TOP ACTIVATIONS
MAX = 1.623

in the angle - of - attack data . Airbus later
w > save [ 10 : 47 ] < f gt
m 2 k [ 10 : 47 ] < j th
/ clear chat [ 10 : 47 ] < her ret
Option < Piece > ; 64 ], // Where are the
m 2 k [ 10 : 48 ] < death d
y 2 k [ 10 : 47 ] < chain x
-- secret < Secret Access Key > Dem o
2 k lol [ 10 : 47 ] < m ik
m 2 k [ 10 : 47 ] < k asse
m 2 k [ 10 : 47 ] < mad ag
l ma o [ 10 : 47 ] < rev itle
anch ak and Mak ovi ich uk , the other owners
> dude nice [ 10 : 47 ] < sp it
> H aha [ 10 : 47 ] < t oxic
m 2 k [ 10 : 47 ] < sn iping
m 2 k [ 10 : 47 ] < mom per
Mang 0 king [ 10 : 47 ] < dan ides
m 2 k [ 10 : 47 ] < l ucky
m 2 k [ 10 : 47 ] < mom per

MIN ACTIVATIONS
MIN = -1.787

images ( args [" images "] ): # load the image
Santa Clara County v . Southern Pacific Railroad Company
; where do we draw the line ? So they say
void V ort on Sim :: Pop ulate D
be equally as tight - f isted as the Conservatives when
to be equally as tight - f isted as the Conservatives
Font Name , $ FS 2 ,[ System . Draw ing
fork - t ender . Chop fl ore ts into small
The rest , nearly two - thirds of respondents , said
of possibilities I had never really considered before . In fact
p ored over by analysts looking for clues on when rates
This will force Unity to invoke a function called vert
they wrote . W arm b ier was convicted
, ( 13 , 5 )) sq K ernel = c
: # load the image , resize it , and convert
used , thus a line like : /* vi : ts
at osis of the palms and sol es ") is an
, called a parcel , and decide where to place buildings
atch 20 B atch 19 B atch
AMA showing that its drug , synth roid , is not

INTERVAL 0.770 - 1.623
CONTAINS 0.471%

2018 open enrollment period and tighten enrollment eligibility " to deter
rene and I exchange worried glances . The first of many
same time she does want to say to her domestic audience
are Whole Al monds , P ec an Hal ves ,
S . My CV has been public and on my website

INTERVAL -0.082 - 0.770
CONTAINS 61.779%

s defenders see his flaws as regular - guy problems ,
. All four people I brought this up too , separately
they � � ve sent two perfectly fine setup man ,
radio program Friday morning . " But it would have been
What was really needed was a confession . Obama

INTERVAL -0.935 - -0.082
CONTAINS 37.629%

] ], step Old ] (* mark locations as Sear ched
was asked by NBC News ' Savannah Guth rie ( right
- play guy who is not interested in just blending in
year - old Hed ges is sure to be a breakout
than M AF , there 's obviously zero drama and the

INTERVAL -1.787 - -0.935
CONTAINS 0.121%

for evidence that Russia was behind the embarrassing Democratic National Committee
Draw ing . Color ] :: From Ar gb ($ BG
. 5 - 4 . 9 tonnes . The study estimated
ma v . Goodell Supplemental Mem o in Support of In
the fly by of Comet Bor rell y was a great
Token in
Token ID287
Feature activation+2.85e-01

Pos logit contributions
bugs+4.924
duction+4.877
 Invaders+4.864
 Kund+4.857
angs+4.787
Neg logit contributions
estone-6.109
PB-5.412
adem-5.350
 Flavoring-5.319
font-5.145
Token the
Token ID262
Feature activation+4.81e-01

Pos logit contributions
duction+2.230
bugs+2.223
 Invaders+2.217
 Kund+2.169
angs+2.152
Neg logit contributions
estone-3.090
PB-2.692
adem-2.675
 Flavoring-2.672
+.-2.646
Token angle
Token ID9848
Feature activation+2.87e-01

Pos logit contributions
duction+4.008
 Invaders+4.002
bugs+3.966
 Kund+3.952
angs+3.867
Neg logit contributions
estone-4.892
 Flavoring-4.229
PB-4.218
adem-4.214
+.-4.116
Token-
Token ID12
Feature activation+3.56e-01

Pos logit contributions
duction+2.410
bugs+2.370
 Invaders+2.354
angs+2.318
 Kund+2.301
Neg logit contributions
estone-2.947
PB-2.561
 Flavoring-2.551
adem-2.525
font-2.455
Tokenof
Token ID1659
Feature activation+6.62e-01

Pos logit contributions
duction+3.596
bugs+3.595
angs+3.502
 Invaders+3.492
 Kund+3.446
Neg logit contributions
estone-3.065
PB-2.585
 Flavoring-2.573
adem-2.533
+.-2.512
Token-
Token ID12
Feature activation+1.62e+00

Pos logit contributions
duction+5.073
bugs+5.051
angs+4.897
 Invaders+4.857
 Kund+4.846
Neg logit contributions
estone-7.025
PB-6.220
 Flavoring-6.193
ntil-6.136
adem-6.021
Tokenattack
Token ID20358
Feature activation+1.54e-01

Pos logit contributions
duction+7.913
cz+7.448
bugs+7.395
angs+7.369
Thunder+6.947
Neg logit contributions
estone-18.692
ntil-18.176
 Flavoring-18.039
PB-17.288
 pharm-16.784
Token data
Token ID1366
Feature activation+1.82e-01

Pos logit contributions
duction+1.373
bugs+1.373
 Invaders+1.364
 Kund+1.335
angs+1.333
Neg logit contributions
estone-1.508
PB-1.295
adem-1.282
 Flavoring-1.274
font-1.270
Token.
Token ID13
Feature activation+3.89e-01

Pos logit contributions
duction+1.606
bugs+1.605
 Invaders+1.595
 Kund+1.561
angs+1.559
Neg logit contributions
estone-1.788
PB-1.538
adem-1.525
 Flavoring-1.514
font-1.510
Token Airbus
Token ID39173
Feature activation+4.26e-01

Pos logit contributions
 Invaders+3.186
bugs+3.176
duction+3.130
 Kund+3.099
angs+3.038
Neg logit contributions
estone-4.055
adem-3.502
PB-3.493
+.-3.445
font-3.440
Token later
Token ID1568
Feature activation-1.44e-01

Pos logit contributions
bugs+3.634
 Invaders+3.611
duction+3.598
 Kund+3.533
angs+3.513
Neg logit contributions
estone-4.269
PB-3.678
adem-3.640
font-3.632
 Flavoring-3.630
Tokenw
Token ID86
Feature activation+2.75e-01

Pos logit contributions
duction+1.515
bugs+1.514
angs+1.482
 Invaders+1.477
 Kund+1.449
Neg logit contributions
estone-1.821
PB-1.587
 Flavoring-1.565
+.-1.555
adem-1.554
Token>
Token ID29
Feature activation-1.04e-01

Pos logit contributions
duction+2.387
bugs+2.381
angs+2.356
 Invaders+2.318
cz+2.304
Neg logit contributions
estone-2.692
PB-2.367
 Flavoring-2.341
+.-2.305
adem-2.293
Token save
Token ID3613
Feature activation-8.18e-02

Pos logit contributions
estone+1.006
PB+0.866
adem+0.858
+.+0.857
font+0.854
Neg logit contributions
duction-0.931
bugs-0.926
 Invaders-0.914
angs-0.899
 Kund-0.890
Token [
Token ID685
Feature activation+1.58e-03

Pos logit contributions
estone+0.797
PB+0.685
font+0.677
adem+0.675
+.+0.674
Neg logit contributions
duction-0.732
bugs-0.726
 Invaders-0.725
angs-0.711
 Kund-0.709
Token10
Token ID940
Feature activation+2.24e-01

Pos logit contributions
 Invaders+0.012
duction+0.012
bugs+0.012
angs+0.011
 Kund+0.011
Neg logit contributions
estone-0.018
PB-0.016
font-0.015
+.-0.015
adem-0.015
Token:
Token ID25
Feature activation+1.57e+00

Pos logit contributions
bugs+1.929
duction+1.918
 Invaders+1.903
 Kund+1.865
angs+1.863
Neg logit contributions
estone-2.262
PB-1.949
adem-1.940
 Flavoring-1.920
+.-1.920
Token47
Token ID2857
Feature activation+1.71e-01

Pos logit contributions
cz+5.533
bugs+5.285
 Invaders+5.143
 Kund+5.099
Thunder+4.860
Neg logit contributions
ntil-20.937
estone-20.288
ModLoader-18.929
insula-18.590
 activ-18.496
Token]
Token ID60
Feature activation-6.01e-01

Pos logit contributions
bugs+0.849
duction+0.846
 Invaders+0.834
angs+0.804
 Kund+0.800
Neg logit contributions
estone-2.348
PB-2.110
adem-2.097
+.-2.089
font-2.088
Token <
Token ID1279
Feature activation+1.88e-01

Pos logit contributions
estone+4.205
PB+3.436
font+3.391
+.+3.377
 Flavoring+3.362
Neg logit contributions
duction-6.764
 Invaders-6.720
bugs-6.715
 Kund-6.586
angs-6.559
Tokenf
Token ID69
Feature activation-3.24e-01

Pos logit contributions
bugs+1.638
duction+1.631
 Invaders+1.595
angs+1.590
 Kund+1.572
Neg logit contributions
estone-1.868
PB-1.601
 Flavoring-1.601
+.-1.587
adem-1.583
Tokengt
Token ID13655
Feature activation+4.81e-01

Pos logit contributions
estone+3.424
adem+2.984
PB+2.946
font+2.935
+.+2.860
Neg logit contributions
 Invaders-2.647
bugs-2.612
duction-2.585
 Kund-2.551
Thunder-2.440
Token m
Token ID285
Feature activation+1.94e-01

Pos logit contributions
bugs+4.196
 Invaders+4.158
duction+4.088
angs+4.079
 Kund+4.062
Neg logit contributions
estone-4.552
PB-3.913
 Flavoring-3.903
adem-3.833
font-3.801
Token2
Token ID17
Feature activation+4.92e-01

Pos logit contributions
duction+1.844
bugs+1.843
 Invaders+1.825
angs+1.795
 Kund+1.788
Neg logit contributions
estone-1.781
PB-1.513
adem-1.495
font-1.488
+.-1.487
Tokenk
Token ID74
Feature activation+2.46e-01

Pos logit contributions
bugs+2.795
duction+2.732
 Kund+2.671
 Invaders+2.647
cz+2.644
Neg logit contributions
estone-6.281
 Flavoring-5.705
adem-5.602
PB-5.593
ntil-5.552
Token [
Token ID685
Feature activation-3.08e-01

Pos logit contributions
bugs+2.107
duction+2.102
 Invaders+2.094
 Kund+2.048
angs+2.042
Neg logit contributions
estone-2.484
PB-2.143
adem-2.133
font-2.114
+.-2.112
Token10
Token ID940
Feature activation+3.52e-02

Pos logit contributions
estone+3.094
font+2.772
PB+2.766
+.+2.738
adem+2.622
Neg logit contributions
 Invaders-2.709
duction-2.598
igers-2.539
bugs-2.503
angs-2.501
Token:
Token ID25
Feature activation+1.57e+00

Pos logit contributions
duction+0.326
 Invaders+0.323
bugs+0.322
angs+0.316
 Kund+0.313
Neg logit contributions
estone-0.334
PB-0.287
font-0.284
+.-0.283
adem-0.280
Token47
Token ID2857
Feature activation+1.86e-01

Pos logit contributions
cz+5.495
bugs+5.110
 Kund+4.918
Thunder+4.892
 Invaders+4.858
Neg logit contributions
ntil-21.079
estone-20.138
ModLoader-19.183
insula-18.706
 activ-18.627
Token]
Token ID60
Feature activation-6.49e-01

Pos logit contributions
bugs+0.919
duction+0.915
 Invaders+0.901
angs+0.869
 Kund+0.866
Neg logit contributions
estone-2.556
PB-2.297
adem-2.285
+.-2.275
font-2.273
Token <
Token ID1279
Feature activation+7.54e-02

Pos logit contributions
estone+3.941
PB+3.262
font+3.218
+.+3.162
 Flavoring+3.132
Neg logit contributions
duction-7.678
 Invaders-7.536
bugs-7.514
angs-7.397
igers-7.344
Tokenj
Token ID73
Feature activation-4.37e-01

Pos logit contributions
bugs+0.651
duction+0.651
 Invaders+0.641
angs+0.633
 Kund+0.628
Neg logit contributions
estone-0.759
PB-0.654
adem-0.647
 Flavoring-0.646
+.-0.646
Tokenth
Token ID400
Feature activation+1.79e-01

Pos logit contributions
estone+4.464
adem+3.905
font+3.834
PB+3.808
+.+3.740
Neg logit contributions
 Invaders-3.693
duction-3.582
bugs-3.559
 Kund-3.546
angs-3.421
Token /
Token ID1220
Feature activation+1.12e-02

Pos logit contributions
estone+0.587
PB+0.506
adem+0.501
+.+0.499
font+0.498
Neg logit contributions
duction-0.541
bugs-0.539
 Invaders-0.532
angs-0.523
 Kund-0.518
Tokenclear
Token ID20063
Feature activation-2.00e-01

Pos logit contributions
duction+0.098
bugs+0.098
 Invaders+0.097
angs+0.095
 Kund+0.095
Neg logit contributions
estone-0.112
PB-0.096
adem-0.095
font-0.095
+.-0.095
Token chat
Token ID8537
Feature activation-3.33e-02

Pos logit contributions
estone+1.990
PB+1.710
font+1.705
adem+1.698
+.+1.684
Neg logit contributions
duction-1.740
 Invaders-1.725
bugs-1.718
 Kund-1.691
angs-1.683
Token [
Token ID685
Feature activation-7.74e-02

Pos logit contributions
estone+0.328
PB+0.282
adem+0.280
font+0.279
+.+0.278
Neg logit contributions
duction-0.295
bugs-0.293
 Invaders-0.292
angs-0.286
 Kund-0.285
Token10
Token ID940
Feature activation+3.12e-01

Pos logit contributions
estone+0.846
PB+0.749
font+0.746
+.+0.741
adem+0.729
Neg logit contributions
 Invaders-0.610
duction-0.599
bugs-0.589
angs-0.579
 Kund-0.579
Token:
Token ID25
Feature activation+1.56e+00

Pos logit contributions
bugs+2.602
duction+2.565
 Invaders+2.547
 Kund+2.509
angs+2.494
Neg logit contributions
estone-3.213
adem-2.781
PB-2.771
 Flavoring-2.749
+.-2.730
Token47
Token ID2857
Feature activation+1.89e-01

Pos logit contributions
cz+4.965
 Invaders+4.810
 Kund+4.401
bugs+4.383
xx+4.025
Neg logit contributions
estone-20.393
ntil-19.822
insula-18.192
 activ-18.156
adem-18.129
Token]
Token ID60
Feature activation-7.54e-01

Pos logit contributions
bugs+0.931
duction+0.927
 Invaders+0.914
angs+0.881
 Kund+0.878
Neg logit contributions
estone-2.601
PB-2.338
adem-2.325
+.-2.314
font-2.313
Token <
Token ID1279
Feature activation+1.89e-01

Pos logit contributions
estone+5.008
PB+4.065
+.+4.019
font+4.012
 Flavoring+4.002
Neg logit contributions
duction-8.540
bugs-8.460
 Invaders-8.448
 Kund-8.286
angs-8.258
Tokenher
Token ID372
Feature activation+3.78e-02

Pos logit contributions
bugs+1.653
duction+1.645
 Invaders+1.610
angs+1.604
 Kund+1.586
Neg logit contributions
estone-1.884
PB-1.614
 Flavoring-1.613
+.-1.599
adem-1.593
Tokenret
Token ID1186
Feature activation+3.98e-01

Pos logit contributions
bugs+0.329
duction+0.328
 Invaders+0.325
angs+0.319
 Kund+0.317
Neg logit contributions
estone-0.378
PB-0.326
adem-0.322
+.-0.322
font-0.321
Token Option
Token ID16018
Feature activation+7.38e-01

Pos logit contributions
 Invaders+3.047
bugs+3.037
duction+2.993
 Kund+2.945
angs+2.898
Neg logit contributions
estone-3.443
adem-2.949
 Flavoring-2.940
+.-2.926
PB-2.918
Token <
Token ID1279
Feature activation+5.99e-01

Pos logit contributions
bugs+6.543
 Invaders+6.392
duction+6.329
 Kund+6.239
icks+6.186
Neg logit contributions
estone-6.818
 Flavoring-5.908
font-5.674
PB-5.637
adem-5.629
Token Piece
Token ID27053
Feature activation+6.77e-01

Pos logit contributions
 Invaders+5.248
bugs+5.145
duction+5.019
 Kund+4.981
cz+4.856
Neg logit contributions
estone-5.763
adem-4.952
font-4.835
+.-4.831
 Flavoring-4.823
Token >
Token ID1875
Feature activation+2.76e-01

Pos logit contributions
bugs+4.711
 Invaders+4.703
duction+4.691
angs+4.436
 Kund+4.415
Neg logit contributions
estone-7.507
adem-6.623
 Flavoring-6.553
font-6.462
+.-6.421
Token ;
Token ID2162
Feature activation+4.30e-01

Pos logit contributions
bugs+2.148
duction+2.147
 Invaders+2.142
angs+2.069
 Kund+2.066
Neg logit contributions
estone-3.001
adem-2.584
PB-2.583
font-2.568
 Flavoring-2.568
Token 64
Token ID5598
Feature activation+1.52e+00

Pos logit contributions
 Invaders+3.542
bugs+3.541
duction+3.488
 Kund+3.424
angs+3.393
Neg logit contributions
estone-4.389
adem-3.820
PB-3.777
+.-3.755
font-3.753
Token ],
Token ID16589
Feature activation+1.19e-01

Pos logit contributions
 Invaders+10.706
bugs+10.467
duction+10.001
cz+9.912
Die+9.768
Neg logit contributions
estone-13.585
 Flavoring-12.713
adem-12.038
font-11.765
insula-11.619
Token //
Token ID3373
Feature activation-8.60e-02

Pos logit contributions
bugs+1.059
duction+1.058
 Invaders+1.052
angs+1.028
 Kund+1.025
Neg logit contributions
estone-1.163
PB-0.999
adem-0.988
font-0.984
+.-0.983
Token Where
Token ID6350
Feature activation-6.16e-01

Pos logit contributions
estone+0.874
PB+0.754
+.+0.747
font+0.744
adem+0.742
Neg logit contributions
duction-0.741
bugs-0.732
angs-0.718
 Invaders-0.718
 Kund-0.707
Token are
Token ID389
Feature activation-1.18e-02

Pos logit contributions
estone+5.286
PB+4.412
+.+4.400
font+4.372
adem+4.339
Neg logit contributions
duction-6.026
angs-5.824
bugs-5.807
 Kund-5.740
cz-5.672
Token the
Token ID262
Feature activation-6.37e-02

Pos logit contributions
estone+0.119
PB+0.103
adem+0.102
font+0.102
+.+0.102
Neg logit contributions
duction-0.102
bugs-0.101
 Invaders-0.100
angs-0.099
 Kund-0.098
Token m
Token ID285
Feature activation+1.74e-01

Pos logit contributions
bugs+3.489
 Invaders+3.466
duction+3.427
angs+3.406
 Kund+3.403
Neg logit contributions
estone-3.636
 Flavoring-3.123
PB-3.115
adem-3.055
font-3.051
Token2
Token ID17
Feature activation+4.79e-01

Pos logit contributions
duction+1.656
bugs+1.655
 Invaders+1.640
angs+1.612
 Kund+1.606
Neg logit contributions
estone-1.591
PB-1.351
adem-1.335
font-1.328
+.-1.328
Tokenk
Token ID74
Feature activation+1.29e-01

Pos logit contributions
bugs+2.729
duction+2.677
 Kund+2.605
 Invaders+2.592
angs+2.582
Neg logit contributions
estone-6.093
 Flavoring-5.534
PB-5.440
adem-5.424
+.-5.369
Token [
Token ID685
Feature activation-2.62e-01

Pos logit contributions
duction+1.141
bugs+1.140
 Invaders+1.130
angs+1.107
 Kund+1.103
Neg logit contributions
estone-1.272
PB-1.094
adem-1.081
+.-1.078
font-1.078
Token10
Token ID940
Feature activation+4.96e-02

Pos logit contributions
estone+2.685
PB+2.396
font+2.396
+.+2.371
adem+2.284
Neg logit contributions
 Invaders-2.259
duction-2.179
igers-2.119
bugs-2.109
angs-2.100
Token:
Token ID25
Feature activation+1.51e+00

Pos logit contributions
duction+0.457
bugs+0.453
 Invaders+0.453
angs+0.444
 Kund+0.439
Neg logit contributions
estone-0.474
PB-0.407
font-0.402
+.-0.401
adem-0.397
Token48
Token ID2780
Feature activation+6.21e-01

Pos logit contributions
cz+5.530
bugs+5.174
 Kund+5.046
 Invaders+4.988
Thunder+4.888
Neg logit contributions
ntil-20.195
estone-19.522
ModLoader-18.340
insula-18.045
 activ-17.917
Token]
Token ID60
Feature activation-7.06e-01

Pos logit contributions
bugs+2.524
 Invaders+2.247
 Kund+2.245
cz+2.244
duction+2.217
Neg logit contributions
estone-8.884
ntil-8.416
adem-8.172
 activ-8.143
 Flavoring-8.116
Token <
Token ID1279
Feature activation+1.17e-01

Pos logit contributions
estone+4.811
PB+3.943
font+3.897
+.+3.886
 Flavoring+3.821
Neg logit contributions
duction-7.928
 Invaders-7.875
bugs-7.863
 Kund-7.721
angs-7.658
Tokendeath
Token ID22595
Feature activation+2.74e-01

Pos logit contributions
bugs+1.015
duction+1.013
 Invaders+0.996
angs+0.986
 Kund+0.978
Neg logit contributions
estone-1.179
PB-1.014
 Flavoring-1.006
+.-1.002
adem-1.002
Tokend
Token ID67
Feature activation+6.39e-01

Pos logit contributions
bugs+2.434
duction+2.403
 Invaders+2.340
angs+2.339
cz+2.307
Neg logit contributions
estone-2.690
 Flavoring-2.330
PB-2.328
+.-2.287
adem-2.281
Token y
Token ID331
Feature activation-1.17e-01

Pos logit contributions
bugs+3.089
 Invaders+3.064
duction+3.038
angs+3.009
 Kund+3.005
Neg logit contributions
estone-3.143
PB-2.688
 Flavoring-2.687
adem-2.642
font-2.632
Token2
Token ID17
Feature activation+1.82e-01

Pos logit contributions
estone+1.328
PB+1.163
adem+1.153
font+1.148
+.+1.146
Neg logit contributions
duction-0.863
bugs-0.860
 Invaders-0.858
 Kund-0.830
angs-0.825
Tokenk
Token ID74
Feature activation-1.52e-01

Pos logit contributions
bugs+1.320
duction+1.315
 Invaders+1.298
angs+1.276
 Kund+1.264
Neg logit contributions
estone-2.080
 Flavoring-1.815
PB-1.813
adem-1.810
+.-1.796
Token [
Token ID685
Feature activation-1.22e-01

Pos logit contributions
estone+1.457
PB+1.249
adem+1.238
+.+1.233
font+1.230
Neg logit contributions
duction-1.377
bugs-1.372
 Invaders-1.359
 Kund-1.329
angs-1.328
Token10
Token ID940
Feature activation+1.19e-01

Pos logit contributions
estone+1.318
PB+1.170
font+1.165
+.+1.157
adem+1.132
Neg logit contributions
 Invaders-0.988
duction-0.966
bugs-0.947
angs-0.933
 Kund-0.932
Token:
Token ID25
Feature activation+1.51e+00

Pos logit contributions
duction+1.064
bugs+1.060
 Invaders+1.055
angs+1.033
 Kund+1.027
Neg logit contributions
estone-1.162
PB-0.998
font-0.985
+.-0.984
adem-0.983
Token47
Token ID2857
Feature activation+1.47e-01

Pos logit contributions
cz+5.587
bugs+5.225
 Kund+5.071
 Invaders+4.991
Thunder+4.882
Neg logit contributions
ntil-20.064
estone-19.514
ModLoader-18.162
insula-17.886
 activ-17.859
Token]
Token ID60
Feature activation-7.25e-01

Pos logit contributions
duction+0.743
bugs+0.742
 Invaders+0.732
angs+0.705
 Kund+0.701
Neg logit contributions
estone-2.014
PB-1.810
adem-1.796
font-1.792
+.-1.792
Token <
Token ID1279
Feature activation+9.21e-02

Pos logit contributions
estone+4.839
PB+3.939
font+3.889
+.+3.875
 Flavoring+3.855
Neg logit contributions
duction-8.224
bugs-8.167
 Invaders-8.162
 Kund-7.994
angs-7.950
Tokenchain
Token ID7983
Feature activation+2.96e-01

Pos logit contributions
bugs+0.795
duction+0.794
 Invaders+0.782
angs+0.772
 Kund+0.766
Neg logit contributions
estone-0.927
PB-0.798
 Flavoring-0.789
adem-0.789
+.-0.789
Tokenx
Token ID87
Feature activation+7.09e-01

Pos logit contributions
bugs+2.622
duction+2.616
 Invaders+2.545
angs+2.539
cz+2.499
Neg logit contributions
estone-2.874
 Flavoring-2.490
PB-2.463
+.-2.450
adem-2.432
Token --
Token ID1377
Feature activation+5.64e-01

Pos logit contributions
estone+0.224
PB+0.193
adem+0.191
+.+0.191
font+0.190
Neg logit contributions
duction-0.191
bugs-0.191
 Invaders-0.190
angs-0.186
 Kund-0.185
Tokensecret
Token ID21078
Feature activation-9.89e-02

Pos logit contributions
bugs+4.723
duction+4.640
angs+4.562
cz+4.500
 Invaders+4.374
Neg logit contributions
estone-5.585
 Flavoring-5.014
PB-4.766
+.-4.736
adem-4.712
Token <
Token ID1279
Feature activation+4.08e-01

Pos logit contributions
estone+0.840
PB+0.702
adem+0.693
+.+0.690
font+0.690
Neg logit contributions
duction-1.010
bugs-1.010
 Invaders-1.002
angs-0.985
 Kund-0.982
TokenSecret
Token ID23725
Feature activation+3.90e-01

Pos logit contributions
duction+2.766
bugs+2.766
Thunder+2.716
angs+2.643
cz+2.626
Neg logit contributions
estone-4.738
adem-4.127
 Flavoring-4.088
font-4.062
 activ-4.052
Token Access
Token ID8798
Feature activation+1.11e+00

Pos logit contributions
 Invaders+3.257
duction+3.224
 Kund+3.198
angs+3.162
bugs+3.160
Neg logit contributions
estone-3.851
adem-3.296
font-3.291
PB-3.266
+.-3.207
Token Key
Token ID7383
Feature activation+1.51e+00

Pos logit contributions
 Kund+6.426
 Invaders+6.253
cz+5.551
bugs+5.495
Date+5.435
Neg logit contributions
estone-12.625
ntil-12.497
 activ-11.563
adem-11.506
insula-11.438
Token>
Token ID29
Feature activation+1.19e-01

Pos logit contributions
 Invaders+6.687
 Kund+6.673
duction+5.894
icks+5.743
»+5.688
Neg logit contributions
estone-17.251
ntil-16.124
adem-15.676
font-15.507
Flor-15.424
Token
Token ID198
Feature activation+8.17e-02

Pos logit contributions
bugs+0.953
duction+0.952
 Invaders+0.946
angs+0.924
 Kund+0.922
Neg logit contributions
estone-1.260
PB-1.092
adem-1.085
font-1.079
 Flavoring-1.078
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
duction+0.723
bugs+0.719
 Invaders+0.718
angs+0.702
 Kund+0.697
Neg logit contributions
estone-0.808
PB-0.696
font-0.688
+.-0.688
adem-0.683
TokenDem
Token ID11522
Feature activation-5.48e-01

Pos logit contributions
bugs+1.002
duction+1.001
 Invaders+0.990
angs+0.973
 Kund+0.968
Neg logit contributions
estone-1.073
PB-0.917
adem-0.910
 Flavoring-0.904
font-0.904
Tokeno
Token ID78
Feature activation-4.01e-01

Pos logit contributions
estone+4.522
adem+3.722
+.+3.668
PB+3.667
font+3.633
Neg logit contributions
 Invaders-5.677
duction-5.639
bugs-5.592
 Kund-5.532
angs-5.466
Token2
Token ID17
Feature activation+5.24e-01

Pos logit contributions
duction+0.566
bugs+0.565
 Invaders+0.559
angs+0.552
 Kund+0.547
Neg logit contributions
estone-0.597
PB-0.512
 Flavoring-0.507
adem-0.506
+.-0.504
Tokenk
Token ID74
Feature activation-8.83e-02

Pos logit contributions
bugs+2.590
duction+2.552
cz+2.510
angs+2.467
 Invaders+2.453
Neg logit contributions
estone-6.864
 Flavoring-6.369
PB-6.137
adem-6.133
font-6.083
Token lol
Token ID19462
Feature activation+5.37e-01

Pos logit contributions
estone+0.864
PB+0.742
adem+0.734
+.+0.731
font+0.731
Neg logit contributions
duction-0.788
bugs-0.786
 Invaders-0.779
angs-0.763
 Kund-0.761
Token [
Token ID685
Feature activation-1.88e-01

Pos logit contributions
bugs+4.061
cz+4.029
 Invaders+4.007
duction+4.002
angs+3.987
Neg logit contributions
estone-5.652
 Flavoring-5.049
PB-4.987
+.-4.900
adem-4.895
Token10
Token ID940
Feature activation+1.69e-01

Pos logit contributions
estone+1.980
PB+1.764
font+1.757
+.+1.744
adem+1.693
Neg logit contributions
 Invaders-1.564
duction-1.520
bugs-1.481
igers-1.472
angs-1.469
Token:
Token ID25
Feature activation+1.50e+00

Pos logit contributions
duction+1.483
bugs+1.482
 Invaders+1.470
angs+1.440
 Kund+1.435
Neg logit contributions
estone-1.672
PB-1.439
adem-1.423
font-1.418
+.-1.418
Token47
Token ID2857
Feature activation+1.82e-01

Pos logit contributions
cz+5.539
bugs+5.191
 Kund+4.994
 Invaders+4.983
Thunder+4.851
Neg logit contributions
ntil-19.937
estone-19.463
ModLoader-18.066
insula-17.835
 activ-17.783
Token]
Token ID60
Feature activation-7.20e-01

Pos logit contributions
bugs+0.898
duction+0.894
 Invaders+0.881
angs+0.850
 Kund+0.847
Neg logit contributions
estone-2.497
PB-2.245
adem-2.232
+.-2.222
font-2.221
Token <
Token ID1279
Feature activation+9.79e-02

Pos logit contributions
estone+4.809
PB+3.925
font+3.875
+.+3.852
 Flavoring+3.838
Neg logit contributions
duction-8.158
 Invaders-8.095
bugs-8.090
 Kund-7.930
angs-7.890
Tokenm
Token ID76
Feature activation-1.11e-01

Pos logit contributions
bugs+0.847
duction+0.845
 Invaders+0.832
angs+0.822
 Kund+0.816
Neg logit contributions
estone-0.985
PB-0.848
 Flavoring-0.839
+.-0.838
adem-0.838
Tokenik
Token ID1134
Feature activation-3.71e-02

Pos logit contributions
estone+1.167
PB+1.008
adem+1.005
font+0.999
+.+0.993
Neg logit contributions
bugs-0.909
 Invaders-0.909
duction-0.908
 Kund-0.880
angs-0.872
Token m
Token ID285
Feature activation+2.68e-01

Pos logit contributions
bugs+2.643
 Invaders+2.612
duction+2.604
angs+2.572
 Kund+2.563
Neg logit contributions
estone-2.671
 Flavoring-2.290
PB-2.276
adem-2.250
font-2.236
Token2
Token ID17
Feature activation+4.03e-01

Pos logit contributions
duction+2.323
bugs+2.297
angs+2.277
 Invaders+2.229
cz+2.219
Neg logit contributions
estone-2.650
 Flavoring-2.345
PB-2.290
adem-2.262
font-2.231
Tokenk
Token ID74
Feature activation-6.87e-02

Pos logit contributions
bugs+2.373
duction+2.344
 Invaders+2.283
 Kund+2.270
angs+2.261
Neg logit contributions
estone-5.085
 Flavoring-4.582
PB-4.540
adem-4.508
+.-4.473
Token [
Token ID685
Feature activation-1.98e-01

Pos logit contributions
estone+0.688
PB+0.592
adem+0.587
font+0.584
+.+0.584
Neg logit contributions
bugs-0.596
duction-0.596
 Invaders-0.592
angs-0.580
 Kund-0.578
Token10
Token ID940
Feature activation+8.68e-02

Pos logit contributions
estone+2.078
PB+1.855
font+1.846
+.+1.830
adem+1.778
Neg logit contributions
 Invaders-1.649
duction-1.602
bugs-1.558
igers-1.547
angs-1.545
Token:
Token ID25
Feature activation+1.50e+00

Pos logit contributions
duction+0.787
bugs+0.782
 Invaders+0.780
angs+0.764
 Kund+0.758
Neg logit contributions
estone-0.840
PB-0.721
font-0.712
+.-0.711
adem-0.708
Token47
Token ID2857
Feature activation+1.54e-01

Pos logit contributions
cz+5.586
bugs+5.263
 Kund+5.058
 Invaders+5.034
Thunder+4.900
Neg logit contributions
ntil-19.829
estone-19.351
ModLoader-18.003
insula-17.720
 activ-17.708
Token]
Token ID60
Feature activation-6.31e-01

Pos logit contributions
duction+0.773
bugs+0.773
 Invaders+0.761
angs+0.734
 Kund+0.730
Neg logit contributions
estone-2.107
PB-1.894
adem-1.880
font-1.875
+.-1.875
Token <
Token ID1279
Feature activation+8.70e-02

Pos logit contributions
estone+3.974
PB+3.256
font+3.219
+.+3.171
 Flavoring+3.139
Neg logit contributions
duction-7.359
 Invaders-7.265
bugs-7.264
angs-7.112
 Kund-7.078
Tokenk
Token ID74
Feature activation+1.05e-01

Pos logit contributions
bugs+0.750
duction+0.749
 Invaders+0.738
angs+0.728
 Kund+0.723
Neg logit contributions
estone-0.877
PB-0.755
 Flavoring-0.747
adem-0.747
+.-0.746
Tokenasse
Token ID21612
Feature activation+4.05e-01

Pos logit contributions
bugs+0.599
duction+0.599
 Invaders+0.587
angs+0.576
 Kund+0.567
Neg logit contributions
estone-1.360
PB-1.221
 Flavoring-1.209
adem-1.206
+.-1.205
Token m
Token ID285
Feature activation+2.89e-01

Pos logit contributions
bugs+4.204
 Invaders+4.126
duction+4.104
cz+4.091
angs+4.048
Neg logit contributions
estone-4.616
 Flavoring-4.008
PB-3.981
adem-3.904
font-3.862
Token2
Token ID17
Feature activation+5.08e-01

Pos logit contributions
duction+2.670
bugs+2.667
 Invaders+2.612
angs+2.598
 Kund+2.575
Neg logit contributions
estone-2.718
PB-2.328
 Flavoring-2.315
adem-2.297
+.-2.277
Tokenk
Token ID74
Feature activation+3.07e-01

Pos logit contributions
bugs+2.863
duction+2.791
 Kund+2.729
cz+2.707
 Invaders+2.692
Neg logit contributions
estone-6.488
 Flavoring-5.913
adem-5.794
PB-5.783
ntil-5.766
Token [
Token ID685
Feature activation-2.90e-01

Pos logit contributions
bugs+2.570
 Invaders+2.553
duction+2.552
 Kund+2.503
angs+2.481
Neg logit contributions
estone-3.136
adem-2.715
PB-2.712
 Flavoring-2.674
font-2.674
Token10
Token ID940
Feature activation+3.32e-02

Pos logit contributions
estone+2.931
font+2.626
PB+2.621
+.+2.591
adem+2.491
Neg logit contributions
 Invaders-2.538
duction-2.434
igers-2.376
bugs-2.349
angs-2.344
Token:
Token ID25
Feature activation+1.50e+00

Pos logit contributions
duction+0.308
 Invaders+0.304
bugs+0.304
angs+0.299
 Kund+0.295
Neg logit contributions
estone-0.315
PB-0.270
font-0.267
+.-0.266
adem-0.263
Token47
Token ID2857
Feature activation+1.91e-01

Pos logit contributions
cz+5.527
bugs+5.262
 Kund+5.000
 Invaders+4.990
Thunder+4.949
Neg logit contributions
ntil-19.926
estone-19.303
ModLoader-18.043
insula-17.806
 activ-17.748
Token]
Token ID60
Feature activation-6.47e-01

Pos logit contributions
bugs+0.938
duction+0.932
 Invaders+0.919
angs+0.886
 Kund+0.883
Neg logit contributions
estone-2.622
PB-2.357
adem-2.345
+.-2.334
font-2.332
Token <
Token ID1279
Feature activation+1.58e-01

Pos logit contributions
estone+4.435
PB+3.620
font+3.587
+.+3.552
 Flavoring+3.543
Neg logit contributions
duction-7.325
 Invaders-7.272
bugs-7.254
 Kund-7.122
angs-7.085
Tokenmad
Token ID9937
Feature activation-2.48e-02

Pos logit contributions
bugs+1.376
duction+1.372
 Invaders+1.342
angs+1.335
 Kund+1.322
Neg logit contributions
estone-1.580
PB-1.354
 Flavoring-1.354
+.-1.340
adem-1.340
Tokenag
Token ID363
Feature activation+4.89e-01

Pos logit contributions
estone+0.259
PB+0.224
adem+0.222
font+0.221
+.+0.221
Neg logit contributions
duction-0.206
bugs-0.205
 Invaders-0.205
angs-0.199
 Kund-0.199
Token l
Token ID300
Feature activation+2.23e-01

Pos logit contributions
bugs+0.263
duction+0.263
 Invaders+0.261
angs+0.255
 Kund+0.254
Neg logit contributions
estone-0.320
PB-0.277
adem-0.274
+.-0.273
font-0.273
Tokenma
Token ID2611
Feature activation-2.89e-02

Pos logit contributions
duction+1.733
bugs+1.725
angs+1.704
 Invaders+1.698
 Kund+1.666
Neg logit contributions
estone-2.404
PB-2.118
 Flavoring-2.108
+.-2.075
font-2.072
Tokeno
Token ID78
Feature activation-2.84e-01

Pos logit contributions
estone+0.259
PB+0.219
adem+0.216
+.+0.215
font+0.215
Neg logit contributions
duction-0.282
bugs-0.282
 Invaders-0.280
angs-0.274
 Kund-0.274
Token [
Token ID685
Feature activation-2.02e-01

Pos logit contributions
estone+2.669
PB+2.280
adem+2.261
+.+2.251
font+2.243
Neg logit contributions
duction-2.630
bugs-2.603
 Invaders-2.577
angs-2.506
 Kund-2.505
Token10
Token ID940
Feature activation+1.12e-01

Pos logit contributions
estone+2.129
font+1.892
PB+1.888
+.+1.872
adem+1.826
Neg logit contributions
 Invaders-1.677
duction-1.627
bugs-1.581
angs-1.575
igers-1.575
Token:
Token ID25
Feature activation+1.49e+00

Pos logit contributions
duction+1.003
bugs+0.997
 Invaders+0.994
angs+0.973
 Kund+0.967
Neg logit contributions
estone-1.091
PB-0.937
font-0.925
+.-0.924
adem-0.923
Token47
Token ID2857
Feature activation+1.24e-01

Pos logit contributions
cz+5.408
bugs+5.065
 Invaders+4.966
 Kund+4.891
Thunder+4.614
Neg logit contributions
ntil-19.460
estone-19.345
ModLoader-17.506
 activ-17.470
insula-17.451
Token]
Token ID60
Feature activation-7.49e-01

Pos logit contributions
duction+0.636
bugs+0.633
 Invaders+0.626
angs+0.603
 Kund+0.599
Neg logit contributions
estone-1.691
PB-1.519
adem-1.505
font-1.505
+.-1.504
Token <
Token ID1279
Feature activation+1.13e-01

Pos logit contributions
estone+4.993
PB+4.056
font+4.018
+.+4.002
 Flavoring+3.982
Neg logit contributions
duction-8.479
bugs-8.401
 Invaders-8.398
 Kund-8.223
angs-8.181
Tokenrev
Token ID18218
Feature activation+2.27e-01

Pos logit contributions
bugs+0.977
duction+0.975
 Invaders+0.959
angs+0.948
 Kund+0.941
Neg logit contributions
estone-1.134
PB-0.975
 Flavoring-0.967
+.-0.964
adem-0.963
Tokenitle
Token ID2578
Feature activation+7.49e-01

Pos logit contributions
duction+1.891
bugs+1.880
 Invaders+1.830
angs+1.819
 Kund+1.797
Neg logit contributions
estone-2.336
PB-2.038
 Flavoring-2.032
+.-2.005
adem-1.991
Tokenanch
Token ID3702
Feature activation+9.21e-01

Pos logit contributions
duction+2.993
bugs+2.980
cz+2.905
angs+2.848
 Kund+2.829
Neg logit contributions
estone-6.595
PB-6.024
 Flavoring-5.962
+.-5.918
adem-5.872
Tokenak
Token ID461
Feature activation+2.72e-01

Pos logit contributions
bugs+5.471
cz+5.425
angs+5.381
duction+5.283
 Kund+5.267
Neg logit contributions
estone-10.561
ntil-10.151
PB-9.742
 Flavoring-9.734
 activ-9.374
Token and
Token ID290
Feature activation+7.52e-01

Pos logit contributions
bugs+2.391
duction+2.382
 Invaders+2.369
 Kund+2.347
angs+2.337
Neg logit contributions
estone-2.646
PB-2.297
 Flavoring-2.267
font-2.251
adem-2.250
Token Mak
Token ID15841
Feature activation+1.85e-01

Pos logit contributions
 Kund+5.595
 Invaders+5.465
duction+5.243
cz+5.190
bugs+5.175
Neg logit contributions
estone-8.200
PB-7.278
font-6.992
 Flavoring-6.970
+.-6.950
Tokenovi
Token ID47297
Feature activation+3.26e-01

Pos logit contributions
duction+2.031
bugs+2.027
 Invaders+2.016
angs+1.980
 Kund+1.976
Neg logit contributions
estone-1.420
PB-1.171
adem-1.146
font-1.145
+.-1.141
Tokenich
Token ID488
Feature activation+1.48e+00

Pos logit contributions
bugs+2.703
duction+2.694
 Invaders+2.665
angs+2.635
 Kund+2.609
Neg logit contributions
estone-3.341
PB-2.947
font-2.875
 Flavoring-2.873
adem-2.870
Tokenuk
Token ID2724
Feature activation+3.49e-01

Pos logit contributions
bugs+4.131
 Kund+4.079
angs+4.055
cz+3.998
icks+3.830
Neg logit contributions
estone-20.040
ntil-19.651
PB-19.232
ModLoader-19.082
 Flavoring-19.054
Token,
Token ID11
Feature activation+4.76e-02

Pos logit contributions
duction+2.932
bugs+2.920
 Invaders+2.909
 Kund+2.876
angs+2.874
Neg logit contributions
estone-3.494
 Flavoring-3.068
PB-3.038
font-3.005
adem-2.987
Token the
Token ID262
Feature activation-4.05e-02

Pos logit contributions
duction+0.412
bugs+0.412
 Invaders+0.408
angs+0.400
 Kund+0.397
Neg logit contributions
estone-0.477
PB-0.411
adem-0.408
+.-0.406
font-0.406
Token other
Token ID584
Feature activation-9.57e-02

Pos logit contributions
estone+0.397
PB+0.340
adem+0.338
+.+0.336
font+0.336
Neg logit contributions
duction-0.362
bugs-0.361
 Invaders-0.356
angs-0.349
 Kund-0.345
Token owners
Token ID4393
Feature activation+2.80e-02

Pos logit contributions
estone+0.955
PB+0.823
adem+0.818
+.+0.814
font+0.813
Neg logit contributions
bugs-0.833
duction-0.831
 Invaders-0.818
angs-0.803
igers-0.791
Token>
Token ID29
Feature activation-1.48e-01

Pos logit contributions
bugs+7.284
angs+7.244
duction+7.158
cz+7.050
icks+7.029
Neg logit contributions
estone-7.873
 Flavoring-7.231
PB-6.960
+.-6.923
font-6.768
Token dude
Token ID18396
Feature activation-3.33e-01

Pos logit contributions
estone+1.430
PB+1.232
adem+1.220
+.+1.220
font+1.214
Neg logit contributions
duction-1.327
bugs-1.318
 Invaders-1.298
angs-1.283
 Kund-1.263
Token nice
Token ID3621
Feature activation-3.26e-02

Pos logit contributions
estone+3.065
PB+2.620
+.+2.603
adem+2.598
font+2.591
Neg logit contributions
duction-3.100
 Invaders-3.056
bugs-3.043
 Kund-3.004
angs-2.980
Token [
Token ID685
Feature activation-1.61e-01

Pos logit contributions
estone+0.316
PB+0.271
adem+0.267
+.+0.267
font+0.267
Neg logit contributions
duction-0.295
bugs-0.294
 Invaders-0.292
angs-0.286
 Kund-0.285
Token10
Token ID940
Feature activation+1.56e-01

Pos logit contributions
estone+1.718
PB+1.524
font+1.523
+.+1.510
adem+1.473
Neg logit contributions
 Invaders-1.326
duction-1.287
bugs-1.258
 Kund-1.245
angs-1.244
Token:
Token ID25
Feature activation+1.48e+00

Pos logit contributions
duction+1.375
bugs+1.374
 Invaders+1.363
angs+1.335
 Kund+1.330
Neg logit contributions
estone-1.544
PB-1.328
adem-1.313
font-1.309
+.-1.309
Token47
Token ID2857
Feature activation+1.19e-01

Pos logit contributions
cz+5.416
bugs+5.223
 Kund+5.033
 Invaders+4.971
Thunder+4.829
Neg logit contributions
ntil-19.816
estone-19.277
ModLoader-17.764
insula-17.666
 activ-17.551
Token]
Token ID60
Feature activation-7.31e-01

Pos logit contributions
duction+0.611
bugs+0.607
 Invaders+0.601
angs+0.579
 Kund+0.575
Neg logit contributions
estone-1.618
PB-1.454
adem-1.441
font-1.440
+.-1.439
Token <
Token ID1279
Feature activation+1.86e-01

Pos logit contributions
estone+4.870
PB+3.960
font+3.923
+.+3.905
 Flavoring+3.885
Neg logit contributions
duction-8.286
 Invaders-8.222
bugs-8.207
 Kund-8.045
angs-8.015
Tokensp
Token ID2777
Feature activation+6.03e-02

Pos logit contributions
bugs+1.620
duction+1.614
 Invaders+1.576
angs+1.571
 Kund+1.554
Neg logit contributions
estone-1.851
 Flavoring-1.587
PB-1.585
+.-1.569
adem-1.566
Tokenit
Token ID270
Feature activation-2.45e-01

Pos logit contributions
duction+0.493
bugs+0.493
 Invaders+0.488
angs+0.479
 Kund+0.476
Neg logit contributions
estone-0.632
PB-0.550
adem-0.543
+.-0.543
font-0.542
Token>
Token ID29
Feature activation-1.38e-01

Pos logit contributions
bugs+4.664
cz+4.444
duction+4.384
angs+4.380
 Invaders+4.288
Neg logit contributions
estone-9.060
 Flavoring-8.392
PB-7.997
+.-7.941
adem-7.927
Token H
Token ID367
Feature activation-5.16e-02

Pos logit contributions
estone+1.334
PB+1.151
adem+1.141
+.+1.139
font+1.134
Neg logit contributions
duction-1.235
bugs-1.227
 Invaders-1.208
angs-1.193
 Kund-1.176
Tokenaha
Token ID12236
Feature activation+5.03e-01

Pos logit contributions
estone+0.532
PB+0.461
adem+0.456
+.+0.454
font+0.454
Neg logit contributions
bugs-0.433
duction-0.433
 Invaders-0.429
 Kund-0.418
angs-0.418
Token [
Token ID685
Feature activation-8.43e-02

Pos logit contributions
bugs+4.278
 Invaders+4.260
angs+4.209
 Kund+4.204
duction+4.189
Neg logit contributions
estone-4.913
 Flavoring-4.255
PB-4.213
adem-4.190
font-4.174
Token10
Token ID940
Feature activation+1.95e-01

Pos logit contributions
estone+0.921
PB+0.816
font+0.811
+.+0.807
adem+0.794
Neg logit contributions
 Invaders-0.666
duction-0.655
bugs-0.642
angs-0.632
 Kund-0.630
Token:
Token ID25
Feature activation+1.48e+00

Pos logit contributions
bugs+1.697
duction+1.693
 Invaders+1.679
angs+1.644
 Kund+1.642
Neg logit contributions
estone-1.951
PB-1.680
adem-1.667
+.-1.655
font-1.655
Token47
Token ID2857
Feature activation+1.27e-01

Pos logit contributions
cz+5.208
 Invaders+4.940
bugs+4.889
 Kund+4.752
Thunder+4.507
Neg logit contributions
estone-19.380
ntil-19.256
insula-17.424
 activ-17.384
adem-17.289
Token]
Token ID60
Feature activation-7.15e-01

Pos logit contributions
duction+0.650
bugs+0.647
 Invaders+0.640
angs+0.616
 Kund+0.612
Neg logit contributions
estone-1.731
PB-1.556
adem-1.542
font-1.541
+.-1.540
Token <
Token ID1279
Feature activation+1.78e-01

Pos logit contributions
estone+4.795
PB+3.907
font+3.859
+.+3.843
 Flavoring+3.828
Neg logit contributions
duction-8.111
bugs-8.042
 Invaders-8.031
 Kund-7.869
angs-7.837
Tokent
Token ID83
Feature activation+4.63e-01

Pos logit contributions
bugs+1.553
duction+1.547
 Invaders+1.514
angs+1.508
 Kund+1.492
Neg logit contributions
estone-1.780
PB-1.526
 Flavoring-1.524
+.-1.512
adem-1.507
Tokenoxic
Token ID18047
Feature activation+5.90e-01

Pos logit contributions
bugs+3.911
angs+3.868
duction+3.861
igers+3.839
cz+3.823
Neg logit contributions
estone-4.527
 Flavoring-4.053
PB-3.998
+.-3.940
font-3.856
Token m
Token ID285
Feature activation+1.93e-01

Pos logit contributions
bugs+3.670
 Invaders+3.642
duction+3.605
 Kund+3.573
angs+3.568
Neg logit contributions
estone-3.812
 Flavoring-3.263
PB-3.257
adem-3.201
font-3.192
Token2
Token ID17
Feature activation+5.35e-01

Pos logit contributions
duction+1.823
bugs+1.822
 Invaders+1.802
angs+1.774
 Kund+1.766
Neg logit contributions
estone-1.774
PB-1.509
adem-1.491
 Flavoring-1.484
+.-1.484
Tokenk
Token ID74
Feature activation+2.09e-01

Pos logit contributions
bugs+2.968
duction+2.904
 Kund+2.831
cz+2.819
 Invaders+2.798
Neg logit contributions
estone-6.849
 Flavoring-6.258
PB-6.119
adem-6.113
ntil-6.072
Token [
Token ID685
Feature activation-1.85e-01

Pos logit contributions
bugs+1.811
duction+1.809
 Invaders+1.799
 Kund+1.758
angs+1.758
Neg logit contributions
estone-2.095
PB-1.806
adem-1.790
font-1.781
+.-1.780
Token10
Token ID940
Feature activation+8.40e-02

Pos logit contributions
estone+1.947
PB+1.734
font+1.728
+.+1.713
adem+1.665
Neg logit contributions
 Invaders-1.546
duction-1.503
bugs-1.462
igers-1.452
angs-1.449
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
duction+0.764
bugs+0.758
 Invaders+0.757
angs+0.742
 Kund+0.735
Neg logit contributions
estone-0.812
PB-0.697
font-0.688
+.-0.687
adem-0.684
Token47
Token ID2857
Feature activation+1.63e-01

Pos logit contributions
cz+5.469
bugs+5.227
 Kund+5.022
 Invaders+5.003
Thunder+4.855
Neg logit contributions
ntil-19.263
estone-18.892
ModLoader-17.383
insula-17.266
 activ-17.232
Token]
Token ID60
Feature activation-6.52e-01

Pos logit contributions
bugs+0.815
duction+0.814
 Invaders+0.802
angs+0.773
 Kund+0.769
Neg logit contributions
estone-2.233
PB-2.007
adem-1.993
+.-1.986
font-1.986
Token <
Token ID1279
Feature activation+1.36e-01

Pos logit contributions
estone+4.470
PB+3.651
font+3.604
+.+3.586
 Flavoring+3.565
Neg logit contributions
duction-7.379
 Invaders-7.326
bugs-7.321
 Kund-7.172
angs-7.142
Tokensn
Token ID16184
Feature activation-4.40e-01

Pos logit contributions
bugs+1.177
duction+1.174
 Invaders+1.153
angs+1.144
 Kund+1.134
Neg logit contributions
estone-1.364
PB-1.172
 Flavoring-1.166
+.-1.159
adem-1.158
Tokeniping
Token ID34690
Feature activation-2.27e-02

Pos logit contributions
estone+4.667
adem+4.091
font+4.044
PB+4.023
+.+3.941
Neg logit contributions
 Invaders-3.562
bugs-3.443
duction-3.434
 Kund-3.410
angs-3.246
Token m
Token ID285
Feature activation+2.47e-01

Pos logit contributions
bugs+2.990
 Invaders+2.973
duction+2.947
angs+2.918
 Kund+2.914
Neg logit contributions
estone-3.022
PB-2.580
 Flavoring-2.573
adem-2.532
font-2.530
Token2
Token ID17
Feature activation+4.82e-01

Pos logit contributions
duction+2.151
bugs+2.138
angs+2.107
 Invaders+2.076
cz+2.054
Neg logit contributions
estone-2.428
 Flavoring-2.132
PB-2.093
adem-2.072
font-2.056
Tokenk
Token ID74
Feature activation+9.71e-02

Pos logit contributions
bugs+2.735
duction+2.690
 Kund+2.615
 Invaders+2.613
angs+2.592
Neg logit contributions
estone-6.150
 Flavoring-5.581
PB-5.489
adem-5.472
font-5.424
Token [
Token ID685
Feature activation-1.65e-01

Pos logit contributions
bugs+0.799
 Invaders+0.799
duction+0.795
angs+0.780
 Kund+0.778
Neg logit contributions
estone-1.011
PB-0.873
 Flavoring-0.872
adem-0.869
font-0.864
Token10
Token ID940
Feature activation+1.06e-01

Pos logit contributions
estone+1.751
PB+1.560
font+1.551
+.+1.542
adem+1.499
Neg logit contributions
 Invaders-1.363
duction-1.330
bugs-1.297
angs-1.282
igers-1.281
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
duction+0.960
bugs+0.954
 Invaders+0.951
angs+0.931
 Kund+0.925
Neg logit contributions
estone-1.035
PB-0.889
font-0.877
+.-0.876
adem-0.874
Token47
Token ID2857
Feature activation+1.64e-01

Pos logit contributions
cz+5.523
bugs+5.234
 Kund+5.067
 Invaders+5.033
Thunder+4.917
Neg logit contributions
ntil-19.259
estone-18.858
ModLoader-17.421
insula-17.271
 activ-17.228
Token]
Token ID60
Feature activation-6.88e-01

Pos logit contributions
bugs+0.821
duction+0.820
 Invaders+0.808
angs+0.778
 Kund+0.774
Neg logit contributions
estone-2.252
PB-2.024
adem-2.010
+.-2.004
font-2.003
Token <
Token ID1279
Feature activation+6.34e-02

Pos logit contributions
estone+4.632
PB+3.784
font+3.732
+.+3.713
 Flavoring+3.694
Neg logit contributions
duction-7.805
bugs-7.748
 Invaders-7.746
 Kund-7.585
angs-7.556
Tokenmom
Token ID32542
Feature activation+5.62e-02

Pos logit contributions
bugs+0.545
duction+0.545
 Invaders+0.537
angs+0.529
 Kund+0.526
Neg logit contributions
estone-0.641
PB-0.553
adem-0.547
+.-0.546
 Flavoring-0.545
Tokenper
Token ID525
Feature activation+3.30e-01

Pos logit contributions
 Invaders+0.503
duction+0.499
bugs+0.498
angs+0.488
 Kund+0.487
Neg logit contributions
estone-0.554
PB-0.475
font-0.470
adem-0.469
+.-0.466
Token Mang
Token ID27609
Feature activation+4.64e-01

Pos logit contributions
bugs+3.586
 Invaders+3.532
duction+3.524
angs+3.472
cz+3.467
Neg logit contributions
estone-3.794
 Flavoring-3.282
PB-3.249
adem-3.200
font-3.183
Token0
Token ID15
Feature activation+1.08e-01

Pos logit contributions
bugs+4.156
duction+4.081
 Invaders+4.031
angs+4.030
 Kund+3.977
Neg logit contributions
estone-4.331
PB-3.802
 Flavoring-3.797
font-3.677
adem-3.676
Tokenking
Token ID3364
Feature activation+5.13e-02

Pos logit contributions
bugs+0.923
duction+0.919
 Invaders+0.915
angs+0.896
 Kund+0.893
Neg logit contributions
estone-1.098
PB-0.947
 Flavoring-0.942
+.-0.938
font-0.937
Token [
Token ID685
Feature activation-2.53e-01

Pos logit contributions
bugs+0.454
duction+0.454
 Invaders+0.450
angs+0.441
 Kund+0.440
Neg logit contributions
estone-0.506
PB-0.434
adem-0.430
+.-0.428
font-0.428
Token10
Token ID940
Feature activation+6.83e-02

Pos logit contributions
estone+2.627
PB+2.356
font+2.346
+.+2.312
adem+2.248
Neg logit contributions
 Invaders-2.148
duction-2.078
igers-2.016
bugs-2.013
 Kund-2.011
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
duction+0.622
bugs+0.617
 Invaders+0.616
angs+0.604
 Kund+0.598
Neg logit contributions
estone-0.658
PB-0.565
font-0.558
+.-0.557
adem-0.554
Token47
Token ID2857
Feature activation+1.39e-01

Pos logit contributions
cz+4.930
 Invaders+4.783
bugs+4.513
 Kund+4.448
Thunder+4.142
Neg logit contributions
estone-19.085
ntil-18.327
adem-16.944
insula-16.941
 activ-16.888
Token]
Token ID60
Feature activation-7.04e-01

Pos logit contributions
duction+0.706
bugs+0.704
 Invaders+0.695
angs+0.670
 Kund+0.665
Neg logit contributions
estone-1.903
PB-1.710
adem-1.696
font-1.693
+.-1.693
Token <
Token ID1279
Feature activation+1.68e-01

Pos logit contributions
estone+4.760
PB+3.867
font+3.821
+.+3.820
 Flavoring+3.816
Neg logit contributions
duction-7.974
bugs-7.892
 Invaders-7.879
 Kund-7.724
angs-7.691
Tokendan
Token ID25604
Feature activation+2.39e-01

Pos logit contributions
bugs+1.464
duction+1.458
 Invaders+1.428
angs+1.421
 Kund+1.407
Neg logit contributions
estone-1.687
PB-1.447
 Flavoring-1.443
+.-1.432
adem-1.429
Tokenides
Token ID1460
Feature activation+5.10e-01

Pos logit contributions
duction+2.090
bugs+2.083
 Invaders+2.031
angs+2.030
cz+1.994
Neg logit contributions
estone-2.365
 Flavoring-2.047
PB-2.044
+.-2.018
adem-2.001
Token m
Token ID285
Feature activation+3.46e-01

Pos logit contributions
bugs+2.493
 Invaders+2.459
duction+2.457
angs+2.420
 Kund+2.415
Neg logit contributions
estone-2.516
 Flavoring-2.160
PB-2.145
adem-2.119
font-2.109
Token2
Token ID17
Feature activation+3.96e-01

Pos logit contributions
duction+2.890
bugs+2.871
angs+2.850
cz+2.763
 Invaders+2.760
Neg logit contributions
estone-3.485
 Flavoring-3.126
PB-3.043
adem-2.993
font-2.945
Tokenk
Token ID74
Feature activation+1.81e-01

Pos logit contributions
bugs+2.358
duction+2.328
 Invaders+2.263
 Kund+2.255
angs+2.244
Neg logit contributions
estone-4.983
 Flavoring-4.485
PB-4.440
adem-4.421
+.-4.385
Token [
Token ID685
Feature activation-1.80e-01

Pos logit contributions
bugs+1.449
 Invaders+1.445
duction+1.439
angs+1.418
 Kund+1.408
Neg logit contributions
estone-1.896
 Flavoring-1.651
PB-1.647
adem-1.646
font-1.630
Token10
Token ID940
Feature activation+7.04e-02

Pos logit contributions
estone+1.899
PB+1.695
font+1.686
+.+1.668
adem+1.629
Neg logit contributions
 Invaders-1.489
duction-1.448
bugs-1.411
angs-1.396
igers-1.395
Token:
Token ID25
Feature activation+1.45e+00

Pos logit contributions
duction+0.642
bugs+0.637
 Invaders+0.635
angs+0.623
 Kund+0.617
Neg logit contributions
estone-0.678
PB-0.582
font-0.575
+.-0.574
adem-0.571
Token47
Token ID2857
Feature activation+2.32e-01

Pos logit contributions
cz+5.357
bugs+5.047
 Invaders+4.923
 Kund+4.900
Thunder+4.782
Neg logit contributions
ntil-19.106
estone-18.811
ModLoader-17.192
insula-17.169
 activ-17.154
Token]
Token ID60
Feature activation-6.23e-01

Pos logit contributions
bugs+1.117
duction+1.103
 Invaders+1.088
angs+1.050
 Kund+1.049
Neg logit contributions
estone-3.220
PB-2.896
adem-2.888
 Flavoring-2.872
+.-2.868
Token <
Token ID1279
Feature activation+1.88e-01

Pos logit contributions
estone+4.298
PB+3.525
font+3.474
+.+3.447
 Flavoring+3.425
Neg logit contributions
duction-7.056
 Invaders-7.002
bugs-6.985
 Kund-6.862
angs-6.834
Tokenl
Token ID75
Feature activation+5.36e-01

Pos logit contributions
bugs+1.629
duction+1.625
 Invaders+1.587
angs+1.584
 Kund+1.567
Neg logit contributions
estone-1.878
 Flavoring-1.613
PB-1.606
+.-1.593
adem-1.591
Tokenucky
Token ID5309
Feature activation+5.47e-01

Pos logit contributions
angs+4.429
duction+4.417
bugs+4.382
cz+4.308
igers+4.298
Neg logit contributions
estone-5.202
 Flavoring-4.750
PB-4.660
+.-4.592
font-4.494
Token m
Token ID285
Feature activation+2.28e-01

Pos logit contributions
bugs+2.431
 Invaders+2.418
duction+2.412
angs+2.386
 Kund+2.371
Neg logit contributions
estone-2.897
 Flavoring-2.524
PB-2.506
font-2.467
+.-2.460
Token2
Token ID17
Feature activation+4.64e-01

Pos logit contributions
duction+1.990
bugs+1.973
angs+1.951
 Invaders+1.921
cz+1.900
Neg logit contributions
estone-2.246
 Flavoring-1.980
PB-1.944
adem-1.914
font-1.902
Tokenk
Token ID74
Feature activation+9.62e-02

Pos logit contributions
bugs+2.658
duction+2.608
 Invaders+2.556
 Kund+2.536
angs+2.523
Neg logit contributions
estone-5.892
 Flavoring-5.344
PB-5.268
adem-5.240
font-5.199
Token [
Token ID685
Feature activation-1.23e-01

Pos logit contributions
bugs+0.791
 Invaders+0.788
duction+0.786
angs+0.774
 Kund+0.768
Neg logit contributions
estone-1.000
PB-0.867
 Flavoring-0.864
adem-0.861
font-0.857
Token10
Token ID940
Feature activation+1.16e-01

Pos logit contributions
estone+1.323
PB+1.176
font+1.170
+.+1.160
adem+1.138
Neg logit contributions
 Invaders-0.992
duction-0.971
bugs-0.949
angs-0.936
 Kund-0.936
Token:
Token ID25
Feature activation+1.44e+00

Pos logit contributions
duction+1.039
bugs+1.034
 Invaders+1.030
angs+1.009
 Kund+1.002
Neg logit contributions
estone-1.132
PB-0.973
font-0.960
+.-0.958
adem-0.957
Token47
Token ID2857
Feature activation+1.65e-01

Pos logit contributions
cz+5.330
bugs+5.047
 Invaders+4.942
 Kund+4.856
Thunder+4.668
Neg logit contributions
ntil-18.828
estone-18.739
insula-16.974
 activ-16.947
ModLoader-16.879
Token]
Token ID60
Feature activation-6.39e-01

Pos logit contributions
bugs+0.820
duction+0.818
 Invaders+0.807
angs+0.777
 Kund+0.774
Neg logit contributions
estone-2.258
PB-2.029
adem-2.017
+.-2.009
font-2.009
Token <
Token ID1279
Feature activation+1.37e-01

Pos logit contributions
estone+4.416
PB+3.598
font+3.562
+.+3.539
 Flavoring+3.522
Neg logit contributions
duction-7.217
 Invaders-7.159
bugs-7.155
 Kund-7.008
angs-6.974
Tokenmom
Token ID32542
Feature activation+6.35e-02

Pos logit contributions
bugs+1.188
duction+1.185
 Invaders+1.163
angs+1.153
 Kund+1.143
Neg logit contributions
estone-1.378
PB-1.184
 Flavoring-1.178
+.-1.171
adem-1.170
Tokenper
Token ID525
Feature activation+3.48e-01

Pos logit contributions
 Invaders+0.565
duction+0.562
bugs+0.560
angs+0.549
 Kund+0.548
Neg logit contributions
estone-0.627
PB-0.538
font-0.533
adem-0.531
+.-0.529
Tokenimages
Token ID17566
Feature activation-4.69e-01

Pos logit contributions
bugs+0.800
duction+0.799
 Invaders+0.787
angs+0.774
 Kund+0.767
Neg logit contributions
estone-0.995
PB-0.862
 Flavoring-0.854
adem-0.853
+.-0.848
Token(
Token ID7
Feature activation-4.70e-01

Pos logit contributions
estone+3.686
font+3.107
+.+3.094
PB+3.078
adem+3.043
Neg logit contributions
 Invaders-4.855
bugs-4.831
 Kund-4.817
duction-4.794
angs-4.730
Tokenargs
Token ID22046
Feature activation-1.22e+00

Pos logit contributions
estone+5.092
font+4.585
PB+4.537
+.+4.446
adem+4.440
Neg logit contributions
duction-3.503
 Invaders-3.496
bugs-3.437
 Kund-3.404
angs-3.366
Token["
Token ID14692
Feature activation-1.80e-01

Pos logit contributions
estone+7.429
+.+6.389
font+5.959
:{+5.694
PB+5.590
Neg logit contributions
bugs-13.103
 Invaders-12.983
 Kund-12.837
duction-12.727
Thunder-12.640
Tokenimages
Token ID17566
Feature activation+3.85e-01

Pos logit contributions
estone+1.877
PB+1.649
font+1.640
adem+1.621
+.+1.620
Neg logit contributions
duction-1.476
 Invaders-1.473
bugs-1.469
 Kund-1.434
angs-1.428
Token"]
Token ID8973
Feature activation-1.79e+00

Pos logit contributions
duction+2.299
bugs+2.282
 Invaders+2.163
angs+2.163
 Kund+2.131
Neg logit contributions
estone-4.828
 Flavoring-4.301
adem-4.255
PB-4.244
+.-4.207
Token):
Token ID2599
Feature activation-7.23e-01

Pos logit contributions
estone+8.538
+.+7.617
:{+6.839
font+6.725
PB+6.457
Neg logit contributions
bugs-18.432
 Kund-18.378
duction-18.281
 Invaders-18.176
angs-17.961
Token #
Token ID1303
Feature activation-5.60e-01

Pos logit contributions
estone+6.243
font+5.507
 activ+5.486
+.+5.482
PB+5.365
Neg logit contributions
bugs-6.615
duction-6.556
angs-6.385
igers-6.369
Thunder-6.303
Token load
Token ID3440
Feature activation+1.69e-01

Pos logit contributions
estone+5.248
+.+4.565
font+4.538
PB+4.489
 activ+4.459
Neg logit contributions
bugs-4.956
duction-4.931
igers-4.769
angs-4.749
 Invaders-4.745
Token the
Token ID262
Feature activation+9.20e-02

Pos logit contributions
duction+1.299
bugs+1.297
 Invaders+1.294
 Kund+1.263
angs+1.260
Neg logit contributions
estone-1.847
PB-1.612
adem-1.600
 Flavoring-1.591
+.-1.591
Token image
Token ID2939
Feature activation+1.76e-01

Pos logit contributions
duction+0.705
bugs+0.704
 Invaders+0.699
angs+0.682
 Kund+0.680
Neg logit contributions
estone-1.014
PB-0.887
adem-0.879
+.-0.875
font-0.875
Token
Token ID198
Feature activation-5.69e-01

Pos logit contributions
estone+1.502
PB+1.278
font+1.276
+.+1.269
adem+1.218
Neg logit contributions
duction-1.614
 Invaders-1.599
bugs-1.575
angs-1.562
igers-1.551
TokenSanta
Token ID42694
Feature activation-5.06e-01

Pos logit contributions
estone+5.387
PB+4.741
font+4.696
Stra+4.630
+.+4.570
Neg logit contributions
 Invaders-5.083
duction-4.961
 Kund-4.942
bugs-4.932
angs-4.845
Token Clara
Token ID27443
Feature activation-3.70e-01

Pos logit contributions
estone+3.738
font+2.933
PB+2.925
+.+2.879
adem+2.836
Neg logit contributions
bugs-5.653
duction-5.552
angs-5.506
 Invaders-5.448
igers-5.408
Token County
Token ID3418
Feature activation-2.91e-02

Pos logit contributions
estone+3.417
PB+2.872
+.+2.847
font+2.842
adem+2.834
Neg logit contributions
bugs-3.487
duction-3.479
 Invaders-3.402
angs-3.380
 Kund-3.356
Token v
Token ID410
Feature activation-7.51e-01

Pos logit contributions
estone+0.268
PB+0.227
adem+0.224
+.+0.224
font+0.224
Neg logit contributions
duction-0.276
bugs-0.276
 Invaders-0.273
angs-0.268
 Kund-0.267
Token.
Token ID13
Feature activation-1.62e+00

Pos logit contributions
estone+5.151
+.+4.508
font+4.383
PB+4.222
Stra+4.178
Neg logit contributions
duction-8.336
bugs-8.009
angs-7.994
igers-7.818
 Invaders-7.694
Token Southern
Token ID8050
Feature activation-5.18e-01

Pos logit contributions
estone+12.153
font+10.538
Stra+10.287
 Flavoring+10.098
PB+10.025
Neg logit contributions
bugs-13.226
duction-13.051
angs-12.863
igers-12.543
Thunder-12.044
Token Pacific
Token ID8211
Feature activation-6.95e-01

Pos logit contributions
estone+4.410
PB+3.739
font+3.637
+.+3.623
 Flavoring+3.613
Neg logit contributions
bugs-5.092
duction-5.076
angs-5.036
igers-5.033
 Invaders-4.919
Token Railroad
Token ID36289
Feature activation-3.23e-01

Pos logit contributions
estone+4.808
+.+3.719
PB+3.664
font+3.612
 Flavoring+3.606
Neg logit contributions
bugs-7.978
duction-7.894
angs-7.773
 Kund-7.770
 Invaders-7.697
Token Company
Token ID5834
Feature activation-6.50e-01

Pos logit contributions
estone+2.637
PB+2.157
+.+2.138
font+2.135
adem+2.124
Neg logit contributions
duction-3.392
bugs-3.391
 Invaders-3.345
 Kund-3.314
angs-3.312
Token
Token ID198
Feature activation+2.32e-02

Pos logit contributions
estone+5.583
PB+4.684
font+4.671
adem+4.650
+.+4.582
Neg logit contributions
duction-6.324
bugs-6.217
 Invaders-6.041
 Kund-6.030
angs-6.020
Token;
Token ID26
Feature activation-3.44e-01

Pos logit contributions
estone+3.033
font+2.596
PB+2.586
+.+2.581
adem+2.561
Neg logit contributions
duction-2.981
bugs-2.954
 Invaders-2.939
angs-2.885
 Kund-2.856
Token where
Token ID810
Feature activation-3.25e-01

Pos logit contributions
estone+3.254
font+2.806
PB+2.803
+.+2.798
adem+2.759
Neg logit contributions
duction-3.080
bugs-3.055
 Invaders-2.998
angs-2.992
 Kund-2.910
Token do
Token ID466
Feature activation+2.57e-01

Pos logit contributions
estone+2.988
PB+2.565
font+2.556
adem+2.548
+.+2.522
Neg logit contributions
duction-3.003
bugs-2.984
 Invaders-2.946
angs-2.904
 Kund-2.864
Token we
Token ID356
Feature activation-4.84e-01

Pos logit contributions
bugs+2.161
 Invaders+2.148
duction+2.140
 Kund+2.117
angs+2.087
Neg logit contributions
estone-2.630
PB-2.271
+.-2.242
adem-2.242
 Flavoring-2.241
Token draw
Token ID3197
Feature activation-1.18e+00

Pos logit contributions
estone+4.393
PB+3.697
adem+3.634
+.+3.623
font+3.580
Neg logit contributions
duction-4.629
bugs-4.529
 Invaders-4.477
igers-4.375
 Kund-4.332
Token the
Token ID262
Feature activation-1.57e+00

Pos logit contributions
estone+9.257
font+7.738
PB+7.506
+.+7.428
adem+7.420
Neg logit contributions
duction-10.950
igers-10.722
 Invaders-10.623
Hunt-10.529
angs-10.491
Token line
Token ID1627
Feature activation-7.13e-01

Pos logit contributions
estone+9.877
font+7.807
 activ+7.700
+.+7.686
Stra+7.434
Neg logit contributions
duction-15.581
igers-15.044
Hunt-15.025
bugs-14.884
Thunder-14.666
Token?
Token ID30
Feature activation-4.54e-02

Pos logit contributions
estone+6.619
+.+5.523
font+5.522
adem+5.472
PB+5.401
Neg logit contributions
duction-6.434
bugs-6.250
 Invaders-6.192
igers-6.045
Thunder-6.044
Token So
Token ID1406
Feature activation+5.96e-03

Pos logit contributions
estone+0.448
PB+0.388
font+0.382
+.+0.382
adem+0.381
Neg logit contributions
duction-0.402
bugs-0.400
 Invaders-0.395
angs-0.390
 Kund-0.385
Token they
Token ID484
Feature activation-1.81e-01

Pos logit contributions
duction+0.053
bugs+0.052
 Invaders+0.052
angs+0.051
 Kund+0.051
Neg logit contributions
estone-0.059
PB-0.051
adem-0.050
font-0.050
+.-0.050
Token say
Token ID910
Feature activation+5.07e-02

Pos logit contributions
estone+1.647
PB+1.390
adem+1.374
+.+1.368
font+1.363
Neg logit contributions
duction-1.736
bugs-1.733
 Invaders-1.714
angs-1.680
 Kund-1.679
Token
Token ID198
Feature activation-2.38e-01

Pos logit contributions
estone+6.461
font+5.584
+.+5.498
PB+5.455
 activ+5.376
Neg logit contributions
bugs-6.958
duction-6.954
angs-6.812
 Invaders-6.710
igers-6.696
Token
Token ID198
Feature activation-7.97e-01

Pos logit contributions
estone+2.084
font+1.793
PB+1.781
+.+1.775
Stra+1.684
Neg logit contributions
 Invaders-2.347
duction-2.347
bugs-2.294
angs-2.285
igers-2.276
Tokenvoid
Token ID19382
Feature activation-8.63e-01

Pos logit contributions
estone+7.284
font+6.548
PB+6.445
+.+6.339
Stra+6.328
Neg logit contributions
 Invaders-7.137
 Kund-6.823
duction-6.775
angs-6.681
bugs-6.624
Token V
Token ID569
Feature activation-1.78e-01

Pos logit contributions
estone+7.505
 activ+6.509
font+6.472
+.+6.430
PB+6.358
Neg logit contributions
duction-7.825
bugs-7.740
angs-7.544
Thunder-7.442
igers-7.428
Tokenort
Token ID419
Feature activation-1.39e-01

Pos logit contributions
estone+1.421
PB+1.156
adem+1.153
font+1.149
+.+1.129
Neg logit contributions
 Invaders-1.949
bugs-1.929
duction-1.898
 Kund-1.881
angs-1.865
Tokenon
Token ID261
Feature activation-1.56e+00

Pos logit contributions
estone+1.538
PB+1.347
adem+1.334
font+1.330
+.+1.330
Neg logit contributions
duction-1.058
bugs-1.056
 Invaders-1.045
angs-1.022
 Kund-1.016
TokenSim
Token ID8890
Feature activation-1.01e+00

Pos logit contributions
estone+11.710
PB+10.777
Stra+10.771
+.+10.405
font+10.359
Neg logit contributions
bugs-12.804
 Invaders-12.563
 Kund-12.536
duction-12.527
igers-12.389
Token::
Token ID3712
Feature activation-1.15e+00

Pos logit contributions
estone+7.000
PB+6.154
+.+6.025
font+6.021
adem+5.908
Neg logit contributions
bugs-10.610
 Invaders-10.514
duction-10.290
 Kund-10.181
angs-10.138
TokenPop
Token ID16979
Feature activation-5.42e-01

Pos logit contributions
estone+9.563
PB+9.281
font+8.978
Stra+8.845
+.+8.604
Neg logit contributions
duction-9.638
 Invaders-9.479
bugs-9.383
 Kund-9.301
angs-9.251
Tokenulate
Token ID5039
Feature activation-4.59e-01

Pos logit contributions
estone+4.847
adem+4.157
font+4.044
+.+4.041
PB+3.960
Neg logit contributions
 Invaders-5.293
 Kund-5.129
bugs-5.052
angs-5.031
duction-4.950
TokenD
Token ID35
Feature activation-3.58e-01

Pos logit contributions
estone+6.023
PB+5.480
font+5.428
+.+5.409
adem+5.387
Neg logit contributions
bugs-2.434
 Invaders-2.390
duction-2.389
angs-2.291
igers-2.255
Token be
Token ID307
Feature activation+1.97e-01

Pos logit contributions
bugs+2.219
duction+2.218
 Invaders+2.198
angs+2.151
 Kund+2.147
Neg logit contributions
estone-2.745
PB-2.378
adem-2.350
font-2.345
+.-2.343
Token equally
Token ID8603
Feature activation-6.04e-01

Pos logit contributions
bugs+1.781
duction+1.776
 Invaders+1.774
angs+1.743
 Kund+1.731
Neg logit contributions
estone-1.897
PB-1.625
font-1.597
+.-1.585
 Flavoring-1.580
Token as
Token ID355
Feature activation-3.40e-01

Pos logit contributions
estone+4.818
adem+4.220
+.+4.136
font+4.093
 activ+4.053
Neg logit contributions
duction-6.079
 Invaders-5.959
bugs-5.896
angs-5.827
igers-5.751
Token tight
Token ID5381
Feature activation-9.09e-01

Pos logit contributions
estone+3.108
adem+2.677
+.+2.624
font+2.621
PB+2.567
Neg logit contributions
duction-3.187
 Invaders-3.170
bugs-3.137
angs-3.086
igers-3.068
Token-
Token ID12
Feature activation-1.42e+00

Pos logit contributions
estone+6.783
font+5.740
adem+5.596
+.+5.506
PB+5.311
Neg logit contributions
 Invaders-9.220
duction-9.154
bugs-9.073
angs-9.009
 Kund-8.982
Tokenf
Token ID69
Feature activation-1.45e+00

Pos logit contributions
estone+6.134
font+5.803
adem+4.576
tan+4.467
stri+4.405
Neg logit contributions
 Invaders-17.374
 Kund-16.723
 Vaugh-16.408
 Vengeance-16.312
ION-16.126
Tokenisted
Token ID6347
Feature activation-2.03e-01

Pos logit contributions
estone+6.852
adem+6.302
oused+4.755
font+4.506
+.+4.269
Neg logit contributions
 Invaders-17.656
bugs-17.251
 Kund-17.067
�-17.049
duction-16.907
Token as
Token ID355
Feature activation+1.66e-01

Pos logit contributions
estone+2.074
PB+1.791
adem+1.779
font+1.777
+.+1.776
Neg logit contributions
duction-1.715
bugs-1.712
 Invaders-1.701
angs-1.665
 Kund-1.663
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
duction+1.337
bugs+1.334
 Invaders+1.323
angs+1.294
 Kund+1.287
Neg logit contributions
estone-1.760
PB-1.531
adem-1.519
font-1.514
+.-1.512
Token Conservatives
Token ID17897
Feature activation-2.81e-01

Pos logit contributions
duction+0.134
bugs+0.133
 Invaders+0.131
 Kund+0.127
angs+0.127
Neg logit contributions
estone-0.267
PB-0.238
adem-0.237
+.-0.237
font-0.236
Token when
Token ID618
Feature activation-6.36e-02

Pos logit contributions
estone+2.368
PB+1.975
adem+1.957
+.+1.953
font+1.948
Neg logit contributions
duction-2.881
bugs-2.875
 Invaders-2.866
angs-2.818
 Kund-2.805
Token to
Token ID284
Feature activation+2.66e-01

Pos logit contributions
estone+3.826
+.+3.212
PB+3.149
font+3.136
 Flavoring+3.067
Neg logit contributions
duction-5.200
angs-5.199
bugs-5.188
 Invaders-5.123
igers-5.012
Token be
Token ID307
Feature activation+1.97e-01

Pos logit contributions
bugs+2.219
duction+2.218
 Invaders+2.198
angs+2.151
 Kund+2.147
Neg logit contributions
estone-2.745
PB-2.378
adem-2.350
font-2.345
+.-2.343
Token equally
Token ID8603
Feature activation-6.04e-01

Pos logit contributions
bugs+1.781
duction+1.776
 Invaders+1.774
angs+1.743
 Kund+1.731
Neg logit contributions
estone-1.897
PB-1.625
font-1.597
+.-1.585
 Flavoring-1.580
Token as
Token ID355
Feature activation-3.40e-01

Pos logit contributions
estone+4.818
adem+4.220
+.+4.136
font+4.093
 activ+4.053
Neg logit contributions
duction-6.079
 Invaders-5.959
bugs-5.896
angs-5.827
igers-5.751
Token tight
Token ID5381
Feature activation-9.09e-01

Pos logit contributions
estone+3.108
adem+2.677
+.+2.624
font+2.621
PB+2.567
Neg logit contributions
duction-3.187
 Invaders-3.170
bugs-3.137
angs-3.086
igers-3.068
Token-
Token ID12
Feature activation-1.42e+00

Pos logit contributions
estone+6.783
font+5.740
adem+5.596
+.+5.506
PB+5.311
Neg logit contributions
 Invaders-9.220
duction-9.154
bugs-9.073
angs-9.009
 Kund-8.982
Tokenf
Token ID69
Feature activation-1.45e+00

Pos logit contributions
estone+6.134
font+5.803
adem+4.576
tan+4.467
stri+4.405
Neg logit contributions
 Invaders-17.374
 Kund-16.723
 Vaugh-16.408
 Vengeance-16.312
ION-16.126
Tokenisted
Token ID6347
Feature activation-2.03e-01

Pos logit contributions
estone+6.852
adem+6.302
oused+4.755
font+4.506
+.+4.269
Neg logit contributions
 Invaders-17.656
bugs-17.251
 Kund-17.067
�-17.049
duction-16.907
Token as
Token ID355
Feature activation+1.66e-01

Pos logit contributions
estone+2.074
PB+1.791
adem+1.779
font+1.777
+.+1.776
Neg logit contributions
duction-1.715
bugs-1.712
 Invaders-1.701
angs-1.665
 Kund-1.663
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
duction+1.337
bugs+1.334
 Invaders+1.323
angs+1.294
 Kund+1.287
Neg logit contributions
estone-1.760
PB-1.531
adem-1.519
font-1.514
+.-1.512
Token Conservatives
Token ID17897
Feature activation-2.81e-01

Pos logit contributions
duction+0.134
bugs+0.133
 Invaders+0.131
 Kund+0.127
angs+0.127
Neg logit contributions
estone-0.267
PB-0.238
adem-0.237
+.-0.237
font-0.236
TokenFont
Token ID23252
Feature activation+4.73e-02

Pos logit contributions
estone+2.686
font+2.323
PB+2.112
adem+2.022
+.+1.900
Neg logit contributions
 Invaders-7.910
duction-7.822
 Kund-7.818
bugs-7.786
angs-7.702
TokenName
Token ID5376
Feature activation-6.62e-01

Pos logit contributions
bugs+0.372
duction+0.371
 Invaders+0.366
angs+0.359
 Kund+0.356
Neg logit contributions
estone-0.510
PB-0.441
 Flavoring-0.439
adem-0.439
+.-0.436
Token,
Token ID11
Feature activation-7.00e-01

Pos logit contributions
estone+5.011
font+4.382
PB+4.339
+.+4.238
Stra+4.041
Neg logit contributions
duction-7.033
 Invaders-6.926
igers-6.841
bugs-6.801
angs-6.765
Token$
Token ID3
Feature activation-3.01e-01

Pos logit contributions
estone+4.564
font+4.269
PB+4.067
Stra+3.759
+.+3.708
Neg logit contributions
 Invaders-8.072
duction-7.913
angs-7.835
bugs-7.830
 Kund-7.728
TokenFS
Token ID10652
Feature activation-4.33e-01

Pos logit contributions
estone+3.010
font+2.646
PB+2.643
adem+2.592
+.+2.568
Neg logit contributions
 Invaders-2.605
duction-2.588
bugs-2.584
 Kund-2.524
angs-2.504
Token2
Token ID17
Feature activation-1.42e+00

Pos logit contributions
estone+3.405
PB+3.070
font+3.018
+.+2.954
Stra+2.843
Neg logit contributions
 Invaders-4.613
duction-4.586
bugs-4.484
igers-4.438
angs-4.436
Token,[
Token ID17414
Feature activation-3.41e-01

Pos logit contributions
estone+5.310
PB+4.305
+.+3.808
font+3.697
:{+3.256
Neg logit contributions
 Invaders-18.423
duction-17.959
igers-17.633
bugs-17.614
angs-17.520
TokenSystem
Token ID11964
Feature activation+4.85e-01

Pos logit contributions
estone+2.228
font+1.962
PB+1.893
+.+1.788
adem+1.782
Neg logit contributions
 Invaders-4.088
duction-4.033
bugs-3.970
angs-3.967
 Kund-3.965
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
bugs+3.846
duction+3.739
 Invaders+3.676
 Kund+3.650
cz+3.645
Neg logit contributions
estone-5.109
ntil-4.570
adem-4.479
 Flavoring-4.438
 activ-4.429
TokenDraw
Token ID25302
Feature activation-2.32e-01

Pos logit contributions
duction+1.049
bugs+1.047
 Invaders+1.039
angs+1.016
 Kund+1.012
Neg logit contributions
estone-1.368
PB-1.192
font-1.179
adem-1.178
+.-1.175
Tokening
Token ID278
Feature activation-3.04e-01

Pos logit contributions
estone+1.679
font+1.373
PB+1.325
adem+1.308
+.+1.303
Neg logit contributions
 Invaders-2.689
duction-2.646
bugs-2.629
angs-2.594
 Kund-2.592
Token fork
Token ID15563
Feature activation-4.31e-01

Pos logit contributions
bugs+2.214
duction+2.156
 Kund+2.038
angs+2.037
 Invaders+1.994
Neg logit contributions
estone-10.021
adem-9.097
font-9.056
PB-9.053
 Flavoring-8.986
Token-
Token ID12
Feature activation+2.75e-01

Pos logit contributions
estone+3.435
font+2.913
+.+2.855
PB+2.848
adem+2.798
Neg logit contributions
 Invaders-4.559
duction-4.491
angs-4.416
bugs-4.378
igers-4.374
Tokent
Token ID83
Feature activation+1.16e-01

Pos logit contributions
bugs+2.542
duction+2.535
 Invaders+2.470
angs+2.461
 Kund+2.435
Neg logit contributions
estone-2.587
PB-2.231
 Flavoring-2.211
+.-2.193
adem-2.183
Tokenender
Token ID2194
Feature activation-2.90e-01

Pos logit contributions
duction+0.763
bugs+0.762
 Invaders+0.762
 Kund+0.731
angs+0.726
Neg logit contributions
estone-1.410
adem-1.241
PB-1.238
font-1.233
+.-1.229
Token.
Token ID13
Feature activation+4.73e-01

Pos logit contributions
estone+2.409
+.+2.073
font+2.046
PB+2.020
 Flavoring+1.960
Neg logit contributions
duction-2.961
 Invaders-2.956
bugs-2.912
angs-2.889
igers-2.850
Token Chop
Token ID40159
Feature activation-1.42e+00

Pos logit contributions
bugs+2.091
 Invaders+2.085
duction+2.059
 Kund+2.025
cz+1.951
Neg logit contributions
estone-6.640
adem-6.000
PB-5.903
font-5.877
+.-5.861
Token fl
Token ID781
Feature activation+1.81e-01

Pos logit contributions
estone+3.159
 flavored+1.948
 activ+1.819
 Flavoring+1.818
 occ+1.580
Neg logit contributions
 Invaders-20.276
igers-20.082
Thunder-19.736
bugs-19.585
angs-19.523
Tokenore
Token ID382
Feature activation-1.18e-01

Pos logit contributions
duction+1.526
bugs+1.525
 Invaders+1.511
angs+1.480
 Kund+1.475
Neg logit contributions
estone-1.854
PB-1.605
adem-1.588
+.-1.583
font-1.582
Tokents
Token ID912
Feature activation-2.14e-01

Pos logit contributions
estone+1.336
font+1.158
PB+1.150
adem+1.145
+.+1.131
Neg logit contributions
 Invaders-0.896
duction-0.876
bugs-0.863
 Kund-0.856
angs-0.836
Token into
Token ID656
Feature activation-3.55e-01

Pos logit contributions
estone+1.991
font+1.683
+.+1.668
PB+1.661
 Flavoring+1.629
Neg logit contributions
 Invaders-2.019
bugs-2.018
duction-2.009
 Kund-1.951
angs-1.945
Token small
Token ID1402
Feature activation+3.48e-01

Pos logit contributions
estone+3.946
PB+3.502
+.+3.410
font+3.385
 activ+3.370
Neg logit contributions
 Invaders-2.714
duction-2.685
bugs-2.643
igers-2.592
angs-2.574
TokenThe
Token ID464
Feature activation-3.58e-01

Pos logit contributions
estone+2.115
PB+1.874
+.+1.829
font+1.820
adem+1.806
Neg logit contributions
 Invaders-1.985
duction-1.962
bugs-1.932
 Kund-1.908
angs-1.900
Token rest
Token ID1334
Feature activation-1.05e-02

Pos logit contributions
estone+3.269
PB+2.802
adem+2.781
+.+2.774
font+2.748
Neg logit contributions
duction-3.364
bugs-3.322
 Invaders-3.273
angs-3.257
igers-3.191
Token,
Token ID11
Feature activation-3.02e-01

Pos logit contributions
estone+0.100
PB+0.086
adem+0.085
+.+0.084
font+0.084
Neg logit contributions
duction-0.096
bugs-0.095
 Invaders-0.095
angs-0.093
 Kund-0.093
Token nearly
Token ID3016
Feature activation-1.44e-01

Pos logit contributions
estone+2.699
+.+2.328
PB+2.289
adem+2.283
font+2.256
Neg logit contributions
duction-2.873
bugs-2.863
 Invaders-2.840
angs-2.794
 Kund-2.758
Token two
Token ID734
Feature activation-9.92e-01

Pos logit contributions
estone+1.303
adem+1.112
PB+1.106
+.+1.105
font+1.089
Neg logit contributions
bugs-1.391
duction-1.372
 Invaders-1.359
angs-1.340
igers-1.323
Token-
Token ID12
Feature activation-1.40e+00

Pos logit contributions
estone+7.066
PB+6.141
+.+5.957
font+5.845
adem+5.755
Neg logit contributions
 Invaders-10.110
duction-10.050
igers-9.949
bugs-9.928
cz-9.787
Tokenthirds
Token ID17936
Feature activation+8.48e-02

Pos logit contributions
estone+5.843
font+5.100
PB+4.868
adem+4.745
+.+4.568
Neg logit contributions
 Invaders-17.360
 Kund-16.401
duction-16.396
 Jagu-15.939
AMI-15.932
Token of
Token ID286
Feature activation-4.04e-01

Pos logit contributions
bugs+0.723
duction+0.722
 Invaders+0.714
angs+0.702
 Kund+0.701
Neg logit contributions
estone-0.860
PB-0.744
adem-0.737
font-0.736
 Flavoring-0.733
Token respondents
Token ID14502
Feature activation-1.01e-01

Pos logit contributions
estone+3.920
PB+3.383
adem+3.366
+.+3.334
font+3.312
Neg logit contributions
bugs-3.530
duction-3.496
 Invaders-3.479
angs-3.422
igers-3.365
Token,
Token ID11
Feature activation-3.70e-01

Pos logit contributions
estone+0.980
PB+0.836
adem+0.829
+.+0.827
font+0.824
Neg logit contributions
duction-0.916
bugs-0.915
 Invaders-0.912
angs-0.891
 Kund-0.887
Token said
Token ID531
Feature activation-2.23e-01

Pos logit contributions
estone+3.296
+.+2.813
PB+2.785
adem+2.778
font+2.719
Neg logit contributions
duction-3.518
 Invaders-3.517
bugs-3.489
angs-3.412
igers-3.378
Token of
Token ID286
Feature activation-6.07e-01

Pos logit contributions
estone+3.452
PB+2.906
+.+2.887
font+2.874
adem+2.861
Neg logit contributions
duction-3.963
 Invaders-3.962
bugs-3.950
 Kund-3.870
angs-3.866
Token possibilities
Token ID12779
Feature activation-3.96e-01

Pos logit contributions
estone+4.884
+.+4.164
 activ+4.143
PB+4.143
 Flavoring+4.111
Neg logit contributions
duction-5.990
igers-5.885
angs-5.829
 Invaders-5.818
bugs-5.809
Token I
Token ID314
Feature activation-1.59e-01

Pos logit contributions
estone+3.520
+.+3.025
PB+2.983
font+2.982
adem+2.925
Neg logit contributions
duction-3.774
 Invaders-3.739
bugs-3.739
angs-3.662
igers-3.628
Token had
Token ID550
Feature activation-7.86e-01

Pos logit contributions
estone+1.483
PB+1.271
+.+1.257
adem+1.251
font+1.250
Neg logit contributions
duction-1.473
bugs-1.470
 Invaders-1.463
 Kund-1.437
angs-1.434
Token never
Token ID1239
Feature activation-1.19e+00

Pos logit contributions
estone+6.452
+.+5.607
PB+5.474
font+5.459
adem+5.335
Neg logit contributions
 Invaders-7.401
duction-7.324
angs-7.199
bugs-7.199
igers-7.151
Token really
Token ID1107
Feature activation-1.34e+00

Pos logit contributions
estone+8.238
+.+6.706
PB+6.569
 activ+6.444
font+6.413
Neg logit contributions
duction-11.633
 Invaders-11.602
bugs-11.477
igers-11.448
Hunt-11.421
Token considered
Token ID3177
Feature activation-9.34e-03

Pos logit contributions
estone+8.445
+.+6.551
PB+6.523
 activ+6.397
 occ+6.369
Neg logit contributions
duction-13.605
 Invaders-13.499
igers-13.479
bugs-13.294
Hunt-13.159
Token before
Token ID878
Feature activation+1.15e-01

Pos logit contributions
estone+0.089
PB+0.077
+.+0.076
adem+0.076
font+0.075
Neg logit contributions
bugs-0.085
duction-0.085
 Invaders-0.084
angs-0.083
 Kund-0.082
Token.
Token ID13
Feature activation-1.18e-02

Pos logit contributions
duction+1.016
bugs+1.015
 Invaders+1.006
angs+0.984
 Kund+0.983
Neg logit contributions
estone-1.141
PB-0.983
adem-0.973
font-0.965
 Flavoring-0.962
Token In
Token ID554
Feature activation+7.99e-03

Pos logit contributions
estone+0.117
PB+0.101
+.+0.099
font+0.099
 Flavoring+0.099
Neg logit contributions
duction-0.105
bugs-0.104
 Invaders-0.102
angs-0.102
 Kund-0.100
Token fact
Token ID1109
Feature activation+1.69e-01

Pos logit contributions
duction+0.068
bugs+0.068
 Invaders+0.067
angs+0.066
 Kund+0.066
Neg logit contributions
estone-0.081
PB-0.070
adem-0.070
font-0.070
+.-0.069
Token p
Token ID279
Feature activation+4.73e-01

Pos logit contributions
estone+1.164
PB+0.984
font+0.972
+.+0.969
adem+0.968
Neg logit contributions
bugs-1.101
duction-1.096
 Invaders-1.088
angs-1.072
 Kund-1.053
Tokenored
Token ID1850
Feature activation-3.34e-01

Pos logit contributions
duction+4.175
angs+4.170
bugs+4.074
cz+3.905
igers+3.903
Neg logit contributions
estone-4.508
 Flavoring-4.025
PB-3.975
+.-3.832
adem-3.819
Token over
Token ID625
Feature activation-7.40e-02

Pos logit contributions
estone+2.807
adem+2.305
font+2.303
+.+2.302
PB+2.300
Neg logit contributions
 Invaders-3.441
bugs-3.426
duction-3.422
 Kund-3.357
angs-3.350
Token by
Token ID416
Feature activation-2.03e-01

Pos logit contributions
estone+0.713
PB+0.609
adem+0.600
font+0.599
+.+0.599
Neg logit contributions
duction-0.674
bugs-0.673
 Invaders-0.668
angs-0.655
 Kund-0.650
Token analysts
Token ID13440
Feature activation-5.65e-01

Pos logit contributions
estone+1.967
PB+1.688
adem+1.674
font+1.654
+.+1.639
Neg logit contributions
duction-1.835
bugs-1.825
 Invaders-1.804
 Kund-1.771
angs-1.768
Token looking
Token ID2045
Feature activation-1.34e+00

Pos logit contributions
estone+4.762
font+3.986
+.+3.965
PB+3.904
adem+3.865
Neg logit contributions
duction-5.635
 Invaders-5.553
bugs-5.522
Thunder-5.419
angs-5.410
Token for
Token ID329
Feature activation-3.51e-01

Pos logit contributions
estone+8.658
font+6.456
adem+6.242
 pharm+6.233
+.+6.213
Neg logit contributions
bugs-14.491
 Invaders-14.204
angs-13.834
 Kund-13.828
icks-13.759
Token clues
Token ID20195
Feature activation-1.06e-01

Pos logit contributions
estone+3.269
PB+2.750
adem+2.733
font+2.721
+.+2.703
Neg logit contributions
duction-3.249
bugs-3.224
 Invaders-3.203
angs-3.182
 Kund-3.117
Token on
Token ID319
Feature activation-4.13e-01

Pos logit contributions
estone+1.038
PB+0.880
font+0.876
+.+0.875
adem+0.875
Neg logit contributions
duction-0.950
bugs-0.948
 Invaders-0.942
angs-0.921
 Kund-0.914
Token when
Token ID618
Feature activation-2.70e-01

Pos logit contributions
estone+3.805
 Flavoring+3.183
PB+3.182
adem+3.154
 activ+3.148
Neg logit contributions
bugs-3.826
angs-3.782
 Invaders-3.779
duction-3.778
Thunder-3.688
Token rates
Token ID3965
Feature activation-7.10e-01

Pos logit contributions
estone+2.646
PB+2.253
+.+2.234
font+2.224
adem+2.221
Neg logit contributions
bugs-2.391
duction-2.381
 Invaders-2.376
angs-2.328
 Kund-2.301
Token
Token ID198
Feature activation-4.51e-01

Pos logit contributions
duction+0.151
 Invaders+0.150
bugs+0.149
angs+0.146
 Kund+0.145
Neg logit contributions
estone-0.161
PB-0.138
font-0.137
+.-0.137
adem-0.135
TokenThis
Token ID1212
Feature activation-5.26e-01

Pos logit contributions
estone+4.089
PB+3.552
font+3.537
+.+3.508
Stra+3.478
Neg logit contributions
 Invaders-4.295
duction-4.200
bugs-4.140
 Kund-4.138
angs-4.052
Token will
Token ID481
Feature activation-6.83e-01

Pos logit contributions
estone+4.819
 activ+4.137
+.+4.055
font+4.029
adem+4.001
Neg logit contributions
bugs-4.883
duction-4.832
 Invaders-4.763
angs-4.732
igers-4.662
Token force
Token ID2700
Feature activation-1.00e+00

Pos logit contributions
estone+6.166
+.+5.313
 activ+5.264
font+5.143
PB+5.104
Neg logit contributions
bugs-6.323
duction-6.308
 Invaders-6.010
igers-5.950
Thunder-5.881
Token Unity
Token ID18714
Feature activation-2.22e-01

Pos logit contributions
estone+8.486
 activ+7.336
+.+7.214
font+7.162
Stra+7.083
Neg logit contributions
duction-8.976
bugs-8.961
igers-8.774
angs-8.721
Hunt-8.580
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
estone+2.138
PB+1.832
font+1.813
+.+1.812
adem+1.807
Neg logit contributions
duction-2.010
bugs-2.001
 Invaders-1.991
angs-1.956
 Kund-1.952
Token invoke
Token ID26342
Feature activation-9.03e-01

Pos logit contributions
estone+10.168
+.+8.992
 activ+8.743
 occ+8.617
font+8.466
Neg logit contributions
bugs-11.974
duction-11.660
igers-11.457
cz-11.321
Hunt-11.117
Token a
Token ID257
Feature activation-5.49e-01

Pos logit contributions
estone+7.914
 activ+6.919
font+6.773
+.+6.743
adem+6.613
Neg logit contributions
bugs-8.044
duction-7.956
igers-7.914
angs-7.728
cz-7.681
Token function
Token ID2163
Feature activation-9.50e-01

Pos logit contributions
estone+5.237
font+4.482
+.+4.479
PB+4.449
 activ+4.436
Neg logit contributions
bugs-4.855
duction-4.769
angs-4.691
igers-4.689
 Invaders-4.642
Token called
Token ID1444
Feature activation-1.26e+00

Pos logit contributions
estone+7.809
 activ+6.679
+.+6.542
font+6.476
adem+6.334
Neg logit contributions
bugs-8.902
igers-8.789
duction-8.640
angs-8.633
 Invaders-8.556
Token vert
Token ID9421
Feature activation-4.39e-01

Pos logit contributions
estone+10.794
 activ+9.614
font+9.363
+.+9.317
 occ+9.117
Neg logit contributions
bugs-10.380
igers-10.376
duction-10.210
angs-9.962
Hunt-9.956
Token they
Token ID484
Feature activation-4.07e-01

Pos logit contributions
estone+2.297
PB+1.979
font+1.977
+.+1.964
adem+1.956
Neg logit contributions
duction-2.077
bugs-2.072
 Invaders-2.058
angs-2.010
 Kund-2.005
Token wrote
Token ID2630
Feature activation-3.70e-01

Pos logit contributions
estone+3.472
PB+2.851
adem+2.816
+.+2.803
font+2.796
Neg logit contributions
duction-4.113
 Invaders-4.098
bugs-4.089
angs-3.987
 Kund-3.983
Token.
Token ID13
Feature activation-1.75e-01

Pos logit contributions
estone+3.409
+.+2.869
font+2.853
PB+2.844
adem+2.826
Neg logit contributions
duction-3.516
bugs-3.482
 Invaders-3.461
angs-3.420
 Kund-3.358
Token
Token ID198
Feature activation-5.69e-02

Pos logit contributions
estone+1.744
PB+1.502
adem+1.487
font+1.485
+.+1.483
Neg logit contributions
duction-1.517
bugs-1.516
 Invaders-1.503
angs-1.474
 Kund-1.467
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
estone+0.537
PB+0.460
font+0.457
+.+0.454
adem+0.443
Neg logit contributions
duction-0.533
 Invaders-0.530
bugs-0.524
angs-0.517
igers-0.510
TokenW
Token ID54
Feature activation-1.32e+00

Pos logit contributions
estone+3.769
PB+3.353
font+3.309
+.+3.253
adem+3.241
Neg logit contributions
 Invaders-3.617
duction-3.573
bugs-3.521
 Kund-3.490
angs-3.477
Tokenarm
Token ID1670
Feature activation-2.21e-01

Pos logit contributions
estone+8.211
adem+7.264
font+6.472
+.+6.247
PB+6.099
Neg logit contributions
 Invaders-15.091
 Jagu-14.890
 Kund-14.526
bugs-13.968
duction-13.885
Tokenb
Token ID65
Feature activation-1.47e-01

Pos logit contributions
estone+1.939
PB+1.615
font+1.610
adem+1.606
+.+1.588
Neg logit contributions
duction-2.220
 Invaders-2.202
bugs-2.178
angs-2.154
 Kund-2.146
Tokenier
Token ID959
Feature activation-5.45e-01

Pos logit contributions
estone+0.773
adem+0.558
font+0.547
+.+0.538
PB+0.528
Neg logit contributions
 Invaders-2.004
duction-1.988
bugs-1.982
 Kund-1.956
angs-1.945
Token was
Token ID373
Feature activation-2.45e-01

Pos logit contributions
estone+4.671
adem+3.918
font+3.847
PB+3.823
+.+3.807
Neg logit contributions
duction-5.310
bugs-5.175
 Invaders-5.173
angs-5.101
 Kund-5.044
Token convicted
Token ID9118
Feature activation-6.79e-01

Pos logit contributions
estone+2.357
adem+2.029
PB+2.022
font+1.996
+.+1.984
Neg logit contributions
bugs-2.184
duction-2.162
 Invaders-2.158
angs-2.138
 Kund-2.084
Token,
Token ID11
Feature activation-6.71e-01

Pos logit contributions
estone+1.048
PB+0.919
+.+0.907
font+0.902
adem+0.897
Neg logit contributions
duction-0.807
bugs-0.806
 Invaders-0.795
angs-0.780
 Kund-0.774
Token (
Token ID357
Feature activation-5.88e-01

Pos logit contributions
estone+6.093
font+5.547
PB+5.398
+.+5.312
 activ+5.257
Neg logit contributions
duction-5.868
bugs-5.814
 Invaders-5.712
igers-5.667
angs-5.618
Token13
Token ID1485
Feature activation-5.81e-01

Pos logit contributions
estone+5.956
font+5.437
PB+5.339
+.+5.213
adem+5.170
Neg logit contributions
duction-4.695
 Invaders-4.663
bugs-4.613
 Kund-4.555
angs-4.514
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
estone+5.260
+.+4.610
PB+4.588
font+4.508
adem+4.391
Neg logit contributions
duction-5.343
bugs-5.270
 Invaders-5.212
angs-5.198
 Kund-5.135
Token 5
Token ID642
Feature activation-2.35e-01

Pos logit contributions
estone+0.186
PB+0.161
font+0.159
adem+0.159
+.+0.159
Neg logit contributions
duction-0.167
bugs-0.166
 Invaders-0.165
angs-0.161
 Kund-0.161
Token))
Token ID4008
Feature activation-1.29e+00

Pos logit contributions
estone+1.882
PB+1.570
font+1.547
+.+1.543
adem+1.535
Neg logit contributions
duction-2.513
bugs-2.505
 Invaders-2.491
 Kund-2.447
angs-2.445
Token sq
Token ID19862
Feature activation-2.74e-01

Pos logit contributions
estone+10.319
font+9.565
+.+9.352
 activ+9.186
 pharm+8.983
Neg logit contributions
duction-10.777
bugs-10.691
igers-10.509
Hunt-10.491
Thunder-10.412
TokenK
Token ID42
Feature activation-8.72e-01

Pos logit contributions
estone+2.639
PB+2.281
font+2.258
adem+2.254
+.+2.226
Neg logit contributions
bugs-2.443
 Invaders-2.434
duction-2.429
 Kund-2.370
angs-2.356
Tokenernel
Token ID7948
Feature activation-7.40e-01

Pos logit contributions
estone+4.175
font+3.318
adem+3.230
PB+2.923
+.+2.855
Neg logit contributions
 Invaders-11.375
bugs-11.185
 Kund-11.047
duction-10.854
Thunder-10.695
Token =
Token ID796
Feature activation-1.03e+00

Pos logit contributions
estone+6.071
PB+5.292
font+5.256
+.+5.187
adem+5.088
Neg logit contributions
bugs-7.193
 Invaders-7.102
duction-7.073
 Kund-6.975
angs-6.919
Token c
Token ID269
Feature activation+9.74e-02

Pos logit contributions
estone+7.602
font+6.697
 activ+6.582
+.+6.545
PB+6.343
Neg logit contributions
bugs-10.170
igers-10.060
duction-10.018
Thunder-9.766
angs-9.751
Token :
Token ID1058
Feature activation-6.02e-01

Pos logit contributions
estone+4.398
font+3.768
PB+3.718
+.+3.671
 activ+3.644
Neg logit contributions
duction-5.267
bugs-5.199
 Invaders-5.114
angs-5.068
Thunder-4.997
Token #
Token ID1303
Feature activation-1.16e+00

Pos logit contributions
estone+4.910
font+4.192
PB+4.118
+.+4.087
adem+4.070
Neg logit contributions
duction-6.175
bugs-6.096
 Invaders-5.966
angs-5.894
 Kund-5.870
Token load
Token ID3440
Feature activation-1.17e-01

Pos logit contributions
estone+6.626
font+5.717
+.+5.571
 activ+5.466
PB+5.168
Neg logit contributions
duction-13.345
bugs-13.217
igers-12.939
 Invaders-12.892
cz-12.791
Token the
Token ID262
Feature activation-3.94e-02

Pos logit contributions
estone+1.165
font+0.991
PB+0.991
+.+0.983
 Flavoring+0.982
Neg logit contributions
duction-1.041
bugs-1.036
 Invaders-1.023
angs-1.016
igers-0.989
Token image
Token ID2939
Feature activation-4.43e-01

Pos logit contributions
estone+0.441
PB+0.385
+.+0.384
font+0.382
adem+0.382
Neg logit contributions
bugs-0.299
duction-0.298
 Invaders-0.292
angs-0.289
igers-0.281
Token,
Token ID11
Feature activation-1.29e+00

Pos logit contributions
estone+3.711
font+3.065
PB+3.024
+.+2.967
 Flavoring+2.862
Neg logit contributions
duction-4.657
bugs-4.554
 Invaders-4.511
igers-4.455
angs-4.452
Token resize
Token ID47558
Feature activation+6.16e-02

Pos logit contributions
estone+4.989
+.+3.932
 activ+3.668
font+3.410
adem+3.064
Neg logit contributions
 Invaders-16.785
igers-16.761
duction-16.672
bugs-16.454
Die-16.263
Token it
Token ID340
Feature activation-2.97e-01

Pos logit contributions
duction+0.577
bugs+0.574
 Invaders+0.569
angs+0.561
 Kund+0.553
Neg logit contributions
estone-0.580
PB-0.493
+.-0.490
font-0.487
adem-0.486
Token,
Token ID11
Feature activation-1.20e-01

Pos logit contributions
estone+2.544
font+2.119
PB+2.099
+.+2.073
adem+2.008
Neg logit contributions
duction-3.080
 Invaders-3.011
bugs-2.996
angs-2.951
igers-2.948
Token and
Token ID290
Feature activation-2.18e-01

Pos logit contributions
estone+0.970
font+0.802
+.+0.801
PB+0.796
adem+0.790
Neg logit contributions
duction-1.272
bugs-1.262
 Invaders-1.260
angs-1.238
 Kund-1.230
Token convert
Token ID10385
Feature activation+1.60e-01

Pos logit contributions
estone+1.959
+.+1.693
font+1.664
PB+1.649
adem+1.641
Neg logit contributions
bugs-2.089
duction-2.071
 Invaders-2.062
 Kund-2.030
angs-2.029
Token used
Token ID973
Feature activation+4.69e-02

Pos logit contributions
 Invaders+3.607
bugs+3.565
duction+3.551
 Kund+3.517
cz+3.458
Neg logit contributions
estone-5.858
 Flavoring-5.218
adem-5.151
PB-5.142
font-5.087
Token,
Token ID11
Feature activation+1.77e-01

Pos logit contributions
duction+0.419
bugs+0.419
 Invaders+0.416
angs+0.407
 Kund+0.406
Neg logit contributions
estone-0.458
PB-0.393
adem-0.389
+.-0.388
font-0.388
Token thus
Token ID4145
Feature activation-1.02e-01

Pos logit contributions
bugs+1.643
duction+1.640
 Invaders+1.630
angs+1.596
 Kund+1.593
Neg logit contributions
estone-1.667
PB-1.424
adem-1.408
 Flavoring-1.396
font-1.393
Token a
Token ID257
Feature activation-2.09e-01

Pos logit contributions
estone+0.986
PB+0.844
font+0.842
+.+0.838
adem+0.834
Neg logit contributions
duction-0.914
bugs-0.906
 Invaders-0.899
angs-0.883
 Kund-0.880
Token line
Token ID1627
Feature activation-2.60e-01

Pos logit contributions
estone+2.023
PB+1.747
+.+1.734
font+1.726
adem+1.722
Neg logit contributions
duction-1.884
bugs-1.872
 Invaders-1.858
angs-1.822
 Kund-1.802
Token like
Token ID588
Feature activation-1.28e+00

Pos logit contributions
estone+2.436
PB+2.070
+.+2.068
font+2.054
adem+2.040
Neg logit contributions
bugs-2.407
duction-2.403
 Invaders-2.389
angs-2.344
 Kund-2.342
Token:
Token ID25
Feature activation-9.13e-01

Pos logit contributions
estone+10.205
font+8.886
 activ+8.751
+.+8.611
PB+8.594
Neg logit contributions
duction-11.231
 Kund-11.056
bugs-10.923
 Invaders-10.713
angs-10.490
Token /*
Token ID11900
Feature activation-5.46e-01

Pos logit contributions
estone+7.744
font+6.870
+.+6.723
 activ+6.645
PB+6.619
Neg logit contributions
duction-8.254
 Kund-8.052
bugs-7.993
 Invaders-7.990
angs-7.801
Token vi
Token ID25357
Feature activation-1.19e+00

Pos logit contributions
estone+3.672
font+3.023
+.+2.996
PB+2.951
 activ+2.862
Neg logit contributions
duction-6.250
 Invaders-6.210
bugs-6.183
 Kund-6.153
angs-6.070
Token:
Token ID25
Feature activation-9.56e-01

Pos logit contributions
estone+10.005
+.+9.210
font+8.930
PB+8.782
Stra+8.520
Neg logit contributions
duction-9.945
 Kund-9.913
 Invaders-9.760
bugs-9.576
igers-9.299
Tokents
Token ID912
Feature activation-4.64e-01

Pos logit contributions
estone+8.398
font+7.747
+.+7.728
 activ+7.475
PB+7.433
Neg logit contributions
duction-8.097
 Kund-8.059
 Invaders-7.978
bugs-7.794
Thunder-7.636
Tokenat
Token ID265
Feature activation+6.90e-01

Pos logit contributions
bugs+3.104
duction+3.092
angs+2.993
 Invaders+2.970
cz+2.951
Neg logit contributions
estone-4.374
PB-3.860
 Flavoring-3.838
+.-3.775
font-3.763
Tokenosis
Token ID5958
Feature activation-1.07e-01

Pos logit contributions
duction+3.952
bugs+3.945
angs+3.857
cz+3.707
 Invaders+3.686
Neg logit contributions
estone-8.529
PB-7.786
adem-7.724
font-7.658
ntil-7.628
Token of
Token ID286
Feature activation+1.04e-01

Pos logit contributions
estone+0.884
font+0.742
+.+0.742
PB+0.739
 Flavoring+0.735
Neg logit contributions
duction-1.096
 Invaders-1.094
bugs-1.093
angs-1.081
igers-1.062
Token the
Token ID262
Feature activation-8.40e-01

Pos logit contributions
duction+0.861
bugs+0.858
 Invaders+0.854
angs+0.835
 Kund+0.828
Neg logit contributions
estone-1.094
PB-0.948
font-0.939
adem-0.938
+.-0.937
Token palms
Token ID39513
Feature activation+1.46e-01

Pos logit contributions
estone+2.003
+.+1.725
font+1.472
 activ+1.415
PB+1.407
Neg logit contributions
 Invaders-12.523
duction-12.318
Hunt-12.124
cz-12.056
 Kund-11.959
Token and
Token ID290
Feature activation-1.28e+00

Pos logit contributions
bugs+1.430
duction+1.429
 Invaders+1.419
angs+1.392
 Kund+1.389
Neg logit contributions
estone-1.307
PB-1.105
adem-1.092
+.-1.086
font-1.085
Token sol
Token ID1540
Feature activation-6.69e-01

Pos logit contributions
estone+4.034
 activ+3.230
+.+3.193
 nic+3.068
 sol+2.766
Neg logit contributions
Thunder-17.355
Hunt-17.290
cz-16.944
 Invaders-16.915
igers-16.768
Tokenes
Token ID274
Feature activation+1.32e-01

Pos logit contributions
estone+5.775
font+4.760
+.+4.682
adem+4.584
PB+4.528
Neg logit contributions
 Invaders-6.671
duction-6.403
 Kund-6.336
Thunder-6.287
bugs-6.197
Token")
Token ID4943
Feature activation-1.66e-01

Pos logit contributions
duction+1.069
bugs+1.068
 Invaders+1.059
angs+1.037
 Kund+1.028
Neg logit contributions
estone-1.394
PB-1.212
font-1.197
adem-1.193
+.-1.192
Token is
Token ID318
Feature activation-1.78e-03

Pos logit contributions
estone+1.419
PB+1.191
+.+1.189
font+1.187
 Flavoring+1.169
Neg logit contributions
duction-1.696
bugs-1.668
 Invaders-1.665
angs-1.656
 Kund-1.618
Token an
Token ID281
Feature activation-2.71e-01

Pos logit contributions
estone+0.018
PB+0.016
font+0.016
+.+0.016
adem+0.016
Neg logit contributions
bugs-0.015
duction-0.015
 Invaders-0.015
angs-0.015
 Kund-0.014
Token,
Token ID11
Feature activation-4.98e-01

Pos logit contributions
estone+1.432
PB+1.204
+.+1.192
font+1.188
adem+1.182
Neg logit contributions
duction-1.520
bugs-1.520
 Invaders-1.500
 Kund-1.475
angs-1.472
Token called
Token ID1444
Feature activation-4.76e-01

Pos logit contributions
estone+4.637
+.+3.899
font+3.839
PB+3.835
 activ+3.807
Neg logit contributions
bugs-4.533
duction-4.489
 Invaders-4.427
 Kund-4.416
angs-4.357
Token a
Token ID257
Feature activation-3.96e-01

Pos logit contributions
estone+4.497
PB+3.888
+.+3.851
 activ+3.836
adem+3.796
Neg logit contributions
bugs-4.235
duction-4.164
angs-4.072
 Invaders-4.066
Thunder-4.055
Token parcel
Token ID25232
Feature activation+1.55e-02

Pos logit contributions
estone+3.683
PB+3.168
+.+3.111
adem+3.075
font+3.070
Neg logit contributions
bugs-3.675
duction-3.606
 Invaders-3.560
angs-3.555
Thunder-3.480
Token,
Token ID11
Feature activation-3.36e-01

Pos logit contributions
duction+0.140
bugs+0.140
 Invaders+0.139
angs+0.136
 Kund+0.136
Neg logit contributions
estone-0.150
PB-0.128
adem-0.127
+.-0.126
font-0.126
Token and
Token ID290
Feature activation-1.27e+00

Pos logit contributions
estone+2.838
PB+2.353
+.+2.323
font+2.313
adem+2.294
Neg logit contributions
bugs-3.431
duction-3.409
angs-3.341
 Invaders-3.340
 Kund-3.326
Token decide
Token ID5409
Feature activation-7.37e-02

Pos logit contributions
estone+10.099
+.+8.396
 activ+8.342
font+7.993
PB+7.855
Neg logit contributions
bugs-11.452
duction-11.004
Thunder-10.992
igers-10.897
angs-10.700
Token where
Token ID810
Feature activation-5.12e-01

Pos logit contributions
estone+0.667
PB+0.563
+.+0.556
adem+0.556
font+0.554
Neg logit contributions
duction-0.714
bugs-0.713
 Invaders-0.706
angs-0.698
 Kund-0.690
Token to
Token ID284
Feature activation-8.66e-01

Pos logit contributions
estone+4.608
PB+3.879
+.+3.861
font+3.856
adem+3.817
Neg logit contributions
duction-4.741
bugs-4.719
 Invaders-4.648
angs-4.632
 Kund-4.598
Token place
Token ID1295
Feature activation-3.01e-01

Pos logit contributions
estone+7.492
+.+6.241
 activ+6.127
PB+6.053
font+5.806
Neg logit contributions
bugs-8.159
duction-7.782
igers-7.776
Thunder-7.695
 Invaders-7.674
Token buildings
Token ID6832
Feature activation-7.61e-02

Pos logit contributions
estone+2.818
PB+2.382
+.+2.364
font+2.344
adem+2.335
Neg logit contributions
duction-2.766
bugs-2.755
 Invaders-2.703
angs-2.697
 Kund-2.653
Tokenatch
Token ID963
Feature activation-7.85e-01

Pos logit contributions
duction+2.953
bugs+2.942
 Invaders+2.901
angs+2.899
 Kund+2.837
Neg logit contributions
estone-3.186
PB-2.754
font-2.718
adem-2.711
+.-2.697
Token 20
Token ID1160
Feature activation-7.00e-02

Pos logit contributions
estone+5.127
PB+4.046
+.+4.032
 Flavoring+3.938
font+3.912
Neg logit contributions
duction-9.162
bugs-8.849
angs-8.753
igers-8.720
cz-8.625
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
estone+0.718
PB+0.618
adem+0.617
font+0.613
+.+0.610
Neg logit contributions
bugs-0.591
duction-0.589
 Invaders-0.585
angs-0.571
 Kund-0.569
Token
Token ID198
Feature activation+1.59e-01

Pos logit contributions
estone+1.610
PB+1.381
font+1.372
+.+1.369
adem+1.308
Neg logit contributions
duction-1.741
 Invaders-1.729
bugs-1.699
angs-1.686
igers-1.672
TokenB
Token ID33
Feature activation+3.25e-01

Pos logit contributions
bugs+1.193
duction+1.174
 Invaders+1.149
angs+1.137
Thunder+1.120
Neg logit contributions
estone-1.795
adem-1.561
 Flavoring-1.545
font-1.543
PB-1.539
Tokenatch
Token ID963
Feature activation-1.26e+00

Pos logit contributions
duction+2.906
bugs+2.897
 Invaders+2.858
angs+2.853
 Kund+2.794
Neg logit contributions
estone-3.123
PB-2.699
font-2.663
adem-2.657
+.-2.642
Token 19
Token ID678
Feature activation-3.11e-01

Pos logit contributions
estone+7.932
font+6.343
+.+6.203
 Flavoring+6.171
 activ+6.148
Neg logit contributions
duction-14.157
bugs-13.137
igers-12.991
angs-12.809
cz-12.775
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
estone+3.061
PB+2.655
+.+2.614
font+2.594
 Flavoring+2.593
Neg logit contributions
duction-2.747
bugs-2.730
 Invaders-2.715
angs-2.668
 Kund-2.657
Token
Token ID198
Feature activation+1.14e-01

Pos logit contributions
estone+1.900
PB+1.628
font+1.620
+.+1.617
adem+1.535
Neg logit contributions
duction-2.107
 Invaders-2.093
bugs-2.051
angs-2.039
igers-2.027
TokenB
Token ID33
Feature activation+3.25e-01

Pos logit contributions
bugs+0.860
duction+0.849
 Invaders+0.834
angs+0.823
 Kund+0.812
Neg logit contributions
estone-1.286
adem-1.117
PB-1.108
 Flavoring-1.107
font-1.107
Tokenatch
Token ID963
Feature activation-8.44e-01

Pos logit contributions
duction+2.900
bugs+2.892
 Invaders+2.852
angs+2.849
 Kund+2.790
Neg logit contributions
estone-3.115
PB-2.691
font-2.655
adem-2.649
+.-2.635
TokenAMA
Token ID25087
Feature activation+1.81e-01

Pos logit contributions
estone+7.151
PB+6.619
+.+6.587
adem+6.584
font+6.514
Neg logit contributions
duction-1.477
 Invaders-1.462
bugs-1.424
 Kund-1.383
angs-1.338
Token showing
Token ID4478
Feature activation-2.92e-01

Pos logit contributions
bugs+1.593
duction+1.593
 Invaders+1.584
 Kund+1.539
angs+1.530
Neg logit contributions
estone-1.795
PB-1.541
adem-1.521
font-1.511
 Flavoring-1.509
Token that
Token ID326
Feature activation-2.87e-01

Pos logit contributions
estone+2.737
adem+2.323
PB+2.320
+.+2.314
font+2.310
Neg logit contributions
duction-2.668
bugs-2.656
 Invaders-2.633
angs-2.609
 Kund-2.554
Token its
Token ID663
Feature activation-4.08e-01

Pos logit contributions
estone+2.676
PB+2.309
adem+2.282
font+2.279
+.+2.264
Neg logit contributions
duction-2.628
bugs-2.609
 Invaders-2.581
angs-2.556
igers-2.507
Token drug
Token ID2563
Feature activation-6.85e-01

Pos logit contributions
estone+3.780
PB+3.245
font+3.212
adem+3.208
+.+3.196
Neg logit contributions
duction-3.747
bugs-3.711
angs-3.647
 Invaders-3.624
igers-3.573
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
estone+6.462
PB+5.695
 activ+5.622
font+5.533
 Flavoring+5.500
Neg logit contributions
bugs-5.781
duction-5.769
igers-5.684
angs-5.672
 Invaders-5.634
Token synth
Token ID33549
Feature activation-8.91e-01

Pos logit contributions
estone+11.192
 activ+10.186
PB+10.084
 pharm+9.985
 flavored+9.892
Neg logit contributions
bugs-9.465
duction-9.408
angs-9.282
igers-8.928
 Invaders-8.806
Tokenroid
Token ID3882
Feature activation-7.33e-03

Pos logit contributions
estone+9.705
PB+8.657
font+8.565
adem+8.326
 activ+8.294
Neg logit contributions
 Invaders-6.390
duction-6.091
 Kund-6.034
bugs-5.928
angs-5.799
Token,
Token ID11
Feature activation+1.30e-01

Pos logit contributions
estone+0.072
PB+0.062
adem+0.061
font+0.061
+.+0.061
Neg logit contributions
duction-0.065
bugs-0.065
 Invaders-0.064
angs-0.063
 Kund-0.063
Token is
Token ID318
Feature activation+4.15e-02

Pos logit contributions
duction+1.099
bugs+1.098
 Invaders+1.089
angs+1.064
 Kund+1.064
Neg logit contributions
estone-1.331
PB-1.151
adem-1.138
+.-1.135
font-1.134
Token not
Token ID407
Feature activation+2.61e-01

Pos logit contributions
duction+0.385
bugs+0.385
 Invaders+0.382
angs+0.375
 Kund+0.373
Neg logit contributions
estone-0.390
PB-0.333
adem-0.330
font-0.328
+.-0.328
Token 2018
Token ID2864
Feature activation+1.98e-01

Pos logit contributions
bugs+5.076
 Invaders+5.054
duction+5.047
 Kund+5.014
angs+4.916
Neg logit contributions
estone-6.435
PB-5.638
adem-5.551
font-5.541
 Flavoring-5.532
Token open
Token ID1280
Feature activation+3.89e-01

Pos logit contributions
duction+1.725
bugs+1.719
 Invaders+1.711
 Kund+1.678
angs+1.671
Neg logit contributions
estone-1.972
PB-1.697
adem-1.683
font-1.674
 Flavoring-1.670
Token enrollment
Token ID20753
Feature activation+6.85e-01

Pos logit contributions
bugs+3.801
duction+3.774
 Invaders+3.740
angs+3.698
 Kund+3.690
Neg logit contributions
estone-3.315
PB-2.805
adem-2.791
+.-2.787
 Flavoring-2.778
Token period
Token ID2278
Feature activation+5.48e-01

Pos logit contributions
bugs+4.701
duction+4.625
 Kund+4.546
 Invaders+4.535
angs+4.422
Neg logit contributions
estone-7.700
PB-6.844
 Flavoring-6.843
adem-6.797
font-6.731
Token and
Token ID290
Feature activation+2.74e-01

Pos logit contributions
bugs+4.369
 Invaders+4.295
duction+4.249
 Kund+4.236
angs+4.198
Neg logit contributions
estone-5.631
 Flavoring-5.029
PB-4.956
adem-4.884
font-4.827
Token tighten
Token ID31833
Feature activation+7.82e-01

Pos logit contributions
bugs+2.342
duction+2.338
 Invaders+2.328
 Kund+2.282
angs+2.272
Neg logit contributions
estone-2.746
PB-2.371
adem-2.344
font-2.340
+.-2.333
Token enrollment
Token ID20753
Feature activation+5.96e-01

Pos logit contributions
duction+6.531
 Kund+6.427
bugs+6.420
 Invaders+6.369
angs+6.237
Neg logit contributions
estone-7.210
PB-6.422
+.-6.288
font-6.267
adem-6.211
Token eligibility
Token ID20069
Feature activation+5.89e-01

Pos logit contributions
bugs+4.785
duction+4.713
 Kund+4.662
 Invaders+4.642
angs+4.500
Neg logit contributions
estone-6.142
PB-5.456
 Flavoring-5.404
adem-5.337
font-5.269
Token "
Token ID366
Feature activation+7.85e-02

Pos logit contributions
bugs+4.532
duction+4.461
 Invaders+4.398
 Kund+4.392
angs+4.336
Neg logit contributions
estone-6.232
PB-5.550
 Flavoring-5.546
adem-5.463
font-5.341
Tokento
Token ID1462
Feature activation+7.98e-02

Pos logit contributions
duction+0.720
bugs+0.719
 Invaders+0.715
angs+0.700
 Kund+0.699
Neg logit contributions
estone-0.748
PB-0.639
adem-0.632
font-0.630
+.-0.629
Token deter
Token ID2206
Feature activation+5.48e-02

Pos logit contributions
duction+0.701
bugs+0.700
 Invaders+0.694
angs+0.680
 Kund+0.677
Neg logit contributions
estone-0.792
PB-0.682
adem-0.675
font-0.672
+.-0.672
Tokenrene
Token ID25924
Feature activation+6.80e-01

Pos logit contributions
duction+1.233
bugs+1.231
 Invaders+1.226
angs+1.200
 Kund+1.199
Neg logit contributions
estone-1.080
PB-0.906
adem-0.897
font-0.893
+.-0.892
Token and
Token ID290
Feature activation+5.92e-01

Pos logit contributions
bugs+5.916
 Kund+5.855
 Invaders+5.760
angs+5.710
duction+5.653
Neg logit contributions
estone-6.437
PB-5.615
adem-5.611
 Flavoring-5.504
font-5.494
Token I
Token ID314
Feature activation+3.58e-01

Pos logit contributions
 Kund+4.784
 Invaders+4.678
bugs+4.636
duction+4.610
angs+4.531
Neg logit contributions
estone-6.198
PB-5.341
adem-5.314
font-5.280
+.-5.268
Token exchange
Token ID5163
Feature activation+4.37e-01

Pos logit contributions
bugs+3.086
 Invaders+3.073
duction+3.059
angs+3.004
 Kund+2.998
Neg logit contributions
estone-3.539
PB-3.052
 Flavoring-3.040
font-3.027
adem-3.020
Token worried
Token ID7960
Feature activation+7.27e-01

Pos logit contributions
bugs+3.688
 Invaders+3.635
 Kund+3.623
duction+3.605
angs+3.578
Neg logit contributions
estone-4.453
PB-3.799
 Flavoring-3.784
adem-3.753
font-3.750
Token glances
Token ID48703
Feature activation+8.02e-01

Pos logit contributions
bugs+4.950
angs+4.794
duction+4.785
 Invaders+4.734
 Kund+4.698
Neg logit contributions
estone-8.312
PB-7.289
 Flavoring-7.272
adem-7.076
+.-7.000
Token.
Token ID13
Feature activation+6.74e-01

Pos logit contributions
bugs+5.934
 Kund+5.779
duction+5.777
angs+5.757
 Invaders+5.660
Neg logit contributions
estone-8.336
PB-7.574
 Flavoring-7.441
adem-7.263
font-7.034
Token The
Token ID383
Feature activation+1.12e-02

Pos logit contributions
 Kund+5.270
 Invaders+5.256
bugs+5.125
duction+5.002
cz+4.981
Neg logit contributions
estone-7.231
adem-6.413
 activ-6.196
PB-6.167
font-6.074
Token first
Token ID717
Feature activation+3.32e-01

Pos logit contributions
duction+0.099
bugs+0.099
 Invaders+0.097
angs+0.096
 Kund+0.095
Neg logit contributions
estone-0.111
PB-0.096
adem-0.094
+.-0.094
font-0.094
Token of
Token ID286
Feature activation+3.63e-01

Pos logit contributions
duction+2.826
bugs+2.804
 Invaders+2.803
 Kund+2.779
angs+2.733
Neg logit contributions
estone-3.340
PB-2.875
adem-2.852
 Flavoring-2.845
font-2.845
Token many
Token ID867
Feature activation+1.34e-01

Pos logit contributions
bugs+2.899
 Kund+2.898
duction+2.882
 Invaders+2.874
angs+2.833
Neg logit contributions
estone-3.850
PB-3.337
adem-3.322
font-3.293
 Flavoring-3.285
Token same
Token ID976
Feature activation+1.18e-01

Pos logit contributions
estone+2.829
font+2.397
PB+2.383
adem+2.375
 Flavoring+2.342
Neg logit contributions
duction-2.974
bugs-2.968
 Invaders-2.938
angs-2.858
 Kund-2.841
Token time
Token ID640
Feature activation+1.66e-01

Pos logit contributions
duction+0.844
bugs+0.839
 Invaders+0.827
 Kund+0.811
angs+0.809
Neg logit contributions
estone-1.358
PB-1.198
adem-1.188
 Flavoring-1.185
+.-1.183
Token she
Token ID673
Feature activation+3.98e-01

Pos logit contributions
duction+1.396
bugs+1.394
 Invaders+1.386
 Kund+1.358
angs+1.354
Neg logit contributions
estone-1.690
PB-1.466
adem-1.449
 Flavoring-1.444
+.-1.438
Token does
Token ID857
Feature activation+1.49e-01

Pos logit contributions
bugs+3.388
duction+3.320
 Invaders+3.286
angs+3.263
 Kund+3.242
Neg logit contributions
estone-3.992
PB-3.500
 Flavoring-3.470
+.-3.435
adem-3.420
Token want
Token ID765
Feature activation+2.67e-01

Pos logit contributions
duction+1.382
bugs+1.380
 Invaders+1.368
angs+1.350
 Kund+1.342
Neg logit contributions
estone-1.393
PB-1.190
 Flavoring-1.177
adem-1.171
font-1.171
Token to
Token ID284
Feature activation+7.93e-01

Pos logit contributions
duction+2.196
bugs+2.153
 Invaders+2.137
 Kund+2.094
angs+2.089
Neg logit contributions
estone-2.742
PB-2.403
 Flavoring-2.381
font-2.366
adem-2.365
Token say
Token ID910
Feature activation+1.54e-01

Pos logit contributions
 Invaders+6.380
duction+6.306
angs+6.217
bugs+6.056
 Kund+6.053
Neg logit contributions
estone-7.890
PB-6.910
font-6.834
adem-6.812
 Flavoring-6.775
Token to
Token ID284
Feature activation+4.93e-01

Pos logit contributions
duction+1.386
bugs+1.384
 Invaders+1.377
angs+1.345
 Kund+1.344
Neg logit contributions
estone-1.490
PB-1.279
adem-1.262
+.-1.257
font-1.257
Token her
Token ID607
Feature activation+4.64e-01

Pos logit contributions
duction+3.870
bugs+3.841
 Invaders+3.822
 Kund+3.761
angs+3.721
Neg logit contributions
estone-5.215
PB-4.556
+.-4.480
adem-4.437
 Flavoring-4.433
Token domestic
Token ID5928
Feature activation+2.26e-01

Pos logit contributions
 Invaders+3.771
bugs+3.734
duction+3.730
 Kund+3.665
angs+3.652
Neg logit contributions
estone-4.792
PB-4.196
 Flavoring-4.093
font-4.073
adem-4.069
Token audience
Token ID5386
Feature activation-1.24e-01

Pos logit contributions
bugs+1.824
duction+1.817
 Invaders+1.804
angs+1.772
 Kund+1.768
Neg logit contributions
estone-2.379
PB-2.076
font-2.054
+.-2.049
adem-2.045
Token are
Token ID389
Feature activation-1.02e-01

Pos logit contributions
estone+2.304
PB+1.988
+.+1.952
font+1.943
adem+1.892
Neg logit contributions
duction-2.334
bugs-2.303
 Invaders-2.294
angs-2.265
igers-2.218
Token Whole
Token ID23431
Feature activation+3.98e-01

Pos logit contributions
estone+0.991
PB+0.856
+.+0.843
font+0.840
 Flavoring+0.837
Neg logit contributions
duction-0.914
bugs-0.908
 Invaders-0.904
angs-0.886
 Kund-0.872
Token Al
Token ID978
Feature activation+4.62e-01

Pos logit contributions
bugs+3.353
duction+3.284
 Invaders+3.275
 Kund+3.232
angs+3.186
Neg logit contributions
estone-4.047
adem-3.500
PB-3.480
 Flavoring-3.403
font-3.391
Tokenmonds
Token ID42620
Feature activation+3.88e-01

Pos logit contributions
duction+3.750
bugs+3.686
angs+3.672
 Kund+3.602
 Invaders+3.581
Neg logit contributions
estone-4.815
PB-4.171
adem-4.144
+.-4.112
font-4.067
Token,
Token ID837
Feature activation-3.20e-03

Pos logit contributions
bugs+3.296
 Invaders+3.284
duction+3.268
 Kund+3.262
angs+3.202
Neg logit contributions
estone-3.877
adem-3.347
PB-3.303
font-3.283
 Flavoring-3.192
Token P
Token ID350
Feature activation+7.87e-01

Pos logit contributions
estone+0.032
PB+0.027
+.+0.027
adem+0.027
font+0.027
Neg logit contributions
duction-0.028
bugs-0.028
 Invaders-0.028
angs-0.027
 Kund-0.027
Tokenec
Token ID721
Feature activation+3.30e-01

Pos logit contributions
angs+6.458
bugs+6.250
duction+6.142
igers+6.097
icks+6.093
Neg logit contributions
estone-7.509
 Flavoring-6.675
+.-6.583
PB-6.536
font-6.493
Tokenan
Token ID272
Feature activation-3.36e-01

Pos logit contributions
bugs+2.563
duction+2.536
angs+2.487
 Invaders+2.469
 Kund+2.399
Neg logit contributions
estone-3.547
PB-3.119
 Flavoring-3.112
+.-3.106
adem-3.055
Token Hal
Token ID11023
Feature activation+5.99e-01

Pos logit contributions
estone+3.384
PB+2.947
 Flavoring+2.913
+.+2.882
font+2.862
Neg logit contributions
duction-2.882
bugs-2.816
 Invaders-2.782
angs-2.770
 Kund-2.726
Tokenves
Token ID1158
Feature activation+5.12e-01

Pos logit contributions
bugs+5.489
duction+5.471
angs+5.382
 Invaders+5.266
cz+5.231
Neg logit contributions
estone-5.489
PB-4.781
adem-4.727
 Flavoring-4.614
font-4.610
Token,
Token ID837
Feature activation+1.35e-01

Pos logit contributions
bugs+4.380
 Invaders+4.270
duction+4.237
 Kund+4.235
angs+4.195
Neg logit contributions
estone-5.043
adem-4.405
PB-4.299
font-4.295
+.-4.204
TokenS
Token ID50
Feature activation-1.05e-01

Pos logit contributions
estone+0.888
PB+0.765
+.+0.752
font+0.752
adem+0.746
Neg logit contributions
duction-0.904
bugs-0.902
 Invaders-0.896
angs-0.882
 Kund-0.876
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
estone+1.026
PB+0.880
adem+0.871
font+0.867
+.+0.866
Neg logit contributions
duction-0.937
bugs-0.936
 Invaders-0.929
angs-0.910
 Kund-0.907
Token My
Token ID2011
Feature activation+2.67e-02

Pos logit contributions
bugs+2.486
duction+2.478
 Invaders+2.476
 Kund+2.403
angs+2.397
Neg logit contributions
estone-3.093
PB-2.664
adem-2.643
 Flavoring-2.632
font-2.624
Token CV
Token ID26196
Feature activation+3.80e-01

Pos logit contributions
duction+0.241
bugs+0.240
 Invaders+0.238
angs+0.234
 Kund+0.233
Neg logit contributions
estone-0.259
PB-0.222
adem-0.219
+.-0.219
font-0.219
Token has
Token ID468
Feature activation+7.07e-01

Pos logit contributions
duction+3.356
bugs+3.341
 Invaders+3.317
 Kund+3.227
angs+3.223
Neg logit contributions
estone-3.714
 Flavoring-3.195
PB-3.175
adem-3.132
+.-3.099
Token been
Token ID587
Feature activation+8.68e-01

Pos logit contributions
bugs+5.872
 Invaders+5.838
duction+5.789
 Kund+5.668
cz+5.601
Neg logit contributions
estone-6.976
 Flavoring-6.065
PB-5.984
adem-5.907
font-5.855
Token public
Token ID1171
Feature activation+3.42e-01

Pos logit contributions
bugs+7.152
 Invaders+7.001
duction+6.922
 Kund+6.863
cz+6.807
Neg logit contributions
estone-8.068
 Flavoring-7.366
PB-7.067
adem-6.974
font-6.906
Token and
Token ID290
Feature activation+2.25e-01

Pos logit contributions
duction+2.990
bugs+2.979
 Invaders+2.965
 Kund+2.871
angs+2.847
Neg logit contributions
estone-3.378
 Flavoring-2.898
PB-2.880
adem-2.856
font-2.808
Token on
Token ID319
Feature activation+3.45e-01

Pos logit contributions
duction+1.971
bugs+1.970
 Invaders+1.956
 Kund+1.911
angs+1.910
Neg logit contributions
estone-2.213
PB-1.910
 Flavoring-1.886
adem-1.881
font-1.876
Token my
Token ID616
Feature activation+5.32e-01

Pos logit contributions
bugs+2.781
duction+2.778
 Invaders+2.737
 Kund+2.682
angs+2.674
Neg logit contributions
estone-3.610
PB-3.145
 Flavoring-3.100
+.-3.087
adem-3.082
Token website
Token ID3052
Feature activation+7.19e-01

Pos logit contributions
bugs+4.633
 Invaders+4.628
duction+4.587
angs+4.500
 Kund+4.475
Neg logit contributions
estone-5.110
PB-4.377
 Flavoring-4.375
adem-4.304
+.-4.253
Tokens
Token ID82
Feature activation-3.37e-01

Pos logit contributions
estone+0.947
PB+0.818
adem+0.813
font+0.810
+.+0.809
Neg logit contributions
duction-0.763
bugs-0.763
 Invaders-0.758
 Kund-0.738
angs-0.737
Token defenders
Token ID16355
Feature activation-5.05e-02

Pos logit contributions
estone+3.241
PB+2.749
adem+2.728
+.+2.721
font+2.711
Neg logit contributions
duction-3.037
bugs-3.018
 Invaders-2.972
igers-2.902
angs-2.897
Token see
Token ID766
Feature activation+3.59e-02

Pos logit contributions
estone+0.485
PB+0.412
adem+0.411
font+0.408
+.+0.407
Neg logit contributions
duction-0.460
bugs-0.460
 Invaders-0.457
angs-0.448
 Kund-0.445
Token his
Token ID465
Feature activation-2.32e-01

Pos logit contributions
duction+0.311
bugs+0.311
 Invaders+0.308
angs+0.302
 Kund+0.301
Neg logit contributions
estone-0.360
PB-0.310
adem-0.308
font-0.306
+.-0.306
Token flaws
Token ID17978
Feature activation-3.76e-01

Pos logit contributions
estone+2.216
PB+1.872
adem+1.859
+.+1.857
font+1.857
Neg logit contributions
duction-2.128
bugs-2.121
 Invaders-2.092
angs-2.044
 Kund-2.032
Token as
Token ID355
Feature activation-5.86e-02

Pos logit contributions
estone+3.528
adem+2.986
font+2.964
PB+2.962
+.+2.954
Neg logit contributions
duction-3.507
 Invaders-3.459
bugs-3.411
angs-3.334
 Kund-3.326
Token regular
Token ID3218
Feature activation-2.88e-01

Pos logit contributions
estone+0.565
PB+0.483
adem+0.480
font+0.478
+.+0.477
Neg logit contributions
duction-0.529
bugs-0.526
 Invaders-0.523
angs-0.512
 Kund-0.510
Token-
Token ID12
Feature activation-1.21e-01

Pos logit contributions
estone+2.750
font+2.341
adem+2.331
PB+2.327
+.+2.313
Neg logit contributions
duction-2.598
bugs-2.576
 Invaders-2.567
 Kund-2.535
angs-2.514
Tokenguy
Token ID22932
Feature activation-1.25e-01

Pos logit contributions
estone+1.217
font+1.047
PB+1.043
adem+1.041
+.+1.035
Neg logit contributions
duction-1.036
 Invaders-1.035
bugs-1.030
 Kund-1.010
angs-1.007
Token problems
Token ID2761
Feature activation-6.19e-02

Pos logit contributions
estone+1.196
PB+1.025
adem+1.016
font+1.014
+.+1.008
Neg logit contributions
duction-1.129
 Invaders-1.119
bugs-1.113
 Kund-1.093
angs-1.091
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
estone+0.597
PB+0.511
adem+0.506
font+0.505
+.+0.505
Neg logit contributions
duction-0.558
bugs-0.557
 Invaders-0.554
angs-0.542
 Kund-0.541
Token.
Token ID13
Feature activation-4.20e-02

Pos logit contributions
estone+2.475
+.+2.117
PB+2.103
font+2.087
adem+2.080
Neg logit contributions
bugs-2.544
 Invaders-2.539
duction-2.537
angs-2.484
 Kund-2.479
Token All
Token ID1439
Feature activation+1.15e-01

Pos logit contributions
estone+0.414
PB+0.360
+.+0.356
font+0.356
 Flavoring+0.354
Neg logit contributions
duction-0.372
bugs-0.368
 Invaders-0.361
angs-0.360
igers-0.353
Token four
Token ID1440
Feature activation-6.80e-02

Pos logit contributions
bugs+1.023
duction+1.021
 Invaders+1.012
angs+0.994
 Kund+0.991
Neg logit contributions
estone-1.130
PB-0.972
adem-0.963
font-0.956
+.-0.956
Token people
Token ID661
Feature activation+1.50e-01

Pos logit contributions
estone+0.625
PB+0.532
adem+0.524
+.+0.524
font+0.523
Neg logit contributions
duction-0.646
bugs-0.646
 Invaders-0.641
angs-0.627
 Kund-0.625
Token I
Token ID314
Feature activation+8.68e-01

Pos logit contributions
bugs+1.313
duction+1.312
 Invaders+1.300
angs+1.275
 Kund+1.272
Neg logit contributions
estone-1.482
PB-1.278
adem-1.264
font-1.258
+.-1.257
Token brought
Token ID3181
Feature activation-1.28e-02

Pos logit contributions
duction+6.782
bugs+6.690
 Invaders+6.639
angs+6.638
 Kund+6.570
Neg logit contributions
estone-8.670
 Flavoring-7.704
PB-7.500
font-7.381
adem-7.373
Token this
Token ID428
Feature activation-1.26e-01

Pos logit contributions
estone+0.124
PB+0.107
adem+0.105
font+0.105
+.+0.105
Neg logit contributions
duction-0.115
bugs-0.114
 Invaders-0.114
angs-0.111
 Kund-0.111
Token up
Token ID510
Feature activation+1.48e-01

Pos logit contributions
estone+1.174
PB+0.999
font+0.986
+.+0.985
adem+0.982
Neg logit contributions
bugs-1.174
duction-1.169
 Invaders-1.164
angs-1.142
 Kund-1.128
Token too
Token ID1165
Feature activation-8.46e-02

Pos logit contributions
duction+1.310
bugs+1.307
 Invaders+1.292
angs+1.268
 Kund+1.267
Neg logit contributions
estone-1.455
PB-1.256
 Flavoring-1.243
adem-1.242
font-1.230
Token,
Token ID11
Feature activation-8.72e-02

Pos logit contributions
estone+0.801
PB+0.682
+.+0.679
font+0.675
adem+0.671
Neg logit contributions
duction-0.779
bugs-0.778
 Invaders-0.775
angs-0.755
 Kund-0.755
Token separately
Token ID13869
Feature activation-3.02e-01

Pos logit contributions
estone+0.822
PB+0.706
+.+0.700
font+0.698
adem+0.693
Neg logit contributions
duction-0.802
bugs-0.802
 Invaders-0.793
angs-0.779
 Kund-0.768
Token they
Token ID484
Feature activation+3.56e-01

Pos logit contributions
estone+1.116
PB+0.964
+.+0.955
font+0.952
adem+0.948
Neg logit contributions
duction-1.013
bugs-1.012
 Invaders-1.004
angs-0.986
 Kund-0.973
Token�
Token ID447
Feature activation-8.37e-02

Pos logit contributions
bugs+3.103
duction+3.089
 Invaders+3.067
angs+3.008
cz+2.984
Neg logit contributions
estone-3.508
 Flavoring-3.040
PB-3.000
font-2.969
adem-2.959
Token�
Token ID247
Feature activation-3.84e-01

Pos logit contributions
estone+0.616
PB+0.504
+.+0.501
font+0.493
adem+0.489
Neg logit contributions
bugs-0.944
duction-0.938
 Invaders-0.934
angs-0.924
 Kund-0.914
Tokenve
Token ID303
Feature activation+2.97e-01

Pos logit contributions
estone+3.468
font+2.942
+.+2.917
adem+2.903
PB+2.890
Neg logit contributions
 Invaders-3.663
bugs-3.604
duction-3.549
angs-3.514
 Kund-3.512
Token sent
Token ID1908
Feature activation-1.08e-01

Pos logit contributions
bugs+2.694
duction+2.677
 Invaders+2.651
 Kund+2.625
angs+2.593
Neg logit contributions
estone-2.825
 Flavoring-2.435
PB-2.424
adem-2.399
font-2.393
Token two
Token ID734
Feature activation-1.03e-02

Pos logit contributions
estone+1.065
PB+0.923
+.+0.915
adem+0.914
font+0.912
Neg logit contributions
duction-0.941
bugs-0.939
 Invaders-0.929
angs-0.914
 Kund-0.897
Token perfectly
Token ID7138
Feature activation+3.39e-01

Pos logit contributions
estone+0.099
PB+0.084
+.+0.083
adem+0.083
font+0.083
Neg logit contributions
duction-0.094
bugs-0.094
 Invaders-0.093
angs-0.091
 Kund-0.091
Token fine
Token ID3734
Feature activation-2.81e-01

Pos logit contributions
duction+3.110
bugs+3.106
 Invaders+3.057
angs+3.014
 Kund+3.012
Neg logit contributions
estone-3.216
 Flavoring-2.772
PB-2.748
adem-2.696
font-2.676
Token setup
Token ID9058
Feature activation+1.69e-02

Pos logit contributions
estone+2.811
+.+2.441
PB+2.425
font+2.417
adem+2.410
Neg logit contributions
duction-2.390
bugs-2.383
 Invaders-2.355
 Kund-2.299
angs-2.296
Token man
Token ID582
Feature activation+3.36e-01

Pos logit contributions
duction+0.146
bugs+0.145
 Invaders+0.144
angs+0.141
 Kund+0.141
Neg logit contributions
estone-0.171
PB-0.148
adem-0.146
+.-0.146
font-0.146
Token,
Token ID11
Feature activation+4.56e-01

Pos logit contributions
bugs+2.570
duction+2.560
 Invaders+2.519
angs+2.488
 Kund+2.435
Neg logit contributions
estone-3.708
PB-3.236
 Flavoring-3.229
adem-3.180
font-3.161
Token radio
Token ID5243
Feature activation+2.23e-01

Pos logit contributions
 Invaders+3.299
duction+3.216
 Kund+3.215
bugs+3.203
angs+3.141
Neg logit contributions
estone-4.980
PB-4.433
 Flavoring-4.402
adem-4.369
font-4.368
Token program
Token ID1430
Feature activation-3.85e-02

Pos logit contributions
 Invaders+1.628
duction+1.626
bugs+1.623
 Kund+1.582
angs+1.568
Neg logit contributions
estone-2.514
PB-2.222
adem-2.200
 Flavoring-2.199
font-2.191
Token Friday
Token ID3217
Feature activation+1.04e-01

Pos logit contributions
estone+0.370
PB+0.316
adem+0.313
+.+0.312
font+0.312
Neg logit contributions
duction-0.350
bugs-0.349
 Invaders-0.346
angs-0.340
 Kund-0.338
Token morning
Token ID3329
Feature activation+6.32e-03

Pos logit contributions
bugs+0.889
duction+0.884
 Invaders+0.878
 Kund+0.863
angs+0.859
Neg logit contributions
estone-1.039
PB-0.910
adem-0.897
font-0.889
 Flavoring-0.889
Token.
Token ID13
Feature activation-3.27e-02

Pos logit contributions
bugs+0.055
duction+0.055
 Invaders+0.054
 Kund+0.053
angs+0.053
Neg logit contributions
estone-0.063
PB-0.055
adem-0.054
font-0.054
 Flavoring-0.054
Token "
Token ID366
Feature activation+3.23e-02

Pos logit contributions
estone+0.320
PB+0.275
adem+0.272
+.+0.270
font+0.270
Neg logit contributions
bugs-0.292
duction-0.292
 Invaders-0.290
 Kund-0.284
angs-0.283
TokenBut
Token ID1537
Feature activation+2.56e-01

Pos logit contributions
duction+0.298
bugs+0.296
 Invaders+0.296
angs+0.290
 Kund+0.289
Neg logit contributions
estone-0.306
PB-0.265
font-0.260
+.-0.260
adem-0.257
Token it
Token ID340
Feature activation+2.12e-01

Pos logit contributions
bugs+2.187
duction+2.185
 Invaders+2.172
 Kund+2.121
angs+2.121
Neg logit contributions
estone-2.587
PB-2.238
adem-2.213
 Flavoring-2.204
+.-2.198
Token would
Token ID561
Feature activation+2.05e-01

Pos logit contributions
bugs+1.841
duction+1.836
 Invaders+1.821
angs+1.787
 Kund+1.782
Neg logit contributions
estone-2.107
PB-1.823
adem-1.801
 Flavoring-1.794
+.-1.794
Token have
Token ID423
Feature activation+2.04e-01

Pos logit contributions
duction+1.757
bugs+1.756
 Invaders+1.741
angs+1.713
 Kund+1.700
Neg logit contributions
estone-2.068
PB-1.790
adem-1.770
 Flavoring-1.764
+.-1.758
Token been
Token ID587
Feature activation-6.41e-02

Pos logit contributions
bugs+1.841
duction+1.835
 Invaders+1.823
 Kund+1.789
angs+1.784
Neg logit contributions
estone-1.959
PB-1.679
adem-1.664
 Flavoring-1.664
+.-1.653
Token What
Token ID1867
Feature activation+2.99e-01

Pos logit contributions
duction+0.858
bugs+0.855
 Invaders+0.846
angs+0.833
 Kund+0.824
Neg logit contributions
estone-0.919
PB-0.789
+.-0.779
font-0.778
adem-0.776
Token was
Token ID373
Feature activation-1.89e-01

Pos logit contributions
bugs+2.594
duction+2.589
 Invaders+2.569
 Kund+2.528
angs+2.523
Neg logit contributions
estone-2.974
PB-2.560
+.-2.528
adem-2.527
font-2.521
Token really
Token ID1107
Feature activation-4.22e-01

Pos logit contributions
estone+1.714
PB+1.435
adem+1.423
font+1.421
+.+1.419
Neg logit contributions
duction-1.828
bugs-1.809
 Invaders-1.805
angs-1.775
 Kund-1.741
Token needed
Token ID2622
Feature activation-3.28e-01

Pos logit contributions
estone+3.482
PB+2.821
font+2.815
adem+2.808
+.+2.779
Neg logit contributions
duction-4.377
 Invaders-4.280
angs-4.276
bugs-4.275
 Kund-4.126
Token was
Token ID373
Feature activation+2.55e-01

Pos logit contributions
estone+2.950
PB+2.479
font+2.478
adem+2.459
+.+2.434
Neg logit contributions
duction-3.139
bugs-3.132
 Invaders-3.113
angs-3.053
 Kund-3.041
Token a
Token ID257
Feature activation+8.91e-02

Pos logit contributions
duction+2.128
bugs+2.110
 Invaders+2.091
 Kund+2.062
angs+2.058
Neg logit contributions
estone-2.620
PB-2.275
 Flavoring-2.241
+.-2.239
adem-2.234
Token confession
Token ID24250
Feature activation-3.27e-02

Pos logit contributions
duction+0.794
bugs+0.793
 Invaders+0.788
angs+0.772
 Kund+0.771
Neg logit contributions
estone-0.870
PB-0.747
adem-0.739
font-0.736
+.-0.735
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
estone+0.320
PB+0.274
adem+0.272
+.+0.272
font+0.271
Neg logit contributions
duction-0.291
bugs-0.291
 Invaders-0.289
angs-0.283
 Kund-0.282
Token
Token ID198
Feature activation-4.08e-02

Pos logit contributions
duction+0.936
bugs+0.934
 Invaders+0.925
angs+0.909
 Kund+0.903
Neg logit contributions
estone-1.025
PB-0.882
adem-0.870
+.-0.870
font-0.870
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
estone+0.386
PB+0.332
font+0.330
+.+0.328
adem+0.322
Neg logit contributions
duction-0.379
 Invaders-0.376
bugs-0.373
angs-0.368
 Kund-0.362
TokenObama
Token ID15948
Feature activation+3.02e-01

Pos logit contributions
estone+1.238
PB+1.081
font+1.054
+.+1.054
adem+1.046
Neg logit contributions
 Invaders-1.278
duction-1.273
bugs-1.258
 Kund-1.236
angs-1.236
Token]
Token ID60
Feature activation-3.90e-01

Pos logit contributions
bugs+3.403
 Invaders+3.387
duction+3.385
 Kund+3.305
angs+3.298
Neg logit contributions
estone-4.736
 Flavoring-4.114
adem-4.100
PB-4.044
font-4.022
Token],
Token ID4357
Feature activation-2.56e-02

Pos logit contributions
estone+3.901
PB+3.463
+.+3.451
font+3.392
adem+3.316
Neg logit contributions
duction-3.256
bugs-3.230
 Invaders-3.211
angs-3.169
 Kund-3.141
Token step
Token ID2239
Feature activation+6.34e-01

Pos logit contributions
estone+0.251
PB+0.217
+.+0.214
font+0.214
 Flavoring+0.213
Neg logit contributions
bugs-0.227
duction-0.227
 Invaders-0.224
angs-0.221
 Kund-0.219
TokenOld
Token ID19620
Feature activation-5.57e-03

Pos logit contributions
bugs+5.027
duction+4.917
Thunder+4.860
 Invaders+4.839
Date+4.800
Neg logit contributions
estone-6.474
adem-5.631
 activ-5.460
font-5.450
 Flavoring-5.411
Token]
Token ID60
Feature activation-4.07e-01

Pos logit contributions
estone+0.054
PB+0.047
adem+0.046
+.+0.046
font+0.046
Neg logit contributions
duction-0.050
bugs-0.050
 Invaders-0.049
angs-0.048
 Kund-0.048
Token (*
Token ID20789
Feature activation-3.97e-01

Pos logit contributions
estone+4.056
PB+3.598
+.+3.592
font+3.500
 Flavoring+3.454
Neg logit contributions
bugs-3.411
duction-3.398
 Invaders-3.358
angs-3.331
 Kund-3.294
Token mark
Token ID1317
Feature activation+8.17e-02

Pos logit contributions
estone+3.624
PB+3.071
+.+3.052
font+3.048
adem+3.018
Neg logit contributions
bugs-3.711
duction-3.709
 Invaders-3.610
angs-3.609
 Kund-3.587
Token locations
Token ID7064
Feature activation+2.72e-02

Pos logit contributions
duction+0.697
bugs+0.696
 Invaders+0.691
angs+0.676
 Kund+0.674
Neg logit contributions
estone-0.831
PB-0.718
adem-0.711
font-0.708
+.-0.708
Token as
Token ID355
Feature activation-2.35e-02

Pos logit contributions
bugs+0.256
duction+0.256
 Invaders+0.254
angs+0.249
 Kund+0.248
Neg logit contributions
estone-0.253
PB-0.215
adem-0.212
+.-0.212
font-0.211
Token Sear
Token ID42016
Feature activation-3.51e-01

Pos logit contributions
estone+0.229
PB+0.196
+.+0.194
adem+0.193
font+0.193
Neg logit contributions
bugs-0.211
duction-0.211
 Invaders-0.208
angs-0.206
 Kund-0.204
Tokenched
Token ID1740
Feature activation-8.79e-02

Pos logit contributions
estone+3.527
PB+3.024
+.+3.008
font+2.996
adem+2.981
Neg logit contributions
bugs-2.990
duction-2.990
 Invaders-2.989
 Kund-2.934
angs-2.885
Token was
Token ID373
Feature activation-8.82e-02

Pos logit contributions
bugs+1.421
duction+1.417
 Invaders+1.405
angs+1.381
 Kund+1.380
Neg logit contributions
estone-1.531
PB-1.318
adem-1.301
+.-1.297
 Flavoring-1.294
Token asked
Token ID1965
Feature activation+5.29e-02

Pos logit contributions
estone+0.823
PB+0.697
adem+0.693
font+0.690
+.+0.685
Neg logit contributions
bugs-0.826
duction-0.823
 Invaders-0.818
angs-0.806
igers-0.792
Token by
Token ID416
Feature activation+8.46e-01

Pos logit contributions
duction+0.465
bugs+0.465
 Invaders+0.461
angs+0.452
 Kund+0.450
Neg logit contributions
estone-0.524
PB-0.451
adem-0.446
font-0.445
+.-0.445
Token NBC
Token ID9716
Feature activation+5.81e-01

Pos logit contributions
 Kund+5.894
 Invaders+5.821
bugs+5.673
angs+5.586
duction+5.583
Neg logit contributions
estone-8.920
PB-8.069
 Flavoring-8.062
font-7.980
adem-7.779
Token News
Token ID3000
Feature activation+4.02e-01

Pos logit contributions
bugs+4.214
 Invaders+4.126
duction+4.084
 Kund+4.006
cz+3.904
Neg logit contributions
estone-6.472
 Flavoring-5.778
font-5.667
PB-5.636
adem-5.636
Token'
Token ID6
Feature activation-1.47e-01

Pos logit contributions
 Invaders+3.374
bugs+3.372
duction+3.351
 Kund+3.282
angs+3.198
Neg logit contributions
estone-4.057
PB-3.525
 Flavoring-3.504
adem-3.474
font-3.464
Token Savannah
Token ID40695
Feature activation+4.51e-01

Pos logit contributions
estone+1.652
PB+1.445
+.+1.438
font+1.422
adem+1.421
Neg logit contributions
duction-1.125
bugs-1.089
 Invaders-1.066
angs-1.061
igers-1.039
Token Guth
Token ID44003
Feature activation+2.53e-01

Pos logit contributions
 Kund+2.644
bugs+2.642
 Invaders+2.590
duction+2.543
angs+2.423
Neg logit contributions
estone-5.743
PB-5.123
adem-5.102
 Flavoring-5.098
font-5.083
Tokenrie
Token ID5034
Feature activation+1.08e-01

Pos logit contributions
bugs+2.194
duction+2.191
 Invaders+2.158
angs+2.128
 Kund+2.116
Neg logit contributions
estone-2.513
PB-2.177
 Flavoring-2.153
adem-2.149
font-2.141
Token (
Token ID357
Feature activation+2.30e-01

Pos logit contributions
bugs+0.936
duction+0.935
 Invaders+0.929
 Kund+0.907
angs+0.907
Neg logit contributions
estone-1.084
PB-0.935
adem-0.925
font-0.921
+.-0.920
Tokenright
Token ID3506
Feature activation-2.41e-01

Pos logit contributions
duction+2.126
bugs+2.124
 Invaders+2.086
angs+2.073
 Kund+2.047
Neg logit contributions
estone-2.153
 Flavoring-1.854
+.-1.820
adem-1.817
PB-1.805
Token-
Token ID12
Feature activation+4.06e-01

Pos logit contributions
estone+1.199
PB+1.016
font+1.008
+.+1.008
adem+1.007
Neg logit contributions
 Invaders-1.275
duction-1.273
bugs-1.265
angs-1.245
 Kund-1.226
Tokenplay
Token ID1759
Feature activation-1.09e-01

Pos logit contributions
bugs+2.914
duction+2.849
angs+2.744
cz+2.726
 Invaders+2.712
Neg logit contributions
estone-4.677
 Flavoring-4.185
PB-4.077
+.-4.057
adem-4.051
Token guy
Token ID3516
Feature activation+1.18e-01

Pos logit contributions
estone+1.049
PB+0.898
+.+0.892
font+0.889
adem+0.888
Neg logit contributions
bugs-0.985
duction-0.983
 Invaders-0.978
angs-0.960
 Kund-0.948
Token who
Token ID508
Feature activation+2.78e-02

Pos logit contributions
bugs+1.029
duction+1.026
 Invaders+1.018
angs+0.997
 Kund+0.996
Neg logit contributions
estone-1.169
PB-1.009
adem-0.999
 Flavoring-0.992
font-0.990
Token is
Token ID318
Feature activation-4.18e-01

Pos logit contributions
duction+0.260
bugs+0.258
 Invaders+0.257
angs+0.252
 Kund+0.251
Neg logit contributions
estone-0.261
PB-0.222
adem-0.220
font-0.219
+.-0.219
Token not
Token ID407
Feature activation-6.10e-01

Pos logit contributions
estone+3.716
PB+3.127
font+3.115
+.+3.107
adem+3.093
Neg logit contributions
duction-3.985
bugs-3.970
 Invaders-3.901
angs-3.832
igers-3.792
Token interested
Token ID4609
Feature activation+1.30e-02

Pos logit contributions
estone+5.140
font+4.364
PB+4.322
adem+4.319
 activ+4.252
Neg logit contributions
duction-5.901
bugs-5.814
 Invaders-5.781
angs-5.670
 Kund-5.552
Token in
Token ID287
Feature activation+3.78e-01

Pos logit contributions
bugs+0.111
duction+0.111
 Invaders+0.110
angs+0.108
 Kund+0.108
Neg logit contributions
estone-0.132
PB-0.115
adem-0.114
font-0.113
+.-0.113
Token just
Token ID655
Feature activation+3.56e-01

Pos logit contributions
bugs+3.292
 Invaders+3.256
duction+3.249
 Kund+3.216
angs+3.170
Neg logit contributions
estone-3.757
PB-3.198
adem-3.171
+.-3.170
font-3.153
Token blending
Token ID34863
Feature activation-1.33e-02

Pos logit contributions
bugs+3.115
duction+3.089
 Invaders+3.066
 Kund+3.015
angs+3.001
Neg logit contributions
estone-3.525
PB-3.020
+.-2.985
adem-2.984
 Flavoring-2.963
Token in
Token ID287
Feature activation-1.69e-01

Pos logit contributions
estone+0.131
PB+0.112
adem+0.111
+.+0.111
font+0.111
Neg logit contributions
duction-0.117
bugs-0.117
 Invaders-0.116
angs-0.114
 Kund-0.113
Tokenyear
Token ID1941
Feature activation-6.29e-02

Pos logit contributions
bugs+1.227
duction+1.224
 Invaders+1.213
angs+1.184
 Kund+1.180
Neg logit contributions
estone-1.505
PB-1.298
adem-1.290
 Flavoring-1.286
font-1.280
Token-
Token ID12
Feature activation+1.60e-01

Pos logit contributions
estone+0.627
PB+0.541
adem+0.535
font+0.532
 Flavoring+0.531
Neg logit contributions
bugs-0.548
duction-0.547
 Invaders-0.546
angs-0.534
 Kund-0.532
Tokenold
Token ID727
Feature activation+3.58e-02

Pos logit contributions
duction+1.240
bugs+1.240
 Invaders+1.228
angs+1.200
 Kund+1.195
Neg logit contributions
estone-1.744
PB-1.523
adem-1.509
font-1.503
+.-1.503
Token Hed
Token ID30920
Feature activation-3.89e-02

Pos logit contributions
duction+0.322
bugs+0.322
 Invaders+0.319
angs+0.313
 Kund+0.312
Neg logit contributions
estone-0.348
PB-0.298
adem-0.295
+.-0.294
font-0.294
Tokenges
Token ID3212
Feature activation-3.90e-01

Pos logit contributions
estone+0.457
PB+0.402
adem+0.399
font+0.398
+.+0.398
Neg logit contributions
bugs-0.271
duction-0.271
 Invaders-0.268
angs-0.261
 Kund-0.260
Token is
Token ID318
Feature activation-1.33e-01

Pos logit contributions
estone+3.454
PB+2.907
font+2.881
adem+2.875
+.+2.874
Neg logit contributions
duction-3.762
bugs-3.732
 Invaders-3.709
angs-3.607
 Kund-3.599
Token sure
Token ID1654
Feature activation+1.52e-01

Pos logit contributions
estone+1.309
PB+1.122
adem+1.110
font+1.103
+.+1.101
Neg logit contributions
bugs-1.195
duction-1.189
 Invaders-1.173
angs-1.156
 Kund-1.139
Token to
Token ID284
Feature activation+4.97e-01

Pos logit contributions
duction+1.320
bugs+1.316
 Invaders+1.300
 Kund+1.285
angs+1.277
Neg logit contributions
estone-1.519
PB-1.306
 Flavoring-1.298
adem-1.290
+.-1.288
Token be
Token ID307
Feature activation+5.26e-01

Pos logit contributions
duction+3.902
 Invaders+3.879
bugs+3.864
angs+3.844
 Kund+3.783
Neg logit contributions
estone-5.140
 Flavoring-4.518
font-4.468
PB-4.464
adem-4.455
Token a
Token ID257
Feature activation+2.82e-01

Pos logit contributions
duction+4.172
bugs+4.162
 Invaders+4.154
 Kund+4.115
angs+4.019
Neg logit contributions
estone-5.357
 Flavoring-4.696
+.-4.663
adem-4.654
PB-4.623
Token breakout
Token ID31661
Feature activation-1.56e-01

Pos logit contributions
duction+2.405
bugs+2.391
 Invaders+2.391
 Kund+2.353
angs+2.315
Neg logit contributions
estone-2.825
adem-2.410
PB-2.401
font-2.393
 Flavoring-2.389
Token than
Token ID621
Feature activation+2.79e-01

Pos logit contributions
estone+1.765
PB+1.499
font+1.477
+.+1.475
 Flavoring+1.450
Neg logit contributions
duction-1.858
bugs-1.839
 Invaders-1.811
angs-1.797
 Kund-1.779
Token M
Token ID337
Feature activation+1.67e-01

Pos logit contributions
 Invaders+2.303
bugs+2.302
duction+2.302
 Kund+2.252
angs+2.222
Neg logit contributions
estone-2.885
PB-2.498
adem-2.470
 Flavoring-2.461
+.-2.449
TokenAF
Token ID8579
Feature activation+1.35e-01

Pos logit contributions
bugs+1.092
duction+1.088
 Invaders+1.079
angs+1.056
 Kund+1.044
Neg logit contributions
estone-2.025
PB-1.799
adem-1.782
font-1.778
 Flavoring-1.777
Token,
Token ID11
Feature activation-7.08e-02

Pos logit contributions
bugs+1.171
duction+1.169
 Invaders+1.165
angs+1.137
 Kund+1.136
Neg logit contributions
estone-1.349
PB-1.158
adem-1.151
font-1.148
 Flavoring-1.143
Token there
Token ID612
Feature activation-1.82e-01

Pos logit contributions
estone+0.700
PB+0.604
font+0.597
+.+0.596
adem+0.595
Neg logit contributions
duction-0.621
bugs-0.618
 Invaders-0.613
angs-0.605
 Kund-0.596
Token's
Token ID338
Feature activation-2.68e-01

Pos logit contributions
estone+1.649
PB+1.393
adem+1.393
+.+1.383
font+1.381
Neg logit contributions
duction-1.746
bugs-1.741
 Invaders-1.741
angs-1.703
 Kund-1.701
Token obviously
Token ID6189
Feature activation-3.39e-01

Pos logit contributions
estone+2.672
PB+2.317
font+2.304
+.+2.304
adem+2.300
Neg logit contributions
duction-2.273
bugs-2.268
 Invaders-2.255
angs-2.233
igers-2.169
Token zero
Token ID6632
Feature activation-1.48e-01

Pos logit contributions
estone+3.302
PB+2.853
adem+2.849
font+2.842
+.+2.832
Neg logit contributions
duction-2.929
 Invaders-2.904
bugs-2.900
angs-2.873
igers-2.817
Token drama
Token ID10512
Feature activation-1.42e-01

Pos logit contributions
estone+1.443
PB+1.237
+.+1.233
font+1.228
adem+1.217
Neg logit contributions
duction-1.318
bugs-1.312
 Invaders-1.291
angs-1.285
igers-1.260
Token and
Token ID290
Feature activation+9.35e-02

Pos logit contributions
estone+1.361
PB+1.158
+.+1.157
font+1.153
adem+1.146
Neg logit contributions
duction-1.293
 Invaders-1.285
bugs-1.282
angs-1.260
 Kund-1.248
Token the
Token ID262
Feature activation+3.36e-02

Pos logit contributions
duction+0.802
bugs+0.801
 Invaders+0.795
angs+0.778
 Kund+0.775
Neg logit contributions
estone-0.947
PB-0.817
adem-0.809
font-0.806
+.-0.806
Token for
Token ID329
Feature activation-2.72e-01

Pos logit contributions
estone+3.597
font+2.991
+.+2.987
PB+2.964
adem+2.948
Neg logit contributions
duction-3.732
bugs-3.705
angs-3.701
 Invaders-3.634
igers-3.608
Token evidence
Token ID2370
Feature activation-1.05e-01

Pos logit contributions
estone+2.546
PB+2.137
adem+2.127
font+2.126
+.+2.106
Neg logit contributions
duction-2.557
bugs-2.543
 Invaders-2.498
angs-2.486
igers-2.427
Token that
Token ID326
Feature activation-9.99e-02

Pos logit contributions
estone+0.980
PB+0.826
font+0.825
+.+0.823
adem+0.823
Neg logit contributions
duction-0.976
bugs-0.971
 Invaders-0.965
angs-0.952
 Kund-0.935
Token Russia
Token ID3284
Feature activation-4.22e-01

Pos logit contributions
estone+0.957
PB+0.814
adem+0.809
font+0.808
+.+0.804
Neg logit contributions
bugs-0.908
duction-0.906
 Invaders-0.898
angs-0.886
 Kund-0.869
Token was
Token ID373
Feature activation-2.86e-01

Pos logit contributions
estone+4.032
PB+3.421
+.+3.392
adem+3.380
font+3.321
Neg logit contributions
duction-3.788
bugs-3.737
 Invaders-3.727
angs-3.670
igers-3.612
Token behind
Token ID2157
Feature activation-1.16e+00

Pos logit contributions
estone+2.702
adem+2.305
PB+2.297
font+2.286
+.+2.266
Neg logit contributions
 Invaders-2.611
bugs-2.602
duction-2.571
angs-2.553
 Kund-2.474
Token the
Token ID262
Feature activation-3.74e-01

Pos logit contributions
estone+9.123
adem+7.652
 activ+7.652
 pharm+7.642
font+7.427
Neg logit contributions
bugs-10.442
angs-10.273
 Invaders-10.253
igers-10.230
duction-9.983
Token embarrassing
Token ID18997
Feature activation-3.90e-02

Pos logit contributions
estone+3.917
adem+3.394
PB+3.356
+.+3.345
font+3.341
Neg logit contributions
bugs-3.000
duction-2.953
 Invaders-2.941
angs-2.931
igers-2.856
Token Democratic
Token ID4390
Feature activation+1.90e-01

Pos logit contributions
estone+0.409
PB+0.353
adem+0.351
font+0.350
+.+0.350
Neg logit contributions
bugs-0.320
duction-0.320
 Invaders-0.317
angs-0.312
 Kund-0.308
Token National
Token ID2351
Feature activation+2.28e-02

Pos logit contributions
duction+1.604
bugs+1.602
 Invaders+1.590
 Kund+1.556
angs+1.549
Neg logit contributions
estone-1.950
PB-1.688
adem-1.668
font-1.667
+.-1.666
Token Committee
Token ID4606
Feature activation+1.60e-01

Pos logit contributions
duction+0.170
bugs+0.170
 Invaders+0.169
angs+0.164
 Kund+0.164
Neg logit contributions
estone-0.256
PB-0.225
adem-0.223
font-0.222
+.-0.222
TokenDraw
Token ID25302
Feature activation-3.00e-01

Pos logit contributions
estone+3.078
PB+2.723
font+2.711
adem+2.657
+.+2.638
Neg logit contributions
duction-2.695
bugs-2.693
 Invaders-2.685
angs-2.644
 Kund-2.622
Tokening
Token ID278
Feature activation+1.17e-01

Pos logit contributions
estone+2.137
font+1.732
PB+1.666
adem+1.641
+.+1.637
Neg logit contributions
 Invaders-3.505
duction-3.442
bugs-3.420
 Kund-3.397
angs-3.382
Token.
Token ID13
Feature activation-1.30e-01

Pos logit contributions
bugs+0.980
duction+0.979
 Invaders+0.971
angs+0.947
 Kund+0.941
Neg logit contributions
estone-1.191
adem-1.025
PB-1.021
 Flavoring-1.003
+.-0.997
TokenColor
Token ID10258
Feature activation+3.36e-01

Pos logit contributions
estone+1.340
PB+1.174
font+1.161
adem+1.152
+.+1.148
Neg logit contributions
duction-1.088
bugs-1.082
 Invaders-1.078
angs-1.053
 Kund-1.052
Token]
Token ID60
Feature activation-1.08e+00

Pos logit contributions
duction+2.237
bugs+2.221
 Invaders+2.217
angs+2.141
 Kund+2.136
Neg logit contributions
estone-4.001
adem-3.480
 Flavoring-3.475
+.-3.467
PB-3.452
Token::
Token ID3712
Feature activation-9.75e-01

Pos logit contributions
estone+6.937
PB+6.457
font+6.276
+.+6.182
adem+5.798
Neg logit contributions
duction-11.519
bugs-11.510
angs-11.466
 Invaders-11.434
igers-11.318
TokenFrom
Token ID4863
Feature activation-6.64e-01

Pos logit contributions
estone+8.779
PB+8.557
font+8.470
adem+8.003
Stra+7.936
Neg logit contributions
 Invaders-8.141
duction-8.040
bugs-7.870
igers-7.758
 Kund-7.735
TokenAr
Token ID3163
Feature activation+8.10e-02

Pos logit contributions
estone+6.050
PB+5.575
font+5.421
 Flavoring+5.198
Stra+5.187
Neg logit contributions
 Invaders-6.047
bugs-6.041
duction-6.015
angs-5.878
igers-5.832
Tokengb
Token ID22296
Feature activation+1.63e-01

Pos logit contributions
duction+1.037
bugs+1.037
 Invaders+1.029
angs+1.016
 Kund+1.013
Neg logit contributions
estone-0.477
PB-0.366
adem-0.358
+.-0.355
font-0.355
Token($
Token ID16763
Feature activation-4.23e-01

Pos logit contributions
duction+1.472
bugs+1.468
 Invaders+1.464
angs+1.433
 Kund+1.427
Neg logit contributions
estone-1.565
PB-1.331
adem-1.327
+.-1.319
 Flavoring-1.317
TokenBG
Token ID40469
Feature activation-3.00e-01

Pos logit contributions
estone+3.909
PB+3.473
font+3.436
adem+3.360
+.+3.295
Neg logit contributions
 Invaders-3.937
duction-3.876
bugs-3.859
 Kund-3.822
angs-3.789
Token.
Token ID13
Feature activation-3.73e-01

Pos logit contributions
estone+5.470
PB+4.969
+.+4.777
font+4.665
adem+4.575
Neg logit contributions
duction-5.633
 Invaders-5.615
bugs-5.613
angs-5.501
 Kund-5.334
Token5
Token ID20
Feature activation-8.35e-01

Pos logit contributions
estone+3.484
PB+3.094
+.+3.074
font+3.014
 Flavoring+2.983
Neg logit contributions
duction-3.379
bugs-3.312
 Invaders-3.274
angs-3.250
igers-3.213
Token-
Token ID12
Feature activation-2.33e-01

Pos logit contributions
estone+7.055
PB+6.510
+.+6.161
font+6.047
adem+5.996
Neg logit contributions
bugs-7.544
 Invaders-7.535
duction-7.526
angs-7.319
igers-7.125
Token4
Token ID19
Feature activation-7.37e-01

Pos logit contributions
estone+2.295
PB+1.991
font+1.962
adem+1.957
+.+1.955
Neg logit contributions
 Invaders-2.046
duction-2.025
bugs-2.018
angs-1.974
 Kund-1.968
Token.
Token ID13
Feature activation-4.44e-01

Pos logit contributions
estone+6.299
PB+5.526
+.+5.427
 Flavoring+5.289
font+5.269
Neg logit contributions
 Invaders-7.031
bugs-6.958
duction-6.955
angs-6.818
 Kund-6.745
Token9
Token ID24
Feature activation-1.16e+00

Pos logit contributions
estone+4.298
+.+3.781
PB+3.771
font+3.708
adem+3.643
Neg logit contributions
duction-3.883
 Invaders-3.850
bugs-3.840
igers-3.689
angs-3.688
Token tonnes
Token ID26840
Feature activation-1.03e-01

Pos logit contributions
estone+9.144
PB+8.694
+.+8.077
font+7.846
adem+7.815
Neg logit contributions
 Invaders-10.158
bugs-10.127
duction-10.067
angs-9.849
igers-9.500
Token.
Token ID13
Feature activation-2.51e-01

Pos logit contributions
estone+1.078
PB+0.937
+.+0.929
adem+0.927
font+0.926
Neg logit contributions
duction-0.842
bugs-0.839
 Invaders-0.833
angs-0.812
 Kund-0.805
Token The
Token ID383
Feature activation-9.78e-02

Pos logit contributions
estone+2.434
PB+2.097
 Flavoring+2.074
+.+2.074
font+2.050
Neg logit contributions
duction-2.257
bugs-2.249
 Invaders-2.196
angs-2.176
igers-2.137
Token study
Token ID2050
Feature activation-6.00e-03

Pos logit contributions
estone+0.964
PB+0.828
+.+0.819
adem+0.817
font+0.812
Neg logit contributions
duction-0.866
bugs-0.866
 Invaders-0.853
angs-0.838
 Kund-0.825
Token estimated
Token ID6108
Feature activation-2.64e-01

Pos logit contributions
estone+0.059
PB+0.051
adem+0.050
+.+0.050
font+0.050
Neg logit contributions
duction-0.053
bugs-0.053
 Invaders-0.053
angs-0.051
 Kund-0.051
Tokenma
Token ID2611
Feature activation-3.35e-02

Pos logit contributions
estone+2.119
font+1.835
adem+1.831
PB+1.815
+.+1.792
Neg logit contributions
 Invaders-1.397
duction-1.381
bugs-1.361
 Kund-1.325
angs-1.324
Token v
Token ID410
Feature activation-1.97e-01

Pos logit contributions
estone+0.313
PB+0.268
adem+0.264
font+0.263
+.+0.263
Neg logit contributions
bugs-0.312
duction-0.311
 Invaders-0.311
angs-0.304
 Kund-0.303
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
estone+1.750
+.+1.495
PB+1.475
font+1.459
 Flavoring+1.450
Neg logit contributions
duction-1.947
bugs-1.912
 Invaders-1.874
angs-1.870
 Kund-1.824
Token Goodell
Token ID41648
Feature activation-1.08e-01

Pos logit contributions
estone+1.077
PB+0.927
adem+0.917
font+0.914
+.+0.914
Neg logit contributions
duction-0.944
bugs-0.944
 Invaders-0.936
angs-0.917
 Kund-0.914
Token Supplemental
Token ID48165
Feature activation-2.91e-01

Pos logit contributions
estone+1.121
PB+0.970
+.+0.961
adem+0.960
font+0.960
Neg logit contributions
duction-0.897
bugs-0.889
 Invaders-0.873
angs-0.861
 Kund-0.853
Token Mem
Token ID4942
Feature activation-9.35e-01

Pos logit contributions
estone+2.981
PB+2.552
+.+2.534
adem+2.527
font+2.520
Neg logit contributions
duction-2.515
bugs-2.448
angs-2.387
 Invaders-2.364
igers-2.353
Tokeno
Token ID78
Feature activation-2.61e-01

Pos logit contributions
estone+7.158
font+5.558
PB+5.526
+.+5.442
adem+5.261
Neg logit contributions
duction-9.894
bugs-9.893
 Invaders-9.699
 Kund-9.343
igers-9.310
Token in
Token ID287
Feature activation-8.46e-02

Pos logit contributions
estone+2.522
PB+2.140
+.+2.127
font+2.120
adem+2.101
Neg logit contributions
duction-2.350
bugs-2.347
 Invaders-2.303
angs-2.260
 Kund-2.247
Token Support
Token ID7929
Feature activation-3.10e-01

Pos logit contributions
estone+0.776
PB+0.654
adem+0.647
font+0.646
+.+0.641
Neg logit contributions
bugs-0.810
duction-0.808
 Invaders-0.799
angs-0.787
 Kund-0.782
Token of
Token ID286
Feature activation-2.86e-01

Pos logit contributions
estone+2.763
PB+2.299
adem+2.285
font+2.284
+.+2.270
Neg logit contributions
duction-3.036
bugs-3.030
 Invaders-3.000
angs-2.943
 Kund-2.940
Token In
Token ID554
Feature activation+7.57e-02

Pos logit contributions
estone+2.994
PB+2.589
adem+2.561
 Flavoring+2.550
font+2.545
Neg logit contributions
duction-2.355
bugs-2.335
angs-2.242
 Invaders-2.239
 Kund-2.188
Token the
Token ID262
Feature activation+4.70e-01

Pos logit contributions
bugs+2.939
 Invaders+2.926
duction+2.921
 Kund+2.880
angs+2.821
Neg logit contributions
estone-3.515
PB-3.031
adem-3.008
 Flavoring-3.000
font-2.988
Token fly
Token ID6129
Feature activation+5.52e-02

Pos logit contributions
bugs+4.070
 Invaders+4.027
 Kund+3.996
duction+3.988
angs+3.865
Neg logit contributions
estone-4.649
adem-3.982
 Flavoring-3.971
PB-3.962
font-3.937
Tokenby
Token ID1525
Feature activation+2.65e-01

Pos logit contributions
bugs+0.538
duction+0.536
 Invaders+0.528
angs+0.519
 Kund+0.515
Neg logit contributions
estone-0.493
PB-0.420
 Flavoring-0.417
adem-0.416
+.-0.412
Token of
Token ID286
Feature activation+1.25e-02

Pos logit contributions
duction+2.321
bugs+2.320
 Invaders+2.303
 Kund+2.262
angs+2.245
Neg logit contributions
estone-2.614
PB-2.259
 Flavoring-2.241
adem-2.235
font-2.231
Token Comet
Token ID36238
Feature activation-5.38e-01

Pos logit contributions
duction+0.099
bugs+0.099
 Invaders+0.098
angs+0.096
 Kund+0.095
Neg logit contributions
estone-0.135
PB-0.117
adem-0.116
font-0.116
+.-0.116
Token Bor
Token ID12182
Feature activation-9.81e-01

Pos logit contributions
estone+5.326
+.+4.697
font+4.677
PB+4.646
 Flavoring+4.609
Neg logit contributions
duction-4.394
angs-4.286
bugs-4.278
 Invaders-4.204
igers-4.181
Tokenrell
Token ID11252
Feature activation-8.03e-01

Pos logit contributions
estone+5.983
font+4.509
+.+4.319
adem+4.293
PB+4.170
Neg logit contributions
 Invaders-11.350
angs-11.102
 Kund-11.097
bugs-10.896
Thunder-10.725
Tokeny
Token ID88
Feature activation-9.13e-02

Pos logit contributions
estone+4.187
font+3.172
+.+3.030
PB+2.922
adem+2.844
Neg logit contributions
 Invaders-10.632
duction-10.400
angs-10.036
igers-10.012
 Kund-9.993
Token was
Token ID373
Feature activation+2.75e-01

Pos logit contributions
estone+0.872
PB+0.740
+.+0.733
adem+0.732
font+0.727
Neg logit contributions
duction-0.841
bugs-0.836
 Invaders-0.826
angs-0.814
 Kund-0.804
Token a
Token ID257
Feature activation+2.97e-02

Pos logit contributions
duction+2.389
bugs+2.388
 Invaders+2.368
 Kund+2.328
angs+2.302
Neg logit contributions
estone-2.723
PB-2.364
 Flavoring-2.344
font-2.333
adem-2.322
Token great
Token ID1049
Feature activation-2.91e-01

Pos logit contributions
bugs+0.265
duction+0.265
 Invaders+0.262
angs+0.257
 Kund+0.255
Neg logit contributions
estone-0.290
PB-0.249
adem-0.246
+.-0.246
font-0.245