.147
orm-0.142
-0.141
awar-0.140
nown-0.138
Token x
Token ID2124
Feature activation+1.37e-01

Pos logit contributions
icult+0.461
orm+0.452
awar+0.435
aj+0.432
Dub+0.432
Neg logit contributions
aspers-0.701
 Nose-0.697
ertodd-0.686
itiz-0.679
 bluff-0.677
Token original
Token ID2656
Feature activation+1.81e-01

Pos logit contributions
 Nose+1.591
aspers+1.548
 bluff+1.505
ertodd+1.487
   +1.480
Neg logit contributions
icult-1.663
-1.612
orm-1.593
awar-1.591
nown-1.566
Token image
Token ID2939
Feature activation-1.27e-01

Pos logit contributions
 Nose+1.537
aspers+1.493
 bluff+1.451
ertodd+1.436
itiz+1.432
Neg logit contributions
icult-1.680
-1.626
orm-1.614
awar-1.607
nown-1.586
Token from
Token ID422
Feature activation+1.84e-01

Pos logit contributions
icult+1.072
orm+1.059
+1.026
awar+1.021
 iceberg+1.018
Neg logit contributions
 Nose-1.156
aspers-1.135
ertodd-1.111
 bluff-1.097
itiz-1.094
Token disk
Token ID11898
Feature activation+1.03e-01

Pos logit contributions
 Nose+1.585
aspers+1.538
 bluff+1.497
ertodd+1.485
   +1.481
Neg logit contributions
icult-1.687
-1.630
orm-1.613
awar-1.609
nown-1.582
Token and
Token ID290
Feature activation-8.51e-02

Pos logit contributions
 Nose+0.882
aspers+0.863
ertodd+0.839
 bluff+0.838
itiz+0.832
Neg logit contributions
icult-0.941
orm-0.907
-0.903
awar-0.897
Dub-0.884
Token res
Token ID581
Feature activation-1.24e+00

Pos logit contributions
icult+0.747
orm+0.732
+0.714
awar+0.714
Dub+0.704
Neg logit contributions
 Nose-0.751
aspers-0.740
ertodd-0.724
 bluff-0.709
itiz-0.705
Tokenizes
Token ID4340
Feature activation+5.25e-02

Pos logit contributions
aj+8.640
icult+8.355
orm+8.162
awar+7.659
buff+7.627
Neg logit contributions
 Nose-11.726
 bluff-11.555
ertodd-11.511
   -11.167
aspers-10.928
Token it
Token ID340
Feature activation-1.73e-01

Pos logit contributions
 Nose+0.477
aspers+0.467
 bluff+0.453
ertodd+0.452
itiz+0.451
Neg logit contributions
icult-0.454
orm-0.435
-0.435
awar-0.432
nown-0.424
Token to
Token ID284
Feature activation+9.95e-03

Pos logit contributions
icult+1.475
orm+1.453
awar+1.409
+1.401
 iceberg+1.401
Neg logit contributions
 Nose-1.562
aspers-1.540
ertodd-1.510
 bluff-1.469
itiz-1.467
Token have
Token ID423
Feature activation-1.32e-01

Pos logit contributions
 Nose+0.088
aspers+0.086
ertodd+0.083
 bluff+0.083
itiz+0.083
Neg logit contributions
icult-0.088
orm-0.085
-0.085
awar-0.084
nown-0.083
Token a
Token ID257
Feature activation-2.41e-01

Pos logit contributions
icult+1.192
orm+1.167
awar+1.140
+1.139
 iceberg+1.129
Neg logit contributions
 Nose-1.119
aspers-1.099
ertodd-1.084
 bluff-1.061
itiz-1.056
Token a
Token ID257
Feature activation-5.25e-01

Pos logit contributions
icult+2.884
orm+2.871
Dub+2.768
aj+2.764
 iceberg+2.760
Neg logit contributions
aspers-3.132
 Nose-3.129
ertodd-3.098
 bluff-2.983
itiz-2.963
Token 2
Token ID362
Feature activation-8.60e-01

Pos logit contributions
orm+4.155
icult+4.019
 lett+4.007
 Wol+3.966
aj+3.918
Neg logit contributions
aspers-4.944
ertodd-4.900
 Nose-4.772
itiz-4.549
   -4.525
Token.
Token ID13
Feature activation-7.77e-02

Pos logit contributions
orm+6.323
aj+6.201
icult+6.107
Dub+5.963
 iceberg+5.923
Neg logit contributions
aspers-8.060
 Nose-7.967
ertodd-7.960
itiz-7.702
   -7.688
Token5
Token ID20
Feature activation-5.60e-01

Pos logit contributions
icult+0.721
orm+0.703
+0.693
awar+0.692
Dub+0.684
Neg logit contributions
 Nose-0.647
aspers-0.636
ertodd-0.621
 bluff-0.615
itiz-0.610
Token per
Token ID583
Feature activation-2.58e-01

Pos logit contributions
orm+4.196
icult+4.172
aj+4.075
awar+4.058
 iceberg+4.013
Neg logit contributions
 Nose-5.425
aspers-5.404
ertodd-5.286
itiz-5.176
   -5.117
Token cent
Token ID1247
Feature activation-1.20e+00

Pos logit contributions
icult+0.841
orm+0.813
 iceberg+0.778
aj+0.743
awar+0.741
Neg logit contributions
aspers-3.687
 Nose-3.674
ertodd-3.566
itiz-3.527
   -3.526
Token increase
Token ID2620
Feature activation-1.86e-01

Pos logit contributions
orm+7.529
 Wol+7.488
 iceberg+7.479
 lett+7.369
aj+7.363
Neg logit contributions
ertodd-11.957
aspers-11.846
 Nose-11.016
itiz-10.685
��-10.561
Token in
Token ID287
Feature activation-6.66e-01

Pos logit contributions
icult+1.587
orm+1.554
awar+1.517
+1.505
aj+1.500
Neg logit contributions
 Nose-1.673
aspers-1.646
ertodd-1.609
 bluff-1.584
itiz-1.571
Token the
Token ID262
Feature activation-4.10e-01

Pos logit contributions
orm+4.849
 lett+4.771
 Wol+4.704
 iceberg+4.673
icult+4.664
Neg logit contributions
aspers-6.576
ertodd-6.487
 Nose-6.302
itiz-6.117
 bluff-6.032
Token first
Token ID717
Feature activation-4.98e-01

Pos logit contributions
icult+3.288
orm+3.262
awar+3.179
 iceberg+3.160
Dub+3.155
Neg logit contributions
aspers-3.807
ertodd-3.767
 Nose-3.757
itiz-3.623
   -3.564
Token year
Token ID614
Feature activation-2.33e-01

Pos logit contributions
orm+3.564
icult+3.500
 iceberg+3.459
 lett+3.427
aj+3.424
Neg logit contributions
aspers-4.997
ertodd-4.935
 Nose-4.877
   -4.709
 bluff-4.699
Token reached
Token ID4251
Feature activation-1.60e-01

Pos logit contributions
 Nose+0.728
aspers+0.713
 bluff+0.697
ertodd+0.694
itiz+0.691
Neg logit contributions
icult-0.629
-0.607
orm-0.607
awar-0.600
nown-0.589
Token a
Token ID257
Feature activation-3.15e-01

Pos logit contributions
icult+1.482
orm+1.441
+1.425
awar+1.412
Dub+1.399
Neg logit contributions
 Nose-1.349
aspers-1.320
ertodd-1.284
 bluff-1.271
itiz-1.259
Token preliminary
Token ID15223
Feature activation-1.87e-01

Pos logit contributions
icult+2.582
orm+2.542
 iceberg+2.475
Dub+2.470
 lett+2.468
Neg logit contributions
 Nose-2.922
aspers-2.876
ertodd-2.839
itiz-2.739
   -2.724
Token understanding
Token ID4547
Feature activation-9.11e-02

Pos logit contributions
icult+1.548
orm+1.505
+1.475
 iceberg+1.467
awar+1.464
Neg logit contributions
 Nose-1.746
aspers-1.716
ertodd-1.681
 bluff-1.635
   -1.635
Token to
Token ID284
Feature activation-1.07e-01

Pos logit contributions
icult+0.787
orm+0.764
+0.753
awar+0.748
Dub+0.740
Neg logit contributions
 Nose-0.823
aspers-0.806
ertodd-0.786
 bluff-0.778
itiz-0.774
Token normal
Token ID3487
Feature activation-1.20e+00

Pos logit contributions
icult+0.910
orm+0.892
awar+0.869
+0.866
 iceberg+0.860
Neg logit contributions
 Nose-0.973
aspers-0.953
ertodd-0.941
itiz-0.918
 bluff-0.910
Tokenize
Token ID1096
Feature activation-2.25e-01

Pos logit contributions
orm+4.737
+4.658
aj+4.423
Dub+4.244
icult+4.183
Neg logit contributions
ertodd-15.131
 Nose-14.881
aspers-14.265
 bluff-14.053
   -13.836
Token relations
Token ID2316
Feature activation-3.99e-01

Pos logit contributions
icult+1.816
orm+1.774
+1.751
awar+1.726
Dub+1.715
Neg logit contributions
 Nose-2.146
aspers-2.102
ertodd-2.084
 bluff-2.028
itiz-2.021
Token,
Token ID11
Feature activation+3.09e-02

Pos logit contributions
icult+3.100
orm+3.087
aj+2.957
Dub+2.941
+2.934
Neg logit contributions
 Nose-3.858
ertodd-3.760
aspers-3.739
itiz-3.619
 bluff-3.619
Token including
Token ID1390
Feature activation-3.26e-01

Pos logit contributions
 Nose+0.278
aspers+0.272
 bluff+0.265
ertodd+0.263
itiz+0.263
Neg logit contributions
icult-0.269
orm-0.260
-0.257
awar-0.256
nown-0.250
Token the
Token ID262
Feature activation-5.50e-01

Pos logit contributions
icult+2.715
orm+2.685
+2.655
Dub+2.607
 iceberg+2.603
Neg logit contributions
 Nose-2.935
ertodd-2.894
aspers-2.893
 bluff-2.756
itiz-2.736
Token removed
Token ID4615
Feature activation+3.82e-02

Pos logit contributions
icult+1.693
orm+1.645
awar+1.613
+1.607
aj+1.596
Neg logit contributions
 Nose-1.556
aspers-1.536
ertodd-1.526
   -1.479
 bluff-1.473
Token and
Token ID290
Feature activation+2.04e-01

Pos logit contributions
 Nose+0.340
aspers+0.332
ertodd+0.323
 bluff+0.322
itiz+0.320
Neg logit contributions
icult-0.336
orm-0.325
-0.322
awar-0.320
Dub-0.315
Token turn
Token ID1210
Feature activation+1.90e-01

Pos logit contributions
 Nose+1.738
aspers+1.683
 bluff+1.642
itiz+1.631
ertodd+1.627
Neg logit contributions
icult-1.878
-1.804
orm-1.804
awar-1.790
nown-1.761
Token the
Token ID262
Feature activation-6.57e-02

Pos logit contributions
 Nose+1.627
aspers+1.582
 bluff+1.544
itiz+1.537
ertodd+1.515
Neg logit contributions
icult-1.741
-1.671
orm-1.667
awar-1.663
nown-1.631
Token V
Token ID569
Feature activation+6.55e-01

Pos logit contributions
icult+0.680
orm+0.662
+0.655
awar+0.653
Dub+0.646
Neg logit contributions
 Nose-0.479
aspers-0.469
ertodd-0.455
 bluff-0.449
itiz-0.446
Tokenitus
Token ID17506
Feature activation-1.20e+00

Pos logit contributions
aspers+4.836
itiz+4.754
 Nose+4.744
irts+4.581
ertodd+4.560
Neg logit contributions
-6.371
icult-6.237
 lett-6.117
awar-6.072
 iceberg-6.066
Token into
Token ID656
Feature activation+2.49e-04

Pos logit contributions
 Wol+8.556
icult+8.406
orm+8.399
aj+8.373
Dub+8.357
Neg logit contributions
ertodd-10.805
aspers-10.336
 Nose-9.627
��-9.603
   -9.493
Token a
Token ID257
Feature activation-3.18e-01

Pos logit contributions
 Nose+0.002
aspers+0.002
ertodd+0.002
 bluff+0.002
itiz+0.002
Neg logit contributions
icult-0.002
orm-0.002
-0.002
awar-0.002
nown-0.002
Token fixed
Token ID5969
Feature activation-3.09e-01

Pos logit contributions
icult+2.714
orm+2.669
 iceberg+2.614
 lett+2.610
Dub+2.607
Neg logit contributions
aspers-2.771
 Nose-2.743
ertodd-2.727
   -2.629
itiz-2.623
Token gear
Token ID7733
Feature activation-3.97e-01

Pos logit contributions
icult+2.695
orm+2.644
Dub+2.572
 iceberg+2.570
awar+2.546
Neg logit contributions
aspers-2.687
 Nose-2.674
ertodd-2.645
   -2.560
 bluff-2.540
Token bike
Token ID7161
Feature activation-6.00e-01

Pos logit contributions
icult+3.859
orm+3.817
 iceberg+3.706
Dub+3.700
aj+3.696
Neg logit contributions
 Nose-2.998
aspers-2.982
ertodd-2.970
 bluff-2.816
   -2.811
Token international
Token ID3230
Feature activation-3.58e-01

Pos logit contributions
 Nose+0.591
aspers+0.574
ertodd+0.557
 bluff+0.556
itiz+0.553
Neg logit contributions
icult-0.678
orm-0.657
-0.652
awar-0.649
nown-0.639
Token treaties
Token ID30734
Feature activation-3.22e-02

Pos logit contributions
icult+3.016
orm+3.008
awar+2.889
aj+2.887
 lett+2.883
Neg logit contributions
 Nose-3.174
ertodd-3.162
aspers-3.098
itiz-2.988
 bluff-2.988
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
icult+0.296
orm+0.287
+0.284
awar+0.283
Dub+0.279
Neg logit contributions
 Nose-0.273
aspers-0.267
ertodd-0.260
 bluff-0.258
itiz-0.256
Token Any
Token ID4377
Feature activation-9.90e-02

Pos logit contributions
icult+1.508
orm+1.472
+1.448
awar+1.444
Dub+1.440
Neg logit contributions
aspers-1.352
 Nose-1.348
ertodd-1.314
 bluff-1.307
itiz-1.288
Token reproduction
Token ID20728
Feature activation-4.41e-02

Pos logit contributions
icult+0.827
orm+0.802
+0.793
awar+0.787
Dub+0.774
Neg logit contributions
 Nose-0.921
aspers-0.905
ertodd-0.884
 bluff-0.876
itiz-0.872
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
icult+0.391
orm+0.379
+0.375
awar+0.373
Dub+0.367
Neg logit contributions
 Nose-0.389
aspers-0.380
ertodd-0.370
 bluff-0.369
itiz-0.366
Token copying
Token ID23345
Feature activation-9.96e-02

Pos logit contributions
 lett+7.406
Dub+7.196
orm+7.116
 iceberg+7.092
 Asgard+7.069
Neg logit contributions
aspers-11.959
ertodd-11.726
 Nose-11.084
   -10.877
itiz-10.728
Token,
Token ID11
Feature activation-9.22e-01

Pos logit contributions
icult+0.901
orm+0.872
+0.865
awar+0.861
Dub+0.847
Neg logit contributions
 Nose-0.861
aspers-0.842
ertodd-0.819
 bluff-0.817
itiz-0.810
Token or
Token ID393
Feature activation-7.88e-01

Pos logit contributions
orm+6.278
icult+6.117
 lett+6.082
Dub+6.042
awar+6.026
Neg logit contributions
aspers-9.067
ertodd-8.862
 Nose-8.835
itiz-8.573
   -8.329
Token redistribution
Token ID41425
Feature activation-2.20e-01

Pos logit contributions
orm+5.638
icult+5.600
 lett+5.517
Dub+5.510
aj+5.447
Neg logit contributions
aspers-7.773
ertodd-7.569
 Nose-7.418
itiz-7.318
 bluff-7.061
Token (
Token ID357
Feature activation-6.43e-01

Pos logit contributions
icult+1.870
orm+1.819
+1.795
awar+1.770
Dub+1.767
Neg logit contributions
 Nose-1.985
aspers-1.962
ertodd-1.915
 bluff-1.900
itiz-1.877
Token said
Token ID531
Feature activation-2.79e-01

Pos logit contributions
icult+0.459
orm+0.452
Dub+0.437
awar+0.437
aj+0.435
Neg logit contributions
 Nose-0.543
aspers-0.538
ertodd-0.525
 bluff-0.513
   -0.511
Token she
Token ID673
Feature activation+2.57e-01

Pos logit contributions
orm+2.091
icult+2.087
aj+2.000
 iceberg+1.991
awar+1.948
Neg logit contributions
 Nose-2.764
aspers-2.759
ertodd-2.758
   -2.582
 bluff-2.566
Token risked
Token ID42179
Feature activation+2.30e-01

Pos logit contributions
 Nose+1.960
aspers+1.903
 bluff+1.881
itiz+1.859
ertodd+1.845
Neg logit contributions
icult-2.570
-2.529
orm-2.503
awar-2.477
Dub-2.447
Token severe
Token ID6049
Feature activation+1.15e-01

Pos logit contributions
 Nose+2.006
aspers+1.952
ertodd+1.907
 bluff+1.904
itiz+1.891
Neg logit contributions
icult-2.052
orm-1.987
-1.983
awar-1.961
nown-1.931
Token infection
Token ID10280
Feature activation-2.49e-01

Pos logit contributions
 Nose+0.887
aspers+0.866
ertodd+0.845
 bluff+0.830
itiz+0.824
Neg logit contributions
icult-1.150
orm-1.122
awar-1.102
-1.099
 iceberg-1.092
Token and
Token ID290
Feature activation-1.18e+00

Pos logit contributions
orm+1.776
icult+1.762
aj+1.695
 iceberg+1.693
awar+1.676
Neg logit contributions
aspers-2.564
 Nose-2.534
ertodd-2.490
itiz-2.418
 bluff-2.410
Token scar
Token ID10153
Feature activation-3.21e-01

Pos logit contributions
awar+6.556
 iceberg+6.418
orm+6.049
 Wol+5.849
icult+5.843
Neg logit contributions
aspers-12.243
irts-11.901
 Nose-11.811
ertodd-11.632
itiz-11.602
Tokenring
Token ID1806
Feature activation-1.36e-01

Pos logit contributions
orm+2.883
icult+2.866
awar+2.792
aj+2.750
Dub+2.728
Neg logit contributions
 Nose-2.767
aspers-2.742
ertodd-2.646
itiz-2.586
 bluff-2.518
Token if
Token ID611
Feature activation-3.72e-01

Pos logit contributions
icult+1.075
orm+1.043
awar+1.023
+1.011
Dub+1.004
Neg logit contributions
 Nose-1.324
aspers-1.307
ertodd-1.284
 bluff-1.260
itiz-1.259
Token she
Token ID673
Feature activation+2.22e-01

Pos logit contributions
orm+2.617
icult+2.595
aj+2.499
 iceberg+2.493
 Asgard+2.430
Neg logit contributions
aspers-3.827
 Nose-3.792
ertodd-3.731
   -3.578
 bluff-3.534
Token didn
Token ID1422
Feature activation-2.17e-01

Pos logit contributions
 Nose+1.631
aspers+1.581
ertodd+1.535
 bluff+1.535
itiz+1.525
Neg logit contributions
icult-2.289
-2.227
orm-2.226
awar-2.202
Dub-2.173
Token to
Token ID284
Feature activation-3.83e-02

Pos logit contributions
icult+1.968
orm+1.927
+1.900
awar+1.883
aj+1.858
Neg logit contributions
 Nose-1.981
aspers-1.942
ertodd-1.890
 bluff-1.875
itiz-1.855
Token fully
Token ID3938
Feature activation-2.03e-01

Pos logit contributions
icult+0.337
orm+0.327
+0.323
awar+0.322
 iceberg+0.316
Neg logit contributions
 Nose-0.341
aspers-0.334
ertodd-0.325
 bluff-0.322
itiz-0.322
Token enter
Token ID3802
Feature activation-4.29e-01

Pos logit contributions
icult+1.678
orm+1.647
+1.604
awar+1.603
 iceberg+1.585
Neg logit contributions
 Nose-1.910
aspers-1.865
ertodd-1.826
itiz-1.805
 bluff-1.785
Token the
Token ID262
Feature activation-7.22e-01

Pos logit contributions
icult+3.470
orm+3.420
+3.356
awar+3.337
aj+3.288
Neg logit contributions
 Nose-4.007
aspers-3.942
ertodd-3.830
 bluff-3.786
itiz-3.735
Token fast
Token ID3049
Feature activation-9.34e-01

Pos logit contributions
icult+4.835
orm+4.664
awar+4.588
 iceberg+4.573
+4.554
Neg logit contributions
 Nose-7.424
aspers-7.367
ertodd-7.178
 bluff-7.004
itiz-7.002
Tokened
Token ID276
Feature activation-1.17e+00

Pos logit contributions
orm+3.293
icult+3.042
aj+3.012
awar+2.718
nown+2.497
Neg logit contributions
aspers-12.366
 Nose-12.288
ertodd-11.938
 bluff-11.803
thora-11.637
Token state
Token ID1181
Feature activation-8.67e-01

Pos logit contributions
orm+5.897
icult+5.668
+5.665
aj+5.356
 iceberg+5.272
Neg logit contributions
 Nose-13.066
aspers-12.929
ertodd-12.599
 bluff-12.428
itiz-12.385
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
orm+6.423
icult+6.274
aj+6.174
 iceberg+6.084
+6.074
Neg logit contributions
 Nose-8.032
aspers-7.978
ertodd-7.666
 bluff-7.499
itiz-7.490
Token
Token ID198
Feature activation+3.89e-02

Pos logit contributions
icult+1.982
orm+1.944
awar+1.907
Dub+1.898
aj+1.898
Neg logit contributions
aspers-2.363
 Nose-2.331
ertodd-2.323
 bluff-2.293
itiz-2.279
Token
Token ID198
Feature activation-3.23e-01

Pos logit contributions
 Nose+0.360
aspers+0.357
ertodd+0.349
 bluff+0.345
itiz+0.342
Neg logit contributions
icult-0.324
orm-0.318
awar-0.311
Dub-0.309
aj-0.308
TokenWhen
Token ID2215
Feature activation-2.83e-01

Pos logit contributions
icult+2.631
Dub+2.601
orm+2.599
+2.566
aj+2.560
Neg logit contributions
 Nose-3.049
aspers-2.951
ertodd-2.941
 bluff-2.921
itiz-2.833
Token number
Token ID1271
Feature activation+1.08e-01

Pos logit contributions
icult+0.593
orm+0.578
+0.570
awar+0.565
Dub+0.561
Neg logit contributions
 Nose-0.647
aspers-0.639
ertodd-0.624
itiz-0.611
 bluff-0.611
Token of
Token ID286
Feature activation+1.16e-01

Pos logit contributions
 Nose+0.817
aspers+0.785
 bluff+0.781
   +0.764
itiz+0.763
Neg logit contributions
icult-1.089
orm-1.063
awar-1.058
-1.042
nown-1.036
Token steps
Token ID4831
Feature activation-5.40e-02

Pos logit contributions
 Nose+1.043
aspers+1.010
 bluff+0.999
itiz+0.985
ertodd+0.981
Neg logit contributions
icult-1.018
orm-0.985
-0.975
awar-0.971
nown-0.956
Token planned
Token ID6027
Feature activation-3.42e-01

Pos logit contributions
icult+0.458
orm+0.444
+0.439
awar+0.436
Dub+0.430
Neg logit contributions
 Nose-0.496
aspers-0.486
ertodd-0.475
 bluff-0.472
itiz-0.468
Token to
Token ID284
Feature activation-3.36e-01

Pos logit contributions
icult+2.724
orm+2.696
+2.654
Dub+2.605
aj+2.600
Neg logit contributions
 Nose-3.206
aspers-3.178
ertodd-3.111
 bluff-3.024
itiz-2.999
Token normal
Token ID3487
Feature activation-1.16e+00

Pos logit contributions
icult+2.700
orm+2.692
+2.601
 iceberg+2.591
aj+2.577
Neg logit contributions
 Nose-3.153
ertodd-3.101
aspers-3.088
itiz-2.954
 bluff-2.917
Tokenize
Token ID1096
Feature activation-1.17e-01

Pos logit contributions
orm+4.280
+4.235
aj+4.004
Dub+3.806
icult+3.801
Neg logit contributions
ertodd-14.633
 Nose-14.573
aspers-14.032
 bluff-13.717
   -13.547
Token relations
Token ID2316
Feature activation-4.52e-01

Pos logit contributions
icult+0.946
orm+0.918
+0.907
awar+0.898
Dub+0.887
Neg logit contributions
 Nose-1.118
aspers-1.098
ertodd-1.077
 bluff-1.063
itiz-1.055
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
icult+3.594
orm+3.588
aj+3.451
Dub+3.424
+3.422
Neg logit contributions
 Nose-4.211
ertodd-4.123
aspers-4.114
 bluff-3.984
itiz-3.953
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
icult+1.268
orm+1.232
+1.220
awar+1.210
Dub+1.198
Neg logit contributions
 Nose-1.307
aspers-1.287
ertodd-1.256
 bluff-1.248
itiz-1.236
Token
Token ID198
Feature activation-1.77e-01

Pos logit contributions
orm+1.185
icult+1.182
Dub+1.164
aj+1.163
awar+1.140
Neg logit contributions
aspers-1.562
 Nose-1.559
ertodd-1.534
 bluff-1.517
itiz-1.485
Token.
Token ID13
Feature activation+5.77e-02

Pos logit contributions
icult+0.065
orm+0.065
awar+0.063
+0.063
aj+0.063
Neg logit contributions
 Nose-0.060
aspers-0.059
 bluff-0.058
ertodd-0.058
itiz-0.057
Tokenx
Token ID87
Feature activation+2.61e-01

Pos logit contributions
 Nose+0.370
aspers+0.356
ertodd+0.350
   +0.339
itiz+0.337
Neg logit contributions
icult-0.645
-0.630
orm-0.627
awar-0.624
Dub-0.620
Token.
Token ID13
Feature activation-2.05e-01

Pos logit contributions
 Nose+2.004
aspers+1.940
ertodd+1.877
   +1.871
 bluff+1.867
Neg logit contributions
icult-2.623
-2.534
orm-2.534
awar-2.510
nown-2.482
Tokenx
Token ID87
Feature activation-1.58e-01

Pos logit contributions
icult+2.214
orm+2.157
+2.142
awar+2.133
Dub+2.106
Neg logit contributions
 Nose-1.424
aspers-1.381
ertodd-1.341
 bluff-1.322
itiz-1.315
Token.
Token ID13
Feature activation-7.04e-01

Pos logit contributions
icult+1.373
orm+1.362
aj+1.340
Dub+1.330
awar+1.329
Neg logit contributions
aspers-1.373
 Nose-1.367
ertodd-1.350
 bluff-1.338
itiz-1.318
Token80
Token ID1795
Feature activation-1.15e+00

Pos logit contributions
icult+4.461
orm+4.272
+4.209
awar+4.175
aj+4.135
Neg logit contributions
 Nose-7.711
aspers-7.583
 bluff-7.439
itiz-7.412
ertodd-7.386
Token 106
Token ID15696
Feature activation+6.47e-02

Pos logit contributions
icult+6.878
 Asgard+6.815
orm+6.768
 Wol+6.731
 iceberg+6.694
Neg logit contributions
aspers-11.516
ertodd-11.190
 bluff-11.108
itiz-10.867
 Nose-10.785
Token27
Token ID1983
Feature activation-1.39e-01

Pos logit contributions
 Nose+0.568
aspers+0.550
ertodd+0.533
 bluff+0.532
   +0.531
Neg logit contributions
icult-0.583
orm-0.560
-0.557
awar-0.553
nown-0.545
Token66
Token ID2791
Feature activation+1.21e-01

Pos logit contributions
icult+1.189
orm+1.165
+1.142
awar+1.141
Dub+1.134
Neg logit contributions
 Nose-1.238
aspers-1.226
ertodd-1.198
 bluff-1.188
itiz-1.180
Token x
Token ID2124
Feature activation-2.37e-02

Pos logit contributions
 Nose+1.119
aspers+1.070
ertodd+1.069
 bluff+1.047
   +1.038
Neg logit contributions
icult-1.031
orm-0.985
-0.984
awar-0.977
nown-0.968
Token.
Token ID13
Feature activation-6.74e-02

Pos logit contributions
icult+0.214
orm+0.212
awar+0.207
aj+0.206
+0.206
Neg logit contributions
 Nose-0.201
aspers-0.199
ertodd-0.194
 bluff-0.193
itiz-0.190
Token of
Token ID286
Feature activation-6.61e-02

Pos logit contributions
 Nose+2.155
 bluff+2.059
aspers+2.048
itiz+2.014
   +1.985
Neg logit contributions
icult-2.585
-2.529
orm-2.506
awar-2.483
nown-2.436
Token a
Token ID257
Feature activation+1.30e-02

Pos logit contributions
icult+0.618
orm+0.600
+0.594
awar+0.591
Dub+0.582
Neg logit contributions
 Nose-0.551
aspers-0.539
ertodd-0.524
 bluff-0.521
itiz-0.517
Token missing
Token ID4814
Feature activation-1.15e-01

Pos logit contributions
 Nose+0.108
aspers+0.106
ertodd+0.103
 bluff+0.102
itiz+0.101
Neg logit contributions
icult-0.122
orm-0.118
-0.117
awar-0.116
Dub-0.115
Token 1982
Token ID14489
Feature activation-2.73e-01

Pos logit contributions
icult+1.164
orm+1.141
+1.122
awar+1.118
Dub+1.109
Neg logit contributions
 Nose-0.852
aspers-0.842
ertodd-0.823
 bluff-0.806
itiz-0.798
Token V
Token ID569
Feature activation+8.54e-01

Pos logit contributions
icult+2.169
orm+2.123
awar+2.051
Dub+2.051
aj+2.045
Neg logit contributions
 Nose-2.584
aspers-2.572
ertodd-2.555
 bluff-2.473
   -2.460
Tokenitus
Token ID17506
Feature activation-1.15e+00

Pos logit contributions
aspers+5.842
itiz+5.782
 Nose+5.657
irts+5.602
   +5.554
Neg logit contributions
-8.470
icult-8.314
 lett-8.244
awar-8.141
 iceberg-8.119
Token road
Token ID2975
Feature activation-2.78e-01

Pos logit contributions
orm+8.465
 Wol+8.441
icult+8.306
aj+8.257
 Gan+8.104
Neg logit contributions
ertodd-10.441
aspers-10.006
 Nose-9.456
irts-9.121
   -9.111
Token bike
Token ID7161
Feature activation-4.12e-01

Pos logit contributions
icult+2.974
orm+2.913
+2.858
awar+2.854
Dub+2.838
Neg logit contributions
 Nose-1.916
aspers-1.866
ertodd-1.821
 bluff-1.777
   -1.768
Token.
Token ID13
Feature activation-2.56e-01

Pos logit contributions
icult+3.488
orm+3.486
+3.375
Dub+3.364
 lett+3.364
Neg logit contributions
 Nose-3.596
aspers-3.553
ertodd-3.491
   -3.413
itiz-3.382
Token
Token ID198
Feature activation-2.20e-01

Pos logit contributions
icult+2.128
orm+2.085
awar+2.046
+2.041
Dub+2.032
Neg logit contributions
 Nose-2.331
aspers-2.328
ertodd-2.261
 bluff-2.245
itiz-2.242
Token
Token ID198
Feature activation-2.04e-01

Pos logit contributions
orm+1.609
icult+1.590
aj+1.574
Dub+1.563
awar+1.534
Neg logit contributions
aspers-2.218
 Nose-2.216
ertodd-2.188
 bluff-2.151
itiz-2.119
Token chooses
Token ID19769
Feature activation-4.22e-01

Pos logit contributions
icult+3.008
orm+2.985
awar+2.867
aj+2.849
 iceberg+2.847
Neg logit contributions
 Nose-3.346
aspers-3.301
ertodd-3.272
   -3.139
itiz-3.125
Token to
Token ID284
Feature activation-2.20e-01

Pos logit contributions
icult+3.451
orm+3.424
awar+3.321
aj+3.316
 Asgard+3.314
Neg logit contributions
ertodd-3.801
 Nose-3.778
aspers-3.753
itiz-3.622
   -3.582
Token go
Token ID467
Feature activation+8.82e-02

Pos logit contributions
icult+1.783
orm+1.754
awar+1.723
 iceberg+1.701
nown+1.687
Neg logit contributions
 Nose-2.077
aspers-2.040
ertodd-2.013
itiz-1.977
   -1.940
Token alone
Token ID3436
Feature activation-1.60e-01

Pos logit contributions
 Nose+0.763
aspers+0.743
 bluff+0.728
ertodd+0.718
itiz+0.717
Neg logit contributions
icult-0.802
orm-0.772
-0.767
awar-0.762
Dub-0.752
Token to
Token ID284
Feature activation-4.36e-01

Pos logit contributions
icult+1.359
orm+1.338
awar+1.309
+1.306
nown+1.301
Neg logit contributions
 Nose-1.446
aspers-1.425
ertodd-1.391
 bluff-1.359
itiz-1.359
Token Mord
Token ID29548
Feature activation-1.15e+00

Pos logit contributions
icult+3.549
orm+3.543
awar+3.529
+3.479
 Asgard+3.475
Neg logit contributions
 Nose-3.914
ertodd-3.905
aspers-3.900
itiz-3.770
   -3.688
Tokenor
Token ID273
Feature activation-3.67e-01

Pos logit contributions
orm+4.586
aj+3.923
awar+3.505
icult+3.267
 Asgard+3.254
Neg logit contributions
ertodd-15.235
 Nose-14.655
 bluff-14.609
��-14.207
aspers-14.182
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
icult+3.039
orm+3.013
nown+2.966
awar+2.931
aj+2.903
Neg logit contributions
 Nose-3.319
aspers-3.307
ertodd-3.271
itiz-3.134
   -3.122
Token but
Token ID475
Feature activation-5.45e-01

Pos logit contributions
icult+1.541
orm+1.505
awar+1.486
+1.480
nown+1.469
Neg logit contributions
 Nose-1.487
aspers-1.469
ertodd-1.443
itiz-1.397
   -1.395
Token Sam
Token ID3409
Feature activation-4.34e-01

Pos logit contributions
orm+4.236
icult+4.176
nown+4.119
 iceberg+4.107
 Asgard+4.090
Neg logit contributions
ertodd-5.109
aspers-5.047
 Nose-4.965
itiz-4.732
   -4.725
Token guesses
Token ID44774
Feature activation-7.55e-02

Pos logit contributions
icult+3.630
orm+3.621
aj+3.488
awar+3.473
+3.430
Neg logit contributions
 Nose-3.914
ertodd-3.870
aspers-3.855
itiz-3.670
   -3.657
Token
Token ID247
Feature activation-1.85e-01

Pos logit contributions
icult+0.016
orm+0.016
+0.015
awar+0.015
Dub+0.015
Neg logit contributions
 Nose-0.013
aspers-0.013
ertodd-0.013
 bluff-0.013
itiz-0.013
Tokens
Token ID82
Feature activation-8.50e-01

Pos logit contributions
icult+1.587
orm+1.541
+1.524
awar+1.513
Dub+1.498
Neg logit contributions
 Nose-1.669
aspers-1.628
ertodd-1.603
 bluff-1.593
itiz-1.570
Token weak
Token ID4939
Feature activation-7.49e-01

Pos logit contributions
orm+6.886
icult+6.768
 Asgard+6.725
aj+6.540
 iceberg+6.527
Neg logit contributions
aspers-7.206
ertodd-7.206
 Nose-7.128
itiz-6.989
   -6.925
Token coalition
Token ID9906
Feature activation-6.26e-01

Pos logit contributions
orm+6.540
icult+6.530
aj+6.280
 Asgard+6.222
awar+6.132
Neg logit contributions
 Nose-6.120
ertodd-6.003
aspers-5.929
itiz-5.870
   -5.846
Token of
Token ID286
Feature activation-8.64e-01

Pos logit contributions
icult+4.566
orm+4.403
aj+4.290
 Asgard+4.206
 iceberg+4.205
Neg logit contributions
 Nose-6.300
aspers-6.163
ertodd-6.060
itiz-5.922
 bluff-5.829
Token Social
Token ID5483
Feature activation-1.14e+00

Pos logit contributions
orm+6.640
icult+6.602
 iceberg+6.515
 Asgard+6.514
aj+6.460
Neg logit contributions
ertodd-7.666
aspers-7.578
 Nose-7.509
itiz-7.313
   -7.228
Token Democrats
Token ID4956
Feature activation-5.41e-01

Pos logit contributions
orm+7.398
icult+7.359
 Asgard+7.116
aj+6.925
awar+6.602
Neg logit contributions
 bluff-11.657
 Nose-11.394
ertodd-11.138
aspers-10.555
itiz-10.503
Token and
Token ID290
Feature activation-3.69e-01

Pos logit contributions
icult+4.235
orm+4.182
+4.096
aj+4.037
 iceberg+3.988
Neg logit contributions
 Nose-5.088
aspers-4.995
ertodd-4.939
 bluff-4.821
itiz-4.819
Token Greens
Token ID18753
Feature activation-2.93e-01

Pos logit contributions
icult+2.477
orm+2.433
aj+2.351
 iceberg+2.327
 Asgard+2.311
Neg logit contributions
 Nose-3.936
aspers-3.900
ertodd-3.873
itiz-3.809
 bluff-3.788
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
icult+2.537
orm+2.484
+2.436
awar+2.418
aj+2.407
Neg logit contributions
 Nose-2.602
aspers-2.537
ertodd-2.500
 bluff-2.450
itiz-2.442
Token and
Token ID290
Feature activation-3.28e-01

Pos logit contributions
icult+1.754
orm+1.698
+1.669
awar+1.669
 iceberg+1.654
Neg logit contributions
 Nose-1.895
aspers-1.867
ertodd-1.848
itiz-1.796
 bluff-1.790
Token and
Token ID290
Feature activation-5.93e-03

Pos logit contributions
icult+0.090
orm+0.087
+0.086
awar+0.086
Dub+0.085
Neg logit contributions
 Nose-0.094
aspers-0.092
ertodd-0.090
 bluff-0.089
itiz-0.089
Token shudder
Token ID50130
Feature activation-4.07e-02

Pos logit contributions
icult+0.053
orm+0.052
+0.051
awar+0.051
Dub+0.050
Neg logit contributions
 Nose-0.052
aspers-0.051
ertodd-0.049
 bluff-0.049
itiz-0.049
Token.
Token ID13
Feature activation-3.70e-01

Pos logit contributions
icult+0.363
orm+0.353
+0.349
awar+0.347
nown+0.342
Neg logit contributions
 Nose-0.356
aspers-0.349
ertodd-0.340
 bluff-0.338
itiz-0.335
Token
Token ID447
Feature activation-2.92e-01

Pos logit contributions
icult+2.854
orm+2.804
Dub+2.802
+2.759
awar+2.757
Neg logit contributions
aspers-3.504
ertodd-3.490
 bluff-3.426
 Nose-3.417
itiz-3.378
Token
Token ID251
Feature activation-3.85e-01

Pos logit contributions
icult+2.294
orm+2.236
+2.205
awar+2.195
Dub+2.161
Neg logit contributions
 Nose-2.825
aspers-2.784
ertodd-2.722
 bluff-2.722
itiz-2.693
Token[
Token ID58
Feature activation-1.12e+00

Pos logit contributions
icult+3.039
orm+2.982
Dub+2.951
+2.922
aj+2.897
Neg logit contributions
ertodd-3.596
aspers-3.575
 Nose-3.550
 bluff-3.545
itiz-3.466
Token19
Token ID1129
Feature activation-2.88e-01

Pos logit contributions
aj+6.131
orm+6.049
icult+5.953
nown+5.804
+5.623
Neg logit contributions
 Nose-11.939
ertodd-11.901
aspers-11.671
 bluff-11.631
itiz-11.376
Token]
Token ID60
Feature activation-4.16e-01

Pos logit contributions
icult+2.662
orm+2.585
+2.552
awar+2.540
Dub+2.503
Neg logit contributions
 Nose-2.424
aspers-2.373
ertodd-2.307
 bluff-2.299
itiz-2.278
Token Myth
Token ID18900
Feature activation-1.45e-01

Pos logit contributions
icult+3.167
Dub+3.116
orm+3.113
 Wol+3.057
 Asgard+3.049
Neg logit contributions
ertodd-3.966
aspers-3.960
 bluff-3.884
 Nose-3.873
itiz-3.841
Tokenos
Token ID418
Feature activation-3.27e-01

Pos logit contributions
icult+1.443
orm+1.408
+1.386
awar+1.383
aj+1.366
Neg logit contributions
 Nose-1.114
aspers-1.088
ertodd-1.064
 bluff-1.053
itiz-1.038
Token became
Token ID2627
Feature activation+2.33e-01

Pos logit contributions
icult+2.836
orm+2.784
aj+2.705
awar+2.705
+2.704
Neg logit contributions
 Nose-2.868
aspers-2.815
ertodd-2.789
 bluff-2.721
itiz-2.680
TokenK
Token ID42
Feature activation+5.86e-02

Pos logit contributions
orm+3.908
aj+3.864
icult+3.851
+3.846
awar+3.821
Neg logit contributions
ertodd-4.801
aspers-4.773
 Nose-4.709
 bluff-4.638
itiz-4.605
Token AND
Token ID5357
Feature activation-3.01e-01

Pos logit contributions
 Nose+0.545
aspers+0.532
 bluff+0.516
ertodd+0.516
   +0.514
Neg logit contributions
icult-0.494
orm-0.476
-0.471
awar-0.468
Dub-0.461
Token AP
Token ID3486
Feature activation-8.26e-01

Pos logit contributions
icult+2.537
orm+2.510
awar+2.474
+2.470
aj+2.462
Neg logit contributions
 Nose-2.653
aspers-2.643
ertodd-2.627
 bluff-2.565
itiz-2.558
TokenAC
Token ID2246
Feature activation+4.12e-01

Pos logit contributions
icult+4.656
+4.609
awar+4.498
aj+4.484
Dub+4.479
Neg logit contributions
 Nose-9.156
itiz-8.945
aspers-8.935
ertodd-8.904
 bluff-8.864
TokenHE
Token ID13909
Feature activation+2.02e-01

Pos logit contributions
 Nose+2.804
aspers+2.696
   +2.633
ertodd+2.573
itiz+2.566
Neg logit contributions
icult-4.509
orm-4.336
awar-4.330
-4.293
nown-4.246
Token T
Token ID309
Feature activation-1.11e+00

Pos logit contributions
 Nose+1.561
aspers+1.469
   +1.455
 bluff+1.432
ertodd+1.407
Neg logit contributions
icult-2.046
orm-1.977
-1.953
awar-1.939
nown-1.933
TokenOC
Token ID4503
Feature activation+3.96e-01

Pos logit contributions
orm+5.082
aj+4.863
icult+4.198
IUM+4.188
GREEN+4.159
Neg logit contributions
ertodd-13.431
 bluff-13.325
 Nose-13.164
��-12.735
itiz-12.702
Token RE
Token ID4526
Feature activation-4.16e-01

Pos logit contributions
 Nose+3.535
   +3.383
aspers+3.360
 bluff+3.271
ertodd+3.201
Neg logit contributions
icult-3.499
orm-3.319
-3.275
nown-3.248
awar-3.240
TokenP
Token ID47
Feature activation-1.07e-01

Pos logit contributions
Dub+3.078
aj+2.960
orm+2.917
icult+2.888
+2.885
Neg logit contributions
ertodd-4.266
 Nose-4.109
aspers-4.045
 bluff-3.987
itiz-3.935
TokenORTS
Token ID33002
Feature activation-1.03e-01

Pos logit contributions
icult+0.640
orm+0.629
+0.610
aj+0.602
Dub+0.602
Neg logit contributions
 Nose-1.221
ertodd-1.220
aspers-1.218
 bluff-1.202
itiz-1.177
Token 100
Token ID1802
Feature activation-2.28e-01

Pos logit contributions
icult+0.864
orm+0.838
+0.828
awar+0.825
Dub+0.814
Neg logit contributions
 Nose-0.953
aspers-0.942
ertodd-0.923
 bluff-0.912
itiz-0.908
Token are
Token ID389
Feature activation-1.77e-01

Pos logit contributions
icult+2.061
orm+2.032
awar+1.975
aj+1.951
nown+1.940
Neg logit contributions
 Nose-2.207
aspers-2.180
ertodd-2.166
 bluff-2.075
itiz-2.073
Token getting
Token ID1972
Feature activation-6.46e-01

Pos logit contributions
icult+1.464
orm+1.434
awar+1.403
aj+1.383
+1.380
Neg logit contributions
 Nose-1.646
aspers-1.626
ertodd-1.610
itiz-1.548
   -1.540
Token less
Token ID1342
Feature activation-4.00e-01

Pos logit contributions
icult+4.866
orm+4.801
awar+4.575
 lett+4.564
aj+4.561
Neg logit contributions
ertodd-6.272
aspers-6.118
 Nose-6.095
 bluff-5.761
   -5.748
Token than
Token ID621
Feature activation-5.18e-01

Pos logit contributions
icult+2.543
orm+2.523
awar+2.380
 iceberg+2.366
 lett+2.359
Neg logit contributions
aspers-4.413
 Nose-4.412
ertodd-4.349
 bluff-4.205
itiz-4.203
Token the
Token ID262
Feature activation-6.14e-01

Pos logit contributions
icult+3.483
orm+3.478
aj+3.324
 Asgard+3.317
 iceberg+3.314
Neg logit contributions
ertodd-5.345
aspers-5.330
 Nose-5.282
itiz-5.113
   -5.094
Token recommended
Token ID7151
Feature activation-1.11e+00

Pos logit contributions
orm+5.498
icult+5.465
 Asgard+5.340
 iceberg+5.309
aj+5.293
Neg logit contributions
ertodd-5.038
aspers-4.928
 Nose-4.845
   -4.677
itiz-4.608
Token 8
Token ID807
Feature activation-6.42e-01

Pos logit contributions
orm+6.786
 Asgard+6.661
 iceberg+6.660
 Wol+6.612
icult+6.591
Neg logit contributions
ertodd-11.552
aspers-10.839
 Nose-10.584
thora-10.072
itiz-10.030
Token 1
Token ID352
Feature activation-3.63e-01

Pos logit contributions
icult+5.178
orm+5.068
aj+4.986
+4.918
 iceberg+4.868
Neg logit contributions
 Nose-5.854
aspers-5.797
ertodd-5.635
 bluff-5.548
itiz-5.542
Token/
Token ID14
Feature activation-2.06e-01

Pos logit contributions
orm+2.608
aj+2.570
icult+2.551
Dub+2.498
 iceberg+2.472
Neg logit contributions
aspers-3.640
ertodd-3.630
 Nose-3.592
itiz-3.515
 bluff-3.494
Token2
Token ID17
Feature activation-2.33e-01

Pos logit contributions
orm+1.644
Dub+1.586
icult+1.578
aj+1.574
+1.536
Neg logit contributions
 Nose-2.004
aspers-1.966
ertodd-1.962
 bluff-1.909
itiz-1.903
Token to
Token ID284
Feature activation-5.79e-01

Pos logit contributions
icult+2.178
orm+2.117
+2.096
awar+2.084
Dub+2.054
Neg logit contributions
 Nose-1.938
aspers-1.894
ertodd-1.841
 bluff-1.832
itiz-1.818
Token Pre
Token ID3771
Feature activation+3.90e-02

Pos logit contributions
 Nose+4.611
 bluff+4.194
   +4.193
aspers+4.166
itiz+4.153
Neg logit contributions
-6.945
icult-6.852
orm-6.605
awar-6.593
nown-6.495
Tokeny
Token ID88
Feature activation-2.39e-01

Pos logit contributions
 Nose+0.457
aspers+0.452
ertodd+0.442
 bluff+0.439
itiz+0.434
Neg logit contributions
icult-0.234
orm-0.226
awar-0.220
-0.216
aj-0.214
Token."
Token ID526
Feature activation-7.34e-02

Pos logit contributions
icult+2.157
orm+2.104
+2.072
awar+2.065
Dub+2.043
Neg logit contributions
 Nose-2.045
aspers-2.017
ertodd-1.971
 bluff-1.941
itiz-1.924
Token "
Token ID366
Feature activation-9.97e-02

Pos logit contributions
icult+0.676
orm+0.656
+0.648
awar+0.646
nown+0.641
Neg logit contributions
 Nose-0.626
aspers-0.606
ertodd-0.591
 bluff-0.586
itiz-0.586
TokenRating
Token ID29321
Feature activation+6.74e-01

Pos logit contributions
icult+0.886
orm+0.859
+0.851
awar+0.846
Dub+0.836
Neg logit contributions
 Nose-0.876
aspers-0.858
ertodd-0.837
 bluff-0.832
itiz-0.824
Token:
Token ID25
Feature activation+1.11e+00

Pos logit contributions
 Nose+5.175
 bluff+4.898
   +4.842
itiz+4.728
aspers+4.720
Neg logit contributions
icult-6.459
nown-6.405
-6.328
orm-6.214
awar-6.202
Token 9
Token ID860
Feature activation+8.13e-01

Pos logit contributions
 Nose+9.419
   +8.898
 bluff+8.628
aspers+8.302
itiz+8.292
Neg logit contributions
nown-8.991
-8.719
icult-8.630
awar-8.276
orm-8.153
Token/
Token ID14
Feature activation+8.57e-01

Pos logit contributions
 Nose+5.811
 bluff+5.252
   +5.221
aspers+5.203
itiz+5.145
Neg logit contributions
nown-8.015
icult-7.958
-7.766
orm-7.682
awar-7.655
Token10
Token ID940
Feature activation+6.67e-01

Pos logit contributions
 Nose+5.851
   +5.821
aspers+5.455
 bluff+5.239
irts+5.211
Neg logit contributions
icult-8.418
awar-8.214
nown-8.103
 lett-8.062
-7.981
Token"
Token ID1
Feature activation+2.71e-01

Pos logit contributions
 Nose+5.176
   +4.775
aspers+4.772
 bluff+4.711
itiz+4.685
Neg logit contributions
icult-6.232
nown-6.147
-6.100
awar-6.089
orm-6.035
Token
Token ID198
Feature activation+1.14e-01

Pos logit contributions
 Nose+2.118
aspers+1.999
   +1.974
 bluff+1.959
itiz+1.952
Neg logit contributions
icult-2.657
orm-2.587
-2.558
nown-2.556
awar-2.539
Token unstable
Token ID21354
Feature activation-4.62e-01

Pos logit contributions
 Nose+2.911
aspers+2.830
 bluff+2.780
   +2.729
itiz+2.728
Neg logit contributions
icult-3.681
-3.589
awar-3.553
orm-3.543
Dub-3.488
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
icult+3.886
orm+3.833
awar+3.717
 iceberg+3.713
nown+3.685
Neg logit contributions
 Nose-4.175
aspers-4.089
ertodd-4.004
 bluff-3.924
   -3.874
Token like
Token ID588
Feature activation+1.27e-01

Pos logit contributions
 Nose+1.219
aspers+1.194
 bluff+1.163
ertodd+1.157
itiz+1.151
Neg logit contributions
icult-1.264
orm-1.223
-1.218
awar-1.210
Dub-1.190
Token a
Token ID257
Feature activation+1.40e-01

Pos logit contributions
 Nose+1.070
aspers+1.046
 bluff+1.014
ertodd+1.012
itiz+1.007
Neg logit contributions
icult-1.177
-1.135
orm-1.133
awar-1.124
Dub-1.107
Token house
Token ID2156
Feature activation-6.20e-02

Pos logit contributions
 Nose+1.229
aspers+1.196
 bluff+1.169
ertodd+1.161
itiz+1.151
Neg logit contributions
icult-1.261
orm-1.214
-1.213
awar-1.202
nown-1.190
Token of
Token ID286
Feature activation+1.14e+00

Pos logit contributions
icult+0.550
orm+0.534
+0.528
awar+0.525
Dub+0.517
Neg logit contributions
 Nose-0.546
aspers-0.535
ertodd-0.521
 bluff-0.518
itiz-0.514
Token cards
Token ID4116
Feature activation-1.19e-02

Pos logit contributions
 bluff+5.709
 Nose+5.653
aspers+5.161
   +5.045
itiz+5.017
Neg logit contributions
icult-13.379
-13.203
nown-12.988
awar-12.822
IUM-12.306
Token can
Token ID460
Feature activation-8.12e-02

Pos logit contributions
icult+0.106
orm+0.103
+0.101
awar+0.101
Dub+0.099
Neg logit contributions
 Nose-0.105
aspers-0.103
ertodd-0.100
 bluff-0.099
itiz-0.098
Token come
Token ID1282
Feature activation+4.34e-01

Pos logit contributions
icult+0.733
orm+0.715
+0.703
awar+0.700
 iceberg+0.689
Neg logit contributions
 Nose-0.702
aspers-0.685
ertodd-0.668
itiz-0.660
 bluff-0.658
Token crashing
Token ID21899
Feature activation+2.41e-01

Pos logit contributions
 Nose+3.139
 bluff+3.061
aspers+3.003
itiz+2.940
   +2.902
Neg logit contributions
icult-4.490
-4.387
orm-4.296
awar-4.233
nown-4.187
Token down
Token ID866
Feature activation-3.02e-01

Pos logit contributions
 Nose+1.992
aspers+1.908
 bluff+1.900
itiz+1.865
   +1.844
Neg logit contributions
icult-2.288
-2.231
orm-2.191
awar-2.178
Dub-2.154
Token
Token ID198
Feature activation+1.20e-01

Pos logit contributions
 Nose+1.248
aspers+1.198
   +1.176
ertodd+1.162
 bluff+1.159
Neg logit contributions
icult-1.256
orm-1.207
-1.194
awar-1.191
nown-1.169
Token
Token ID198
Feature activation+1.70e-01

Pos logit contributions
 Nose+1.073
aspers+1.054
ertodd+1.027
 bluff+1.022
itiz+1.013
Neg logit contributions
icult-1.050
orm-1.022
-1.008
awar-1.003
Dub-0.993
TokenSign
Token ID11712
Feature activation+1.42e-01

Pos logit contributions
 Nose+1.491
aspers+1.470
   +1.432
itiz+1.418
ertodd+1.408
Neg logit contributions
icult-1.495
orm-1.428
awar-1.426
-1.414
 iceberg-1.399
Token Up
Token ID3205
Feature activation+2.83e-01

Pos logit contributions
 Nose+1.182
aspers+1.151
ertodd+1.123
 bluff+1.114
   +1.107
Neg logit contributions
icult-1.345
-1.285
orm-1.281
awar-1.278
nown-1.262
Token:
Token ID25
Feature activation+4.48e-01

Pos logit contributions
 Nose+2.239
aspers+2.120
 bluff+2.101
   +2.086
ertodd+2.082
Neg logit contributions
icult-2.747
orm-2.661
awar-2.648
-2.643
nown-2.601
Token Stay
Token ID16160
Feature activation+1.10e+00

Pos logit contributions
 Nose+3.426
   +3.287
aspers+3.251
itiz+3.164
 bluff+3.153
Neg logit contributions
icult-4.439
awar-4.327
-4.240
nown-4.216
orm-4.194
Token on
Token ID319
Feature activation+3.72e-01

Pos logit contributions
 Nose+7.432
 bluff+6.869
   +6.568
itiz+6.546
irts+6.503
Neg logit contributions
icult-11.486
awar-10.972
 iceberg-10.727
orm-10.597
-10.563
Token top
Token ID1353
Feature activation+8.75e-01

Pos logit contributions
 Nose+2.925
aspers+2.851
ertodd+2.765
 bluff+2.763
itiz+2.744
Neg logit contributions
icult-3.651
orm-3.539
-3.510
awar-3.493
Dub-3.441
Token of
Token ID286
Feature activation+2.37e-01

Pos logit contributions
 Nose+5.481
   +5.353
itiz+5.119
ertodd+5.088
aspers+5.080
Neg logit contributions
icult-9.396
awar-9.194
-9.178
nown-9.000
orm-8.995
Token the
Token ID262
Feature activation+8.96e-02

Pos logit contributions
 Nose+2.078
aspers+2.034
ertodd+1.981
 bluff+1.971
itiz+1.956
Neg logit contributions
icult-2.115
orm-2.049
-2.030
awar-2.020
Dub-1.987
Token latest
Token ID3452
Feature activation-6.93e-02

Pos logit contributions
 Nose+1.002
aspers+0.999
ertodd+0.960
 bluff+0.957
itiz+0.947
Neg logit contributions
icult-0.582
orm-0.572
 iceberg-0.553
Dub-0.547
-0.543
Token says
Token ID1139
Feature activation+1.15e-01

Pos logit contributions
icult+0.582
orm+0.567
+0.555
awar+0.555
Dub+0.547
Neg logit contributions
 Nose-0.610
aspers-0.600
ertodd-0.587
 bluff-0.577
itiz-0.574
Token,
Token ID11
Feature activation-5.57e-02

Pos logit contributions
 Nose+0.944
aspers+0.913
 bluff+0.892
ertodd+0.886
itiz+0.883
Neg logit contributions
icult-1.089
orm-1.057
-1.054
awar-1.046
nown-1.027
Token the
Token ID262
Feature activation-1.59e-01

Pos logit contributions
icult+0.513
orm+0.498
+0.493
awar+0.491
Dub+0.483
Neg logit contributions
 Nose-0.471
aspers-0.462
ertodd-0.449
 bluff-0.446
itiz-0.443
Token state
Token ID1181
Feature activation-9.22e-03

Pos logit contributions
icult+1.392
orm+1.347
awar+1.330
+1.319
 iceberg+1.310
Neg logit contributions
 Nose-1.404
aspers-1.394
ertodd-1.366
itiz-1.334
 bluff-1.327
Token Board
Token ID5926
Feature activation-2.04e-01

Pos logit contributions
icult+0.079
orm+0.077
+0.076
awar+0.076
Dub+0.075
Neg logit contributions
 Nose-0.083
aspers-0.082
ertodd-0.080
 bluff-0.079
itiz-0.078
Token of
Token ID286
Feature activation+1.26e+00

Pos logit contributions
icult+1.885
orm+1.827
+1.808
awar+1.797
nown+1.773
Neg logit contributions
 Nose-1.715
aspers-1.681
ertodd-1.633
 bluff-1.622
itiz-1.609
Token Equal
Token ID28701
Feature activation-7.34e-02

Pos logit contributions
 Nose+9.293
 Voters+8.209
 Pharm+8.117
itiz+8.104
   +7.859
Neg logit contributions
-12.847
nown-11.184
 iceberg-11.173
awar-11.155
luaj-11.078
Tokenization
Token ID1634
Feature activation-1.50e-01

Pos logit contributions
icult+0.585
orm+0.562
awar+0.545
+0.538
aj+0.537
Neg logit contributions
 Nose-0.714
aspers-0.711
ertodd-0.703
 bluff-0.691
   -0.677
Token slapped
Token ID31213
Feature activation-1.37e-01

Pos logit contributions
icult+1.295
orm+1.266
awar+1.228
+1.222
Dub+1.219
Neg logit contributions
 Nose-1.334
aspers-1.325
ertodd-1.301
 bluff-1.263
itiz-1.251
Token a
Token ID257
Feature activation-1.76e-01

Pos logit contributions
icult+1.206
orm+1.171
awar+1.158
+1.158
Dub+1.136
Neg logit contributions
 Nose-1.205
aspers-1.192
ertodd-1.165
 bluff-1.148
itiz-1.144
Token l
Token ID300
Feature activation+2.88e-01

Pos logit contributions
icult+1.575
orm+1.545
+1.504
awar+1.500
aj+1.494
Neg logit contributions
 Nose-1.505
aspers-1.504
ertodd-1.478
itiz-1.432
 bluff-1.425
Token Game
Token ID3776
Feature activation+3.94e-01

Pos logit contributions
 Nose+1.682
aspers+1.613
   +1.574
 bluff+1.570
itiz+1.554
Neg logit contributions
icult-1.632
orm-1.572
-1.567
awar-1.545
nown-1.532
TokenSpot
Token ID32565
Feature activation+4.59e-01

Pos logit contributions
 Nose+3.444
aspers+3.301
 bluff+3.191
itiz+3.182
   +3.155
Neg logit contributions
icult-3.454
-3.375
orm-3.329
nown-3.296
awar-3.295
Token gave
Token ID2921
Feature activation+1.79e-01

Pos logit contributions
 Nose+3.961
aspers+3.799
itiz+3.747
 bluff+3.689
   +3.647
Neg logit contributions
icult-4.069
-4.050
nown-3.875
orm-3.871
awar-3.869
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
 Nose+1.554
aspers+1.502
 bluff+1.479
itiz+1.463
   +1.432
Neg logit contributions
icult-1.613
-1.563
orm-1.555
nown-1.538
awar-1.536
Token game
Token ID983
Feature activation+5.70e-01

Pos logit contributions
 Nose+1.737
aspers+1.674
 bluff+1.661
itiz+1.619
   +1.610
Neg logit contributions
icult-1.715
-1.670
orm-1.662
awar-1.638
nown-1.624
Token a
Token ID257
Feature activation+1.09e+00

Pos logit contributions
 Nose+4.480
aspers+4.275
itiz+4.191
 bluff+4.181
   +4.160
Neg logit contributions
icult-5.433
-5.413
nown-5.384
awar-5.322
orm-5.135
Token '
Token ID705
Feature activation+8.01e-01

Pos logit contributions
 Nose+9.090
 bluff+8.177
   +8.166
itiz+7.837
aspers+7.760
Neg logit contributions
nown-9.653
-9.473
icult-9.407
awar-9.053
aj-8.493
TokenTer
Token ID15156
Feature activation+1.84e-02

Pos logit contributions
 Nose+6.681
aspers+6.575
itiz+6.358
   +6.321
cle+6.210
Neg logit contributions
nown-6.601
icult-6.592
-6.547
awar-6.493
 lett-6.289
Tokenrible
Token ID5547
Feature activation+5.68e-01

Pos logit contributions
 Nose+0.113
aspers+0.110
itiz+0.105
ertodd+0.105
 bluff+0.104
Neg logit contributions
icult-0.211
-0.207
orm-0.206
awar-0.204
nown-0.203
Token'
Token ID6
Feature activation+5.98e-01

Pos logit contributions
 Nose+4.929
itiz+4.484
aspers+4.476
   +4.447
 bluff+4.439
Neg logit contributions
icult-5.213
nown-5.152
-5.068
awar-5.062
orm-4.834
Token score
Token ID4776
Feature activation+8.36e-02

Pos logit contributions
 Nose+4.427
aspers+4.043
 bluff+3.995
   +3.990
itiz+3.948
Neg logit contributions
icult-6.133
nown-6.023
-5.938
awar-5.844
orm-5.782
Tokening
Token ID278
Feature activation+6.56e-01

Pos logit contributions
icult+0.639
orm+0.631
aj+0.604
awar+0.599
Dub+0.594
Neg logit contributions
 Nose-0.796
aspers-0.778
 bluff-0.755
ertodd-0.754
itiz-0.740
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
 Nose+4.115
   +3.996
aspers+3.882
itiz+3.770
 bluff+3.695
Neg logit contributions
icult-7.256
-7.157
awar-6.979
nown-6.939
 lett-6.908
Tokenrect
Token ID2554
Feature activation+2.21e-01

Pos logit contributions
aspers+1.056
 Nose+1.055
itiz+1.018
ertodd+1.015
 bluff+1.010
Neg logit contributions
icult-1.125
awar-1.076
-1.075
orm-1.073
 iceberg-1.055
Tokenangle
Token ID9248
Feature activation+6.23e-01

Pos logit contributions
 Nose+1.915
aspers+1.889
itiz+1.833
 bluff+1.820
   +1.818
Neg logit contributions
icult-1.958
-1.921
awar-1.882
orm-1.857
nown-1.855
Tokenf
Token ID69
Feature activation+4.64e-01

Pos logit contributions
 Nose+4.794
   +4.506
aspers+4.486
 bluff+4.418
itiz+4.400
Neg logit contributions
icult-5.988
awar-5.773
-5.670
nown-5.652
orm-5.590
Token(
Token ID7
Feature activation+6.21e-01

Pos logit contributions
 Nose+3.884
aspers+3.739
itiz+3.680
   +3.635
 bluff+3.596
Neg logit contributions
icult-4.035
awar-4.020
-3.999
nown-3.989
 lett-3.935
Token0
Token ID15
Feature activation+8.79e-02

Pos logit contributions
 Nose+4.873
   +4.634
aspers+4.614
 bluff+4.559
itiz+4.531
Neg logit contributions
icult-5.781
awar-5.470
orm-5.407
-5.391
nown-5.385
Token,
Token ID11
Feature activation+3.43e-01

Pos logit contributions
 Nose+0.707
aspers+0.684
ertodd+0.661
   +0.660
 bluff+0.660
Neg logit contributions
icult-0.849
orm-0.822
-0.820
awar-0.813
Dub-0.801
Token0
Token ID15
Feature activation+2.19e-01

Pos logit contributions
 Nose+2.694
aspers+2.577
   +2.529
 bluff+2.508
itiz+2.486
Neg logit contributions
icult-3.335
orm-3.201
awar-3.184
-3.152
 iceberg-3.143
Token,
Token ID11
Feature activation+2.67e-01

Pos logit contributions
 Nose+1.687
aspers+1.623
ertodd+1.579
   +1.569
 bluff+1.563
Neg logit contributions
icult-2.186
orm-2.108
-2.108
awar-2.093
 iceberg-2.050
Token($
Token ID16763
Feature activation+2.60e-01

Pos logit contributions
 Nose+2.029
aspers+1.954
   +1.893
 bluff+1.890
itiz+1.881
Neg logit contributions
icult-2.664
orm-2.569
awar-2.549
-2.523
 iceberg-2.518
Token Project
Token ID4935
Feature activation-4.03e-03

Pos logit contributions
icult+0.601
orm+0.585
+0.576
awar+0.575
Dub+0.566
Neg logit contributions
 Nose-0.600
aspers-0.589
ertodd-0.576
 bluff-0.570
itiz-0.566
Token DI
Token ID14766
Feature activation+4.81e-01

Pos logit contributions
icult+0.025
+0.024
orm+0.023
awar+0.023
nown+0.023
Neg logit contributions
 Nose-0.047
aspers-0.046
 bluff-0.045
ertodd-0.045
itiz-0.044
Tokenva
Token ID6862
Feature activation-9.62e-02

Pos logit contributions
 Nose+4.461
aspers+4.400
 bluff+4.244
itiz+4.239
   +4.148
Neg logit contributions
icult-3.872
-3.798
nown-3.702
awar-3.667
 lett-3.590
Token X
Token ID1395
Feature activation-1.40e-01

Pos logit contributions
icult+0.802
orm+0.779
+0.767
awar+0.764
Dub+0.754
Neg logit contributions
 Nose-0.896
aspers-0.879
ertodd-0.860
 bluff-0.852
itiz-0.846
Token update
Token ID4296
Feature activation-1.76e-01

Pos logit contributions
icult+1.214
orm+1.189
awar+1.163
+1.159
Dub+1.147
Neg logit contributions
 Nose-1.262
aspers-1.238
ertodd-1.220
 bluff-1.194
itiz-1.191
Token is
Token ID318
Feature activation+2.95e-01

Pos logit contributions
icult+1.602
orm+1.567
awar+1.532
+1.528
Dub+1.518
Neg logit contributions
 Nose-1.494
aspers-1.476
ertodd-1.448
 bluff-1.417
itiz-1.399
Token in
Token ID287
Feature activation-2.38e-01

Pos logit contributions
 Nose+2.568
aspers+2.471
 bluff+2.454
   +2.435
itiz+2.399
Neg logit contributions
icult-2.638
awar-2.541
-2.537
orm-2.521
nown-2.449
Token.
Token ID13
Feature activation-2.67e-01

Pos logit contributions
icult+1.997
orm+1.976
+1.936
awar+1.916
 iceberg+1.908
Neg logit contributions
 Nose-2.172
aspers-2.131
ertodd-2.100
itiz-2.057
 bluff-2.054
Token
Token ID198
Feature activation+2.10e-01

Pos logit contributions
icult+2.157
orm+2.129
Dub+2.092
awar+2.082
+2.080
Neg logit contributions
aspers-2.456
 Nose-2.445
ertodd-2.443
 bluff-2.402
itiz-2.380
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
 Nose+1.822
aspers+1.779
ertodd+1.729
 bluff+1.723
itiz+1.713
Neg logit contributions
icult-1.886
orm-1.824
-1.813
awar-1.798
nown-1.773
TokenS
Token ID50
Feature activation+2.46e-01

Pos logit contributions
icult+0.415
orm+0.401
+0.397
awar+0.395
nown+0.388
Neg logit contributions
 Nose-0.438
aspers-0.429
ertodd-0.418
 bluff-0.416
itiz-0.413
Token members
Token ID1866
Feature activation+4.07e-01

Pos logit contributions
 Nose+2.943
aspers+2.890
itiz+2.797
ertodd+2.791
   +2.785
Neg logit contributions
icult-2.814
awar-2.696
-2.695
orm-2.649
Dub-2.611
Token.
Token ID13
Feature activation+6.76e-01

Pos logit contributions
 Nose+3.339
aspers+3.263
 bluff+3.194
itiz+3.170
   +3.167
Neg logit contributions
icult-3.825
-3.684
awar-3.637
orm-3.611
Dub-3.567
Token But
Token ID887
Feature activation+6.38e-01

Pos logit contributions
 Nose+5.590
   +5.273
aspers+5.023
itiz+4.793
ertodd+4.755
Neg logit contributions
icult-6.546
-6.199
orm-6.077
awar-6.050
 iceberg-5.944
Token with
Token ID351
Feature activation+6.51e-01

Pos logit contributions
 Nose+5.000
aspers+4.781
   +4.610
 bluff+4.584
itiz+4.529
Neg logit contributions
icult-6.215
-6.051
awar-5.904
orm-5.824
luaj-5.688
Token a
Token ID257
Feature activation+4.11e-01

Pos logit contributions
 Nose+4.887
aspers+4.574
   +4.514
itiz+4.418
 bluff+4.411
Neg logit contributions
icult-6.538
-6.211
awar-6.175
orm-6.050
Dub-6.026
Token change
Token ID1487
Feature activation+5.81e-01

Pos logit contributions
 Nose+3.579
aspers+3.406
 bluff+3.358
itiz+3.326
   +3.324
Neg logit contributions
icult-3.718
-3.551
awar-3.531
orm-3.526
nown-3.471
Token to
Token ID284
Feature activation+7.32e-01

Pos logit contributions
 Nose+4.408
aspers+4.242
itiz+4.189
 bluff+4.105
   +4.087
Neg logit contributions
icult-5.597
-5.467
awar-5.466
orm-5.360
nown-5.257
Token its
Token ID663
Feature activation+4.30e-01

Pos logit contributions
 Nose+5.557
   +5.164
aspers+5.054
itiz+5.016
ertodd+4.937
Neg logit contributions
icult-7.289
awar-6.934
-6.912
orm-6.858
Dub-6.711
Token policies
Token ID4788
Feature activation+1.74e-01

Pos logit contributions
 Nose+3.753
aspers+3.520
   +3.489
 bluff+3.474
ertodd+3.426
Neg logit contributions
icult-3.917
-3.761
awar-3.742
orm-3.734
Dub-3.631
Token at
Token ID379
Feature activation+3.24e-01

Pos logit contributions
 Nose+1.447
aspers+1.413
 bluff+1.361
   +1.357
itiz+1.357
Neg logit contributions
icult-1.632
-1.574
awar-1.569
orm-1.564
Dub-1.534
Token the
Token ID262
Feature activation+5.95e-02

Pos logit contributions
 Nose+2.626
aspers+2.537
 bluff+2.453
   +2.451
itiz+2.424
Neg logit contributions
icult-3.086
-2.987
awar-2.979
orm-2.960
Dub-2.922
Token on
Token ID319
Feature activation+1.96e-02

Pos logit contributions
 Nose+0.571
aspers+0.558
 bluff+0.544
ertodd+0.543
   +0.537
Neg logit contributions
icult-0.567
orm-0.547
-0.544
awar-0.541
nown-0.533
Token the
Token ID262
Feature activation-8.79e-03

Pos logit contributions
 Nose+0.168
aspers+0.163
 bluff+0.159
ertodd+0.159
itiz+0.158
Neg logit contributions
icult-0.179
orm-0.173
-0.172
awar-0.171
nown-0.169
Token other
Token ID584
Feature activation+1.44e-01

Pos logit contributions
icult+0.081
orm+0.078
+0.078
awar+0.077
nown+0.076
Neg logit contributions
 Nose-0.075
aspers-0.073
ertodd-0.071
 bluff-0.071
itiz-0.070
Token end
Token ID886
Feature activation-9.98e-02

Pos logit contributions
 Nose+1.563
aspers+1.513
 bluff+1.506
itiz+1.485
ertodd+1.482
Neg logit contributions
icult-0.989
-0.960
orm-0.949
awar-0.938
nown-0.933
Token of
Token ID286
Feature activation+7.85e-02

Pos logit contributions
icult+0.914
orm+0.889
+0.878
awar+0.874
Dub+0.862
Neg logit contributions
 Nose-0.847
aspers-0.832
ertodd-0.809
 bluff-0.800
itiz-0.798
Token the
Token ID262
Feature activation+4.03e-01

Pos logit contributions
 Nose+0.675
aspers+0.646
 bluff+0.640
ertodd+0.633
itiz+0.633
Neg logit contributions
icult-0.724
orm-0.698
-0.697
awar-0.687
nown-0.685
Token phone
Token ID3072
Feature activation-5.36e-02

Pos logit contributions
 Nose+3.126
 bluff+3.018
itiz+2.932
aspers+2.897
   +2.868
Neg logit contributions
icult-3.959
-3.948
orm-3.861
nown-3.849
awar-3.830
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
icult+0.488
orm+0.475
+0.468
awar+0.467
Dub+0.461
Neg logit contributions
 Nose-0.457
aspers-0.449
ertodd-0.436
 bluff-0.431
itiz-0.430
Token This
Token ID770
Feature activation+6.46e-02

Pos logit contributions
 Nose+2.534
   +2.382
aspers+2.370
 bluff+2.330
ertodd+2.313
Neg logit contributions
icult-2.675
-2.556
orm-2.547
nown-2.517
awar-2.508
Token is
Token ID318
Feature activation+8.91e-02

Pos logit contributions
 Nose+0.568
aspers+0.550
 bluff+0.542
ertodd+0.537
itiz+0.536
Neg logit contributions
icult-0.576
orm-0.560
-0.558
awar-0.553
nown-0.544
Token certainly
Token ID3729
Feature activation-2.86e-02

Pos logit contributions
 Nose+0.783
aspers+0.760
 bluff+0.747
ertodd+0.738
itiz+0.734
Neg logit contributions
icult-0.796
orm-0.771
-0.770
awar-0.760
nown-0.751
Token,
Token ID11
Feature activation-7.64e-02

Pos logit contributions
icult+0.520
orm+0.505
+0.500
awar+0.497
Dub+0.489
Neg logit contributions
 Nose-0.496
aspers-0.485
ertodd-0.472
 bluff-0.470
itiz-0.466
Token
Token ID564
Feature activation-4.47e-02

Pos logit contributions
icult+0.692
orm+0.671
+0.660
awar+0.658
Dub+0.649
Neg logit contributions
 Nose-0.664
aspers-0.647
ertodd-0.631
 bluff-0.628
itiz-0.623
Token
Token ID250
Feature activation-4.40e-02

Pos logit contributions
icult+0.331
orm+0.325
+0.321
awar+0.317
 iceberg+0.313
Neg logit contributions
 Nose-0.456
aspers-0.448
 bluff-0.438
ertodd-0.437
itiz-0.428
TokenToday
Token ID8888
Feature activation-3.14e-01

Pos logit contributions
icult+0.399
orm+0.388
+0.383
awar+0.381
Dub+0.376
Neg logit contributions
 Nose-0.378
aspers-0.370
ertodd-0.361
 bluff-0.358
itiz-0.355
Token
Token ID960
Feature activation-6.69e-02

Pos logit contributions
icult+2.822
orm+2.764
+2.730
 iceberg+2.690
Dub+2.677
Neg logit contributions
 Nose-2.658
aspers-2.628
ertodd-2.558
 bluff-2.539
itiz-2.492
Tokenindependent
Token ID34750
Feature activation+2.56e-01

Pos logit contributions
icult+0.633
orm+0.616
+0.609
awar+0.606
Dub+0.599
Neg logit contributions
 Nose-0.550
aspers-0.537
ertodd-0.524
 bluff-0.520
itiz-0.515
Token of
Token ID286
Feature activation-1.86e-01

Pos logit contributions
 Nose+2.093
aspers+2.059
 bluff+1.993
itiz+1.987
   +1.956
Neg logit contributions
icult-2.394
orm-2.318
awar-2.314
Dub-2.267
-2.266
Token appearance
Token ID5585
Feature activation+6.71e-02

Pos logit contributions
icult+1.609
orm+1.571
+1.561
awar+1.536
 iceberg+1.531
Neg logit contributions
 Nose-1.630
aspers-1.623
ertodd-1.590
 bluff-1.554
itiz-1.547
Token,
Token ID11
Feature activation-5.65e-02

Pos logit contributions
 Nose+0.541
aspers+0.524
 bluff+0.509
itiz+0.508
ertodd+0.506
Neg logit contributions
icult-0.648
orm-0.627
awar-0.621
-0.620
nown-0.611
Token genital
Token ID24678
Feature activation+6.96e-02

Pos logit contributions
icult+0.572
orm+0.558
+0.553
awar+0.551
Dub+0.543
Neg logit contributions
 Nose-0.424
aspers-0.415
ertodd-0.403
 bluff-0.399
itiz-0.395
Tokenia
Token ID544
Feature activation+2.12e-01

Pos logit contributions
 Nose+0.671
aspers+0.651
 bluff+0.642
itiz+0.639
   +0.631
Neg logit contributions
icult-0.562
-0.535
orm-0.534
awar-0.532
Dub-0.525
Token matters
Token ID6067
Feature activation-3.74e-02

Pos logit contributions
 Nose+0.606
aspers+0.592
 bluff+0.578
ertodd+0.572
itiz+0.572
Neg logit contributions
icult-0.599
orm-0.580
-0.575
awar-0.573
nown-0.562
Token most
Token ID749
Feature activation-3.06e-03

Pos logit contributions
icult+0.303
orm+0.293
+0.289
awar+0.288
Dub+0.283
Neg logit contributions
 Nose-0.357
aspers-0.350
ertodd-0.343
 bluff-0.340
itiz-0.338
Token in
Token ID287
Feature activation-7.68e-02

Pos logit contributions
icult+0.024
orm+0.023
+0.023
awar+0.023
Dub+0.022
Neg logit contributions
 Nose-0.030
aspers-0.029
ertodd-0.029
 bluff-0.029
itiz-0.028
Token geop
Token ID30324
Feature activation+1.83e-01

Pos logit contributions
icult+0.693
orm+0.673
+0.667
awar+0.664
Dub+0.654
Neg logit contributions
 Nose-0.661
aspers-0.648
ertodd-0.632
 bluff-0.621
itiz-0.621
Tokenolitics
Token ID21704
Feature activation-2.81e-01

Pos logit contributions
 Nose+0.812
aspers+0.798
 bluff+0.742
itiz+0.725
ertodd+0.723
Neg logit contributions
icult-2.373
-2.355
orm-2.319
Dub-2.315
awar-2.312
Token
Token ID851
Feature activation+9.59e-02

Pos logit contributions
icult+2.085
orm+2.016
awar+1.974
+1.970
aj+1.939
Neg logit contributions
 Nose-2.861
aspers-2.809
ertodd-2.764
 bluff-2.722
itiz-2.709
Token it
Token ID340
Feature activation-3.45e-01

Pos logit contributions
 Nose+0.825
aspers+0.806
 bluff+0.786
ertodd+0.776
itiz+0.776
Neg logit contributions
icult-0.872
orm-0.844
-0.836
awar-0.832
nown-0.820
Token is
Token ID318
Feature activation+5.72e-02

Pos logit contributions
icult+3.063
orm+2.984
+2.909
awar+2.887
aj+2.885
Neg logit contributions
 Nose-3.015
aspers-2.929
ertodd-2.923
 bluff-2.819
itiz-2.770
Token plain
Token ID8631
Feature activation+1.62e-01

Pos logit contributions
 Nose+0.503
aspers+0.492
 bluff+0.478
ertodd+0.477
itiz+0.474
Neg logit contributions
icult-0.508
orm-0.493
-0.489
awar-0.486
nown-0.478
Token to
Token ID284
Feature activation+3.10e-03

Pos logit contributions
 Nose+1.316
aspers+1.269
 bluff+1.257
itiz+1.237
   +1.229
Neg logit contributions
icult-1.523
-1.486
orm-1.482
awar-1.475
Dub-1.456
Token see
Token ID766
Feature activation+7.89e-02

Pos logit contributions
 Nose+0.025
aspers+0.025
ertodd+0.024
 bluff+0.024
itiz+0.024
Neg logit contributions
icult-0.029
orm-0.029
-0.028
awar-0.028
nown-0.028
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
icult+1.740
orm+1.719
awar+1.668
+1.664
 iceberg+1.660
Neg logit contributions
 Nose-1.690
aspers-1.662
ertodd-1.634
 bluff-1.609
   -1.590
Token This
Token ID770
Feature activation-3.90e-01

Pos logit contributions
 Nose+1.260
aspers+1.220
ertodd+1.183
   +1.182
 bluff+1.182
Neg logit contributions
icult-1.198
orm-1.154
-1.151
awar-1.140
nown-1.126
Token is
Token ID318
Feature activation-1.27e-02

Pos logit contributions
icult+3.335
orm+3.316
 iceberg+3.269
Dub+3.205
aj+3.203
Neg logit contributions
aspers-3.401
 Nose-3.378
ertodd-3.360
 bluff-3.215
   -3.176
Token one
Token ID530
Feature activation+2.80e-02

Pos logit contributions
icult+0.111
orm+0.108
+0.106
awar+0.106
Dub+0.104
Neg logit contributions
 Nose-0.114
aspers-0.112
ertodd-0.109
 bluff-0.108
itiz-0.107
Token area
Token ID1989
Feature activation+2.34e-01

Pos logit contributions
 Nose+0.226
aspers+0.220
itiz+0.212
ertodd+0.212
 bluff+0.212
Neg logit contributions
icult-0.269
-0.261
orm-0.261
awar-0.259
nown-0.257
Token where
Token ID810
Feature activation-2.59e-02

Pos logit contributions
 Nose+1.761
aspers+1.698
itiz+1.642
 bluff+1.626
ertodd+1.614
Neg logit contributions
icult-2.367
-2.335
orm-2.299
awar-2.295
nown-2.260
Token Power
Token ID4333
Feature activation+9.49e-02

Pos logit contributions
icult+0.236
orm+0.229
+0.226
awar+0.225
Dub+0.222
Neg logit contributions
 Nose-0.221
aspers-0.217
ertodd-0.211
 bluff-0.210
itiz-0.208
Token BI
Token ID20068
Feature activation-1.34e-01

Pos logit contributions
 Nose+0.562
aspers+0.547
ertodd+0.529
 bluff+0.519
itiz+0.515
Neg logit contributions
icult-1.112
orm-1.087
awar-1.072
-1.069
Dub-1.067
Token beats
Token ID17825
Feature activation-1.95e-01

Pos logit contributions
icult+1.217
orm+1.191
awar+1.163
 iceberg+1.156
Dub+1.155
Neg logit contributions
 Nose-1.127
aspers-1.111
ertodd-1.094
 bluff-1.072
   -1.060
Token other
Token ID584
Feature activation-1.71e-01

Pos logit contributions
icult+1.740
orm+1.698
awar+1.651
 iceberg+1.648
Dub+1.644
Neg logit contributions
 Nose-1.674
aspers-1.655
ertodd-1.638
 bluff-1.596
itiz-1.592
Token vendors
Token ID17192
Feature activation-2.18e-01

Pos logit contributions
icult+1.557
orm+1.514
 iceberg+1.477
awar+1.469
aj+1.462
Neg logit contributions
 Nose-1.454
aspers-1.420
ertodd-1.418
 bluff-1.377
itiz-1.375
Token from
Token ID422
Feature activation+3.27e-01

Pos logit contributions
 Nose+2.478
aspers+2.359
 bluff+2.349
   +2.301
itiz+2.300
Neg logit contributions
icult-2.678
-2.606
awar-2.598
orm-2.597
nown-2.548
Token the
Token ID262
Feature activation+2.17e-01

Pos logit contributions
 Nose+2.700
aspers+2.522
 bluff+2.517
   +2.499
itiz+2.497
Neg logit contributions
icult-3.097
awar-3.007
-2.985
orm-2.979
Dub-2.934
Token top
Token ID1353
Feature activation+1.51e-01

Pos logit contributions
 Nose+1.908
aspers+1.823
 bluff+1.788
   +1.775
itiz+1.772
Neg logit contributions
icult-1.958
-1.897
orm-1.887
awar-1.877
Dub-1.840
Token.
Token ID13
Feature activation+4.13e-01

Pos logit contributions
 Nose+1.300
aspers+1.262
 bluff+1.230
ertodd+1.221
itiz+1.217
Neg logit contributions
icult-1.367
orm-1.320
-1.313
awar-1.310
Dub-1.285
Token I
Token ID314
Feature activation+8.65e-02

Pos logit contributions
 Nose+3.681
aspers+3.414
   +3.401
 bluff+3.340
itiz+3.316
Neg logit contributions
icult-3.679
orm-3.526
awar-3.502
 iceberg-3.479
nown-3.472
Token took
Token ID1718
Feature activation-8.62e-02

Pos logit contributions
 Nose+0.733
aspers+0.717
ertodd+0.697
 bluff+0.694
itiz+0.688
Neg logit contributions
icult-0.795
orm-0.772
-0.765
awar-0.761
Dub-0.749
Token pictures
Token ID5986
Feature activation+1.09e-01

Pos logit contributions
icult+0.762
orm+0.741
+0.729
awar+0.729
Dub+0.716
Neg logit contributions
 Nose-0.759
aspers-0.745
ertodd-0.730
 bluff-0.721
itiz-0.715
Token of
Token ID286
Feature activation+1.30e-01

Pos logit contributions
 Nose+0.927
aspers+0.903
 bluff+0.877
ertodd+0.875
itiz+0.867
Neg logit contributions
icult-1.009
orm-0.978
-0.971
awar-0.968
Dub-0.950
Token where
Token ID810
Feature activation+3.50e-01

Pos logit contributions
 Nose+1.099
aspers+1.058
 bluff+1.032
itiz+1.027
ertodd+1.025
Neg logit contributions
icult-1.200
orm-1.166
-1.163
awar-1.152
nown-1.136
Token I
Token ID314
Feature activation-5.03e-01

Pos logit contributions
 Nose+2.894
aspers+2.732
itiz+2.675
 bluff+2.668
   +2.657
Neg logit contributions
icult-3.309
-3.237
awar-3.188
orm-3.152
Dub-3.126
Token pri
Token ID1293
Feature activation-1.65e-01

Pos logit contributions
icult+4.215
orm+4.133
aj+3.965
awar+3.947
 iceberg+3.900
Neg logit contributions
ertodd-4.457
aspers-4.455
 Nose-4.381
itiz-4.242
 bluff-4.138
Token of
Token ID286
Feature activation-3.60e-01

Pos logit contributions
 Nose+0.782
aspers+0.761
 bluff+0.743
itiz+0.738
   +0.733
Neg logit contributions
icult-0.952
orm-0.918
awar-0.915
-0.910
nown-0.899
Token Trump
Token ID1301
Feature activation+1.25e-01

Pos logit contributions
icult+2.960
orm+2.878
 iceberg+2.850
+2.817
aj+2.814
Neg logit contributions
aspers-3.297
 Nose-3.294
ertodd-3.233
itiz-3.116
 bluff-3.107
Token that
Token ID326
Feature activation-1.85e-01

Pos logit contributions
 Nose+1.047
aspers+1.024
 bluff+0.996
ertodd+0.989
itiz+0.986
Neg logit contributions
icult-1.162
orm-1.120
-1.119
awar-1.117
Dub-1.099
Token there
Token ID612
Feature activation+3.58e-02

Pos logit contributions
icult+1.632
orm+1.588
+1.566
awar+1.551
aj+1.540
Neg logit contributions
 Nose-1.617
aspers-1.599
ertodd-1.562
 bluff-1.524
itiz-1.519
Token
Token ID447
Feature activation+2.14e-01

Pos logit contributions
 Nose+0.283
aspers+0.277
 bluff+0.268
ertodd+0.268
itiz+0.266
Neg logit contributions
icult-0.349
orm-0.339
awar-0.336
-0.336
Dub-0.331
Token
Token ID247
Feature activation-5.71e-02

Pos logit contributions
 Nose+1.709
aspers+1.672
ertodd+1.620
 bluff+1.611
itiz+1.603
Neg logit contributions
icult-2.076
orm-2.011
-1.999
awar-1.986
Dub-1.957
Tokens
Token ID82
Feature activation-2.65e-01

Pos logit contributions
icult+0.494
orm+0.480
+0.471
awar+0.471
nown+0.463
Neg logit contributions
 Nose-0.515
aspers-0.504
ertodd-0.491
 bluff-0.490
itiz-0.485
Token a
Token ID257
Feature activation-3.68e-03

Pos logit contributions
icult+2.312
orm+2.275
+2.235
awar+2.195
aj+2.189
Neg logit contributions
 Nose-2.336
aspers-2.296
ertodd-2.260
 bluff-2.196
   -2.192
Token grown
Token ID7334
Feature activation+9.49e-03

Pos logit contributions
icult+0.032
orm+0.031
+0.031
awar+0.031
Dub+0.030
Neg logit contributions
 Nose-0.033
aspers-0.032
ertodd-0.031
 bluff-0.031
itiz-0.031
Token-
Token ID12
Feature activation-6.10e-02

Pos logit contributions
 Nose+0.079
aspers+0.077
ertodd+0.075
 bluff+0.075
itiz+0.074
Neg logit contributions
icult-0.088
orm-0.086
-0.085
awar-0.085
Dub-0.083
Tokenup
Token ID929
Feature activation-3.73e-01

Pos logit contributions
icult+0.587
orm+0.570
+0.561
awar+0.560
Dub+0.553
Neg logit contributions
 Nose-0.494
aspers-0.481
ertodd-0.471
 bluff-0.466
itiz-0.462
Token own
Token ID898
Feature activation-2.99e-01

Pos logit contributions
icult+0.336
orm+0.328
awar+0.322
+0.320
Dub+0.316
Neg logit contributions
 Nose-0.331
aspers-0.324
ertodd-0.318
itiz-0.312
 bluff-0.312
Token the
Token ID262
Feature activation+1.35e-01

Pos logit contributions
orm+2.302
icult+2.295
+2.209
 iceberg+2.190
awar+2.185
Neg logit contributions
 Nose-2.900
ertodd-2.861
aspers-2.854
 bluff-2.764
   -2.734
Token game
Token ID983
Feature activation+2.73e-01

Pos logit contributions
 Nose+1.451
aspers+1.415
 bluff+1.388
itiz+1.378
   +1.372
Neg logit contributions
icult-0.941
-0.893
orm-0.891
awar-0.882
nown-0.863
Token and
Token ID290
Feature activation+2.35e-01

Pos logit contributions
 Nose+2.193
aspers+2.168
itiz+2.076
 bluff+2.070
   +2.055
Neg logit contributions
icult-2.619
-2.512
orm-2.485
awar-2.477
nown-2.439
Token have
Token ID423
Feature activation+1.66e-01

Pos logit contributions
 Nose+2.022
aspers+1.975
 bluff+1.932
itiz+1.899
   +1.896
Neg logit contributions
icult-2.141
-2.062
orm-2.048
awar-2.027
nown-2.007
Token a
Token ID257
Feature activation+9.75e-02

Pos logit contributions
 Nose+1.436
aspers+1.398
 bluff+1.366
itiz+1.354
ertodd+1.344
Neg logit contributions
icult-1.505
-1.449
orm-1.445
awar-1.435
nown-1.418
Token broadband
Token ID18729
Feature activation-3.12e-02

Pos logit contributions
 Nose+1.077
aspers+1.054
 bluff+1.033
ertodd+1.029
itiz+1.026
Neg logit contributions
icult-0.650
orm-0.618
-0.615
awar-0.609
nown-0.596
Token Internet
Token ID4455
Feature activation+9.15e-02

Pos logit contributions
icult+0.293
orm+0.287
+0.281
awar+0.280
nown+0.278
Neg logit contributions
 Nose-0.257
aspers-0.252
ertodd-0.247
 bluff-0.243
itiz-0.240
Token connection
Token ID4637
Feature activation+1.83e-01

Pos logit contributions
 Nose+0.741
aspers+0.724
ertodd+0.703
 bluff+0.700
itiz+0.694
Neg logit contributions
icult-0.876
orm-0.852
-0.844
awar-0.840
Dub-0.828
Token can
Token ID460
Feature activation-6.24e-02

Pos logit contributions
 Nose+1.489
aspers+1.451
 bluff+1.416
itiz+1.400
ertodd+1.395
Neg logit contributions
icult-1.743
-1.679
orm-1.676
awar-1.654
Dub-1.635
Token play
Token ID711
Feature activation-3.13e-01

Pos logit contributions
icult+0.564
orm+0.552
awar+0.543
+0.542
 iceberg+0.533
Neg logit contributions
 Nose-0.537
aspers-0.527
ertodd-0.516
itiz-0.505
 bluff-0.502
Token of
Token ID286
Feature activation+1.58e-01

Pos logit contributions
 Nose+1.493
aspers+1.432
 bluff+1.414
itiz+1.401
ertodd+1.401
Neg logit contributions
icult-1.795
-1.730
awar-1.722
orm-1.719
Dub-1.675
Token our
Token ID674
Feature activation+2.72e-01

Pos logit contributions
 Nose+1.304
aspers+1.261
 bluff+1.230
ertodd+1.230
   +1.222
Neg logit contributions
icult-1.499
orm-1.438
-1.438
awar-1.427
Dub-1.395
Token old
Token ID1468
Feature activation+2.10e-01

Pos logit contributions
 Nose+2.526
aspers+2.468
 bluff+2.460
   +2.399
itiz+2.384
Neg logit contributions
icult-2.293
-2.207
awar-2.183
orm-2.167
nown-2.126
Token Pont
Token ID26345
Feature activation+1.22e-01

Pos logit contributions
 Nose+1.898
aspers+1.864
 bluff+1.819
itiz+1.796
   +1.786
Neg logit contributions
icult-1.810
-1.751
orm-1.733
awar-1.730
nown-1.704
Tokeniac
Token ID9607
Feature activation+6.38e-02

Pos logit contributions
 Nose+1.565
aspers+1.542
 bluff+1.512
ertodd+1.510
itiz+1.505
Neg logit contributions
icult-0.593
orm-0.557
-0.554
awar-0.545
nown-0.531
Token Bon
Token ID7979
Feature activation-6.62e-01

Pos logit contributions
 Nose+0.558
aspers+0.545
 bluff+0.529
ertodd+0.528
itiz+0.525
Neg logit contributions
icult-0.570
orm-0.552
-0.549
awar-0.545
nown-0.537
Tokenne
Token ID710
Feature activation+1.35e-01

Pos logit contributions
orm+6.524
icult+6.469
aj+6.381
awar+6.325
Dub+6.201
Neg logit contributions
ertodd-4.985
aspers-4.949
 Nose-4.861
   -4.694
 bluff-4.583
Tokenville
Token ID4244
Feature activation-4.85e-02

Pos logit contributions
 Nose+1.136
aspers+1.095
 bluff+1.068
itiz+1.062
ertodd+1.058
Neg logit contributions
icult-1.251
-1.210
orm-1.210
awar-1.194
nown-1.178
Token.
Token ID13
Feature activation+5.13e-02

Pos logit contributions
icult+0.437
orm+0.425
+0.418
awar+0.418
Dub+0.411
Neg logit contributions
 Nose-0.418
aspers-0.411
ertodd-0.401
 bluff-0.396
itiz-0.393
Token Sally
Token ID25737
Feature activation+5.04e-01

Pos logit contributions
 Nose+0.463
aspers+0.453
ertodd+0.441
 bluff+0.439
itiz+0.436
Neg logit contributions
icult-0.444
orm-0.430
-0.426
awar-0.423
Dub-0.416
Token Ye
Token ID11609
Feature activation-2.08e-01

Pos logit contributions
 Nose+4.712
aspers+4.399
 bluff+4.336
itiz+4.320
   +4.314
Neg logit contributions
icult-4.224
awar-3.934
-3.928
orm-3.916
nown-3.915
Token
Token ID251
Feature activation-4.33e-01

Pos logit contributions
icult+3.482
orm+3.410
+3.360
awar+3.342
Dub+3.294
Neg logit contributions
 Nose-3.230
aspers-3.159
 bluff-3.087
ertodd-3.067
itiz-3.045
Token
Token ID198
Feature activation-4.05e-01

Pos logit contributions
icult+3.730
orm+3.605
+3.570
awar+3.522
aj+3.495
Neg logit contributions
 Nose-3.846
aspers-3.810
 bluff-3.722
ertodd-3.709
itiz-3.667
Token
Token ID198
Feature activation-6.12e-01

Pos logit contributions
orm+2.646
aj+2.646
Dub+2.608
icult+2.571
awar+2.497
Neg logit contributions
aspers-4.349
ertodd-4.305
 Nose-4.277
 bluff-4.238
��-4.166
TokenH
Token ID39
Feature activation-4.12e-02

Pos logit contributions
icult+4.935
Dub+4.934
+4.889
aj+4.858
orm+4.831
Neg logit contributions
 Nose-5.558
ertodd-5.518
aspers-5.481
 bluff-5.464
itiz-5.298
Tokenints
Token ID29503
Feature activation-3.41e-01

Pos logit contributions
icult+0.373
orm+0.363
+0.357
awar+0.356
Dub+0.351
Neg logit contributions
 Nose-0.357
aspers-0.348
ertodd-0.340
 bluff-0.338
itiz-0.335
Token on
Token ID319
Feature activation-5.85e-01

Pos logit contributions
icult+2.818
orm+2.754
awar+2.671
+2.670
aj+2.665
Neg logit contributions
 Nose-3.124
aspers-3.096
ertodd-3.082
itiz-2.995
 bluff-2.993
Token Et
Token ID17906
Feature activation-5.27e-01

Pos logit contributions
icult+4.908
aj+4.711
orm+4.698
+4.673
Dub+4.635
Neg logit contributions
aspers-5.190
ertodd-5.108
 Nose-4.853
itiz-4.830
 bluff-4.769
Tokeniquette
Token ID40387
Feature activation-3.44e-01

Pos logit contributions
icult+2.985
orm+2.920
aj+2.832
awar+2.688
nown+2.677
Neg logit contributions
aspers-6.186
 Nose-6.156
ertodd-6.140
 bluff-6.016
   -5.905
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
icult+2.826
orm+2.770
+2.713
aj+2.696
awar+2.680
Neg logit contributions
aspers-3.124
 Nose-3.120
ertodd-3.107
 bluff-3.036
itiz-3.006
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
icult+1.803
orm+1.745
+1.716
awar+1.713
Dub+1.701
Neg logit contributions
aspers-1.786
 Nose-1.768
ertodd-1.753
 bluff-1.705
itiz-1.702
Token Us
Token ID4021
Feature activation+1.72e-01

Pos logit contributions
icult+1.497
orm+1.455
+1.437
awar+1.426
Dub+1.411
Neg logit contributions
aspers-1.390
 Nose-1.389
ertodd-1.361
 bluff-1.333
itiz-1.328
Tokencv
Token ID33967
Feature activation+2.46e-01

Pos logit contributions
 Nose+1.674
aspers+1.667
   +1.606
itiz+1.606
ertodd+1.603
Neg logit contributions
icult-1.334
-1.280
awar-1.264
 iceberg-1.258
orm-1.253
Token2
Token ID17
Feature activation+1.77e-01

Pos logit contributions
 Nose+1.976
aspers+1.937
ertodd+1.872
   +1.865
 bluff+1.864
Neg logit contributions
icult-2.357
-2.287
orm-2.256
awar-2.251
 iceberg-2.218
Token.
Token ID13
Feature activation-4.98e-01

Pos logit contributions
 Nose+1.403
aspers+1.371
ertodd+1.331
 bluff+1.324
itiz+1.313
Neg logit contributions
icult-1.717
orm-1.671
-1.654
awar-1.647
Dub-1.625
TokenM
Token ID44
Feature activation-3.72e-01

Pos logit contributions
icult+4.303
orm+4.288
+4.241
Dub+4.160
aj+4.131
Neg logit contributions
 Nose-4.315
ertodd-4.243
aspers-4.233
 bluff-4.145
itiz-4.098
TokenOR
Token ID1581
Feature activation-9.78e-02

Pos logit contributions
orm+1.317
aj+1.164
icult+1.106
+1.096
awar+1.093
Neg logit contributions
 Nose-5.334
aspers-5.234
 bluff-5.220
ertodd-5.176
itiz-5.091
TokenPH
Token ID11909
Feature activation-6.15e-01

Pos logit contributions
orm+0.724
icult+0.722
+0.700
aj+0.696
Dub+0.680
Neg logit contributions
 Nose-0.996
aspers-0.982
 bluff-0.964
ertodd-0.958
itiz-0.947
Token_
Token ID62
Feature activation-3.83e-01

Pos logit contributions
orm+2.628
aj+2.575
Dub+2.558
+2.385
icult+2.320
Neg logit contributions
aspers-7.772
 Nose-7.770
 bluff-7.761
ertodd-7.658
itiz-7.571
TokenRECT
Token ID23988
Feature activation-2.69e-01

Pos logit contributions
icult+3.146
orm+3.140
+3.106
Dub+3.039
aj+3.017
Neg logit contributions
 Nose-3.524
ertodd-3.455
aspers-3.419
 bluff-3.402
itiz-3.361
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
icult+2.433
orm+2.367
+2.338
awar+2.323
Dub+2.292
Neg logit contributions
 Nose-2.324
aspers-2.271
ertodd-2.212
 bluff-2.203
itiz-2.187
Token (
Token ID357
Feature activation+2.04e-01

Pos logit contributions
icult+0.981
orm+0.949
+0.941
awar+0.937
Dub+0.923
Neg logit contributions
 Nose-0.939
aspers-0.917
ertodd-0.891
 bluff-0.890
itiz-0.882
Token21
Token ID2481
Feature activation+3.59e-01

Pos logit contributions
 Nose+1.721
aspers+1.681
   +1.632
 bluff+1.617
itiz+1.614
Neg logit contributions
icult-1.872
-1.797
orm-1.783
awar-1.780
 iceberg-1.760
Token de
Token ID390
Feature activation-4.61e-01

Pos logit contributions
 Nose+3.027
aspers+2.900
 bluff+2.882
itiz+2.870
   +2.864
Neg logit contributions
icult-3.216
-3.166
awar-3.165
orm-3.131
nown-3.078
Token coup
Token ID12092
Feature activation+3.55e-01

Pos logit contributions
icult+3.965
orm+3.872
 lett+3.838
 iceberg+3.787
Dub+3.771
Neg logit contributions
ertodd-4.042
aspers-4.015
 Nose-3.977
itiz-3.778
 bluff-3.764
Token d
Token ID288
Feature activation+1.56e-01

Pos logit contributions
 Nose+3.079
aspers+2.989
 bluff+2.966
   +2.938
itiz+2.907
Neg logit contributions
icult-3.071
-2.997
awar-2.986
orm-2.956
Dub-2.917
Token'
Token ID6
Feature activation-1.14e-01

Pos logit contributions
 Nose+1.517
aspers+1.494
 bluff+1.446
itiz+1.444
ertodd+1.433
Neg logit contributions
icult-1.223
-1.189
orm-1.173
awar-1.163
nown-1.153
TokenE
Token ID36
Feature activation+2.45e-01

Pos logit contributions
icult+0.938
orm+0.908
+0.890
awar+0.888
Dub+0.876
Neg logit contributions
 Nose-1.080
aspers-1.056
ertodd-1.037
 bluff-1.026
itiz-1.018
Tokent
Token ID83
Feature activation-6.98e-01

Pos logit contributions
 Nose+1.876
aspers+1.859
itiz+1.774
   +1.751
ertodd+1.744
Neg logit contributions
icult-2.368
-2.321
orm-2.284
 iceberg-2.263
awar-2.252
Tokenat
Token ID265
Feature activation-6.06e-02

Pos logit contributions
icult+6.848
orm+6.795
aj+6.647
awar+6.608
Dub+6.368
Neg logit contributions
 Nose-5.237
ertodd-5.224
aspers-5.129
 bluff-4.947
   -4.880
Token,
Token ID11
Feature activation-4.49e-01

Pos logit contributions
icult+0.557
orm+0.541
+0.535
awar+0.531
Dub+0.524
Neg logit contributions
 Nose-0.515
aspers-0.505
ertodd-0.493
 bluff-0.488
itiz-0.484
Token les
Token ID10287
Feature activation-4.49e-01

Pos logit contributions
icult+4.002
orm+3.947
Dub+3.888
+3.875
aj+3.844
Neg logit contributions
 Nose-3.748
ertodd-3.747
aspers-3.728
 bluff-3.573
itiz-3.547
Token mut
Token ID4517
Feature activation+2.72e-01

Pos logit contributions
icult+3.967
orm+3.876
 lett+3.816
+3.772
 iceberg+3.751
Neg logit contributions
aspers-3.816
 Nose-3.813
ertodd-3.802
 bluff-3.620
   -3.617
Tokenins
Token ID1040
Feature activation+1.17e-01

Pos logit contributions
aspers+2.294
 Nose+2.280
itiz+2.230
ertodd+2.171
 bluff+2.160
Neg logit contributions
-2.419
icult-2.396
awar-2.340
nown-2.329
orm-2.318
Tokenve
Token ID303
Feature activation-9.47e-02

Pos logit contributions
 Nose+0.569
aspers+0.557
ertodd+0.540
 bluff+0.537
itiz+0.535
Neg logit contributions
icult-0.582
orm-0.563
awar-0.557
-0.556
nown-0.547
Token believed
Token ID4762
Feature activation-1.18e-01

Pos logit contributions
icult+0.812
orm+0.792
+0.780
awar+0.775
Dub+0.766
Neg logit contributions
 Nose-0.857
aspers-0.842
ertodd-0.823
 bluff-0.813
itiz-0.809
Token in
Token ID287
Feature activation-4.73e-01

Pos logit contributions
icult+1.020
orm+0.999
+0.980
awar+0.973
Dub+0.962
Neg logit contributions
 Nose-1.056
aspers-1.039
ertodd-1.013
 bluff-1.004
itiz-0.996
Token faith
Token ID4562
Feature activation+2.79e-01

Pos logit contributions
orm+3.997
icult+3.959
+3.867
awar+3.816
 iceberg+3.802
Neg logit contributions
 Nose-4.158
aspers-4.109
ertodd-4.055
 bluff-3.940
itiz-3.875
Token that
Token ID326
Feature activation+4.06e-02

Pos logit contributions
 Nose+2.340
aspers+2.273
   +2.241
itiz+2.214
 bluff+2.201
Neg logit contributions
icult-2.583
-2.479
awar-2.464
orm-2.435
nown-2.416
Token something
Token ID1223
Feature activation-7.22e-01

Pos logit contributions
 Nose+0.348
aspers+0.339
ertodd+0.329
 bluff+0.329
itiz+0.328
Neg logit contributions
icult-0.371
orm-0.359
-0.357
awar-0.355
nown-0.348
Token was
Token ID373
Feature activation-4.91e-01

Pos logit contributions
orm+5.625
icult+5.545
 iceberg+5.527
 lett+5.422
aj+5.325
Neg logit contributions
aspers-6.565
ertodd-6.536
 Nose-6.420
 bluff-6.227
itiz-6.049
Token going
Token ID1016
Feature activation-2.57e-01

Pos logit contributions
orm+3.919
icult+3.911
 iceberg+3.774
aj+3.718
 lett+3.687
Neg logit contributions
aspers-4.567
 Nose-4.533
ertodd-4.533
itiz-4.275
 bluff-4.205
Token to
Token ID284
Feature activation-2.08e-01

Pos logit contributions
icult+2.250
orm+2.182
+2.159
awar+2.147
Dub+2.112
Neg logit contributions
 Nose-2.285
aspers-2.241
ertodd-2.181
 bluff-2.168
itiz-2.152
Token happen
Token ID1645
Feature activation+3.54e-02

Pos logit contributions
icult+1.615
orm+1.578
awar+1.533
+1.526
 iceberg+1.524
Neg logit contributions
 Nose-2.040
aspers-2.016
ertodd-1.982
itiz-1.941
 bluff-1.929
Token,
Token ID11
Feature activation+1.37e-01

Pos logit contributions
 Nose+0.292
aspers+0.285
ertodd+0.277
 bluff+0.276
itiz+0.275
Neg logit contributions
icult-0.333
orm-0.323
-0.320
awar-0.319
Dub-0.314