TOP ACTIVATIONS
MAX = 24.480

, bl anc , et rou ge over the last ten
f unt p ère , cr é ateur origin el du
N IN JA / SAM URA I 2006
textual encoding ( er asure , variability , repeat ability ,
and the price of established dwellings gets a boost , investors
way will be in full uniform , will take over the
Once the coffee and cakes are consumed I get up
to throw . If the ball gets hit in the air
. D IV IDE AND CON QU ER was about introducing
: 47 ] < ok clock zy > lol m 2
- Cl over field - Bob Grant - R ac ism
to see if the R FI is affected . Recon nect
km ( 30 miles ) from the central city of B
New England , according to Mon nat s analysis
D IV IDE AND CON QU ER was about introducing the
. When interest rates rise , the cost of
claimed the lives of over 1 million Iraqis .
. The door bell rang while I was preparing
Wat erville Hotel ( now the Wat erville Tavern ) that
rat rice , A u cr é p usc ule de

MIN ACTIVATIONS
MIN = -21.208

series . The high - output 3 . 5
few people on Donald Trump 's short list to be running
give us back our rights . We need the Travel Ban
of terrain at low and high speeds both on -
at West Brom wich Albion and Stoke City achieved without players
Best T reek As yu K ong Ch oya Week end
demonstrate that trans val uation does occur . Brief ly ,
) and wh iz on high for a minute or so
Only a single back sl ash before the ' :' is
the former is truly coming to fruition . Indeed
destroyed , but that can only be done by sending it
pleasing placeholder p > li > ul >
said Klopp , whose side face Crystal Palace at Anfield on
. The high - output 3 . 5 -
pieces ? half _ m oves : u 16 , //
bind =" phone . name "> span > < p ng
Rapt or the ultimate high - performance off - road
blog should also firmly put to bed claims that Facebook comments
she 's got this huge negotiation coming up ," said Quentin
k oul as is a research fellow at Per Cap ita

INTERVAL 13.058 - 24.480
CONTAINS 0.175%

o ia e pa a he p
many southern and central parts of Somalia . But
will update this section when we can add more platforms .
woman , whose name has not been released , rode her
positive ( G 1 : the IPCC s implicit

INTERVAL 1.636 - 13.058
CONTAINS 34.834%

theories are No z ick 's account of rationality as an
Friday , April 3 rd , 2015 FR ES
. If it is , run the power off
th - second lead . When Bolton only semi - cle
. Alex ei Naval ny has been the least lucky :

INTERVAL -9.786 - 1.636
CONTAINS 63.878%

meeting . " The real decision is whether to
building a conflict between Mid n ighter and Dick Grayson ,
remarkable conc ord ances between samples from different fossils , geographic
builder mus ing about the ­ T itan ic . No
Orange " and " One Fle w Over the C uck

INTERVAL -21.208 - -9.786
CONTAINS 1.113%

LGBT people , who are fighting back against street harassment .
dollar campaign to finish the work of the genocide .
losing 75 billion tons of ice every year ]
that claimed the life of activist Heather He yer .)
:: Center $ s Format . Line Al ignment = [
Token,
Token ID11
Feature activation+6.54e+00

Pos logit contributions
ascar+0.969
ropolitan+0.966
mph+0.954
aned+0.929
mith+0.922
Neg logit contributions
bis-1.115
uay-1.103
 Maher-0.953
MIT-0.950
timer-0.927
Token bl
Token ID698
Feature activation+1.25e+01

Pos logit contributions
bis+4.925
uay+4.803
 Maher+4.253
 Labrador+4.177
prints+4.122
Neg logit contributions
ropolitan-4.161
ascar-4.102
mph-4.034
rolet-3.919
aned-3.915
Tokenanc
Token ID1192
Feature activation+2.62e+00

Pos logit contributions
uay+8.056
bis+8.055
prints+6.672
isine+6.527
timer+6.520
Neg logit contributions
ropolitan-8.391
 Mn-8.112
 ►-8.108
mph-8.094
mith-8.059
Token,
Token ID11
Feature activation+1.24e+01

Pos logit contributions
bis+2.214
uay+2.163
 Maher+1.913
MIT+1.896
isine+1.883
Neg logit contributions
ropolitan-1.470
ascar-1.446
mph-1.420
aned-1.384
mith-1.375
Token et
Token ID2123
Feature activation+5.99e-02

Pos logit contributions
bis+9.072
uay+8.621
 Labrador+7.874
 Maher+7.790
 quo+7.774
Neg logit contributions
ropolitan-7.511
ascar-7.318
mph-7.132
aned-7.050
mith-6.994
Token rou
Token ID13805
Feature activation+2.45e+01

Pos logit contributions
bis+0.049
uay+0.048
 Maher+0.042
MIT+0.042
isine+0.041
Neg logit contributions
ropolitan-0.035
ascar-0.035
mph-0.034
aned-0.033
rolet-0.033
Tokenge
Token ID469
Feature activation+1.29e+01

Pos logit contributions
bis+15.187
uay+13.824
prints+12.262
vier+12.247
 quo+12.163
Neg logit contributions
ropolitan-14.607
ascar-13.779
ruction-13.235
 ED-13.090
 Scion-12.746
Token over
Token ID625
Feature activation+8.87e+00

Pos logit contributions
bis+8.779
uay+8.383
 Labrador+7.590
prints+7.552
 Maher+7.478
Neg logit contributions
ropolitan-8.447
ascar-8.074
mph-7.962
aned-7.901
rolet-7.900
Token the
Token ID262
Feature activation+7.34e-01

Pos logit contributions
bis+6.497
uay+6.403
 Maher+5.680
prints+5.546
 Labrador+5.545
Neg logit contributions
ropolitan-5.546
ascar-5.532
mph-5.405
mith-5.287
aned-5.256
Token last
Token ID938
Feature activation+1.91e+00

Pos logit contributions
bis+0.645
uay+0.631
 Maher+0.558
MIT+0.557
isine+0.553
Neg logit contributions
ropolitan-0.390
ascar-0.384
mph-0.377
aned-0.367
mith-0.363
Token ten
Token ID3478
Feature activation+1.64e+00

Pos logit contributions
bis+1.595
uay+1.560
 Maher+1.376
MIT+1.365
isine+1.352
Neg logit contributions
ropolitan-1.097
ascar-1.079
mph-1.057
aned-1.032
mith-1.025
Tokenf
Token ID69
Feature activation+5.98e+00

Pos logit contributions
bis+4.330
uay+4.127
prints+3.593
MIT+3.588
isine+3.577
Neg logit contributions
ropolitan-3.329
ascar-3.268
mph-3.149
aned-3.135
mith-3.105
Tokenunt
Token ID2797
Feature activation+5.42e+00

Pos logit contributions
bis+4.783
uay+4.676
isine+4.019
prints+4.006
 Maher+3.991
Neg logit contributions
ropolitan-3.538
ascar-3.449
mph-3.401
mith-3.360
aned-3.305
Token p
Token ID279
Feature activation+7.85e+00

Pos logit contributions
bis+4.387
uay+4.250
 Maher+3.766
MIT+3.693
 quo+3.690
Neg logit contributions
ropolitan-3.191
ascar-3.093
mph-3.085
mith-3.030
weekly-2.969
Tokenère
Token ID35979
Feature activation+7.81e+00

Pos logit contributions
bis+5.613
uay+5.518
isine+4.688
 Maher+4.591
ieu+4.570
Neg logit contributions
ropolitan-5.251
ascar-5.076
mph-4.967
mith-4.945
 ►-4.935
Token,
Token ID11
Feature activation+7.56e+00

Pos logit contributions
bis+6.229
uay+5.916
 Maher+5.347
 quo+5.265
 Labrador+5.214
Neg logit contributions
ropolitan-4.636
ascar-4.467
mph-4.378
aned-4.286
mith-4.282
Token cr
Token ID1067
Feature activation+2.31e+01

Pos logit contributions
bis+6.023
uay+5.827
 Maher+5.209
 quo+5.160
MIT+5.128
Neg logit contributions
ropolitan-4.482
ascar-4.325
mph-4.252
mith-4.145
aned-4.100
Tokené
Token ID2634
Feature activation+5.27e+00

Pos logit contributions
bis+13.758
uay+13.481
ieu+11.846
ité+11.582
ierre+11.463
Neg logit contributions
ropolitan-13.658
 Mn-13.292
 Lith-13.130
 ►-13.013
-12.988
Tokenateur
Token ID15093
Feature activation+9.05e+00

Pos logit contributions
bis+4.134
uay+3.987
isine+3.472
MIT+3.460
 Maher+3.445
Neg logit contributions
ropolitan-3.268
ascar-3.192
mph-3.100
aned-3.077
mith-3.072
Token origin
Token ID8159
Feature activation+8.76e+00

Pos logit contributions
bis+7.050
uay+6.765
 Maher+6.006
 quo+5.978
isine+5.877
Neg logit contributions
ropolitan-5.395
ascar-5.233
mph-5.126
mith-5.033
rolet-5.005
Tokenel
Token ID417
Feature activation+6.88e+00

Pos logit contributions
bis+7.163
uay+7.009
 quo+6.060
isine+6.050
 Maher+6.043
Neg logit contributions
ropolitan-4.955
mith-4.730
ascar-4.725
mph-4.681
rolet-4.534
Token du
Token ID7043
Feature activation+3.46e+00

Pos logit contributions
bis+5.525
uay+5.301
 Maher+4.697
 quo+4.633
MIT+4.623
Neg logit contributions
ropolitan-4.119
ascar-3.958
mph-3.918
rolet-3.807
mith-3.797
Token
Token ID198
Feature activation+2.42e+00

Pos logit contributions
ropolitan+0.688
ascar+0.680
mph+0.674
mith+0.657
aned+0.656
Neg logit contributions
bis-0.739
uay-0.722
 Maher-0.621
isine-0.619
MIT-0.617
TokenN
Token ID45
Feature activation-4.35e-01

Pos logit contributions
bis+1.789
uay+1.738
MIT+1.509
 Maher+1.503
isine+1.470
Neg logit contributions
ropolitan-1.630
ascar-1.601
mph-1.568
aned-1.545
mith-1.529
TokenIN
Token ID1268
Feature activation+7.51e+00

Pos logit contributions
ascar+0.265
ropolitan+0.264
mph+0.257
aned+0.251
mith+0.247
Neg logit contributions
bis-0.346
uay-0.338
 Maher-0.299
MIT-0.295
isine-0.293
TokenJA
Token ID37048
Feature activation+6.77e+00

Pos logit contributions
bis+4.174
uay+4.044
 Maher+3.403
MIT+3.384
 Labrador+3.206
Neg logit contributions
ropolitan-6.259
aned-6.071
ascar-6.057
mph-5.998
rolet-5.940
Token/
Token ID14
Feature activation+9.54e+00

Pos logit contributions
bis+5.037
uay+4.869
 Maher+4.278
MIT+4.248
 Labrador+4.163
Neg logit contributions
ropolitan-4.428
ascar-4.309
mph-4.259
aned-4.193
rolet-4.152
TokenSAM
Token ID49302
Feature activation+2.18e+01

Pos logit contributions
bis+6.368
uay+6.060
MIT+5.545
 Maher+5.222
timer+5.106
Neg logit contributions
ropolitan-6.826
ascar-6.667
mph-6.518
aned-6.493
rolet-6.417
TokenURA
Token ID45570
Feature activation+7.15e+00

Pos logit contributions
uay+9.482
MIT+8.501
bis+8.474
IRO+7.452
 Maher+7.267
Neg logit contributions
ropolitan-16.850
 twe-16.375
inth-16.345
aned-16.340
ascar-16.312
TokenI
Token ID40
Feature activation+1.37e+01

Pos logit contributions
bis+4.294
uay+4.058
MIT+3.688
 Maher+3.505
IRO+3.332
Neg logit contributions
ropolitan-5.821
ascar-5.676
aned-5.633
rolet-5.587
 tempted-5.409
Token
Token ID198
Feature activation-2.92e-01

Pos logit contributions
bis+9.259
uay+8.662
 Maher+7.812
MIT+7.758
 Labrador+7.620
Neg logit contributions
ropolitan-8.803
ascar-8.638
aned-8.482
mph-8.442
rolet-8.335
Token
Token ID198
Feature activation+3.21e+00

Pos logit contributions
ropolitan+0.203
ascar+0.200
mph+0.198
aned+0.193
mith+0.193
Neg logit contributions
bis-0.207
uay-0.202
 Maher-0.174
MIT-0.172
isine-0.171
Token2006
Token ID13330
Feature activation+3.29e+00

Pos logit contributions
bis+2.422
uay+2.350
MIT+2.056
 Maher+2.034
prints+2.002
Neg logit contributions
ropolitan-2.111
ascar-2.072
mph-2.023
aned-1.994
rolet-1.974
Token textual
Token ID40577
Feature activation+8.30e-02

Pos logit contributions
bis+4.402
uay+4.251
 Maher+3.744
MIT+3.703
isine+3.677
Neg logit contributions
ascar-3.288
ropolitan-3.285
mph-3.174
aned-3.102
rolet-3.095
Token encoding
Token ID21004
Feature activation-1.04e+00

Pos logit contributions
bis+0.065
uay+0.063
 Maher+0.055
MIT+0.055
isine+0.054
Neg logit contributions
ropolitan-0.052
ascar-0.051
mph-0.051
mith-0.050
aned-0.049
Token (
Token ID357
Feature activation+6.28e-01

Pos logit contributions
ropolitan+0.628
ascar+0.619
mph+0.608
mith+0.603
aned+0.598
Neg logit contributions
bis-0.821
uay-0.811
 Maher-0.708
MIT-0.706
isine-0.700
Tokener
Token ID263
Feature activation+2.41e-02

Pos logit contributions
bis+0.469
uay+0.459
 Maher+0.400
MIT+0.394
isine+0.392
Neg logit contributions
ropolitan-0.414
ascar-0.408
mph-0.404
aned-0.394
mith-0.394
Tokenasure
Token ID5015
Feature activation+2.77e+00

Pos logit contributions
bis+0.021
uay+0.021
 Maher+0.019
MIT+0.019
 Labrador+0.018
Neg logit contributions
ropolitan-0.013
ascar-0.012
mph-0.012
aned-0.012
mith-0.012
Token,
Token ID11
Feature activation+2.14e+01

Pos logit contributions
bis+2.046
uay+1.993
 Maher+1.725
MIT+1.713
isine+1.696
Neg logit contributions
ropolitan-1.851
ascar-1.827
mph-1.798
aned-1.762
mith-1.746
Token variability
Token ID25364
Feature activation+5.43e+00

Pos logit contributions
bis+13.247
uay+12.083
 quo+11.696
hum+11.510
 mismatch+11.477
Neg logit contributions
ascar-11.792
ropolitan-11.548
mph-11.341
rolet-11.285
Lex-11.244
Token,
Token ID11
Feature activation+1.10e+01

Pos logit contributions
bis+3.799
uay+3.673
 Maher+3.178
MIT+3.145
isine+3.119
Neg logit contributions
ropolitan-3.760
ascar-3.707
mph-3.664
aned-3.601
rolet-3.566
Token repeat
Token ID9585
Feature activation+4.76e+00

Pos logit contributions
bis+7.935
uay+7.336
 Maher+6.601
 quo+6.543
prints+6.524
Neg logit contributions
ascar-6.994
ropolitan-6.867
mph-6.818
rolet-6.625
aned-6.605
Tokenability
Token ID1799
Feature activation+4.69e+00

Pos logit contributions
bis+3.295
uay+3.116
MIT+2.706
 Maher+2.697
timer+2.676
Neg logit contributions
ropolitan-3.313
ascar-3.255
mph-3.215
rolet-3.209
aned-3.186
Token,
Token ID11
Feature activation+5.86e+00

Pos logit contributions
bis+3.338
uay+3.228
 Maher+2.790
MIT+2.767
isine+2.742
Neg logit contributions
ropolitan-3.226
ascar-3.193
mph-3.137
aned-3.087
rolet-3.055
Token and
Token ID290
Feature activation+3.06e+00

Pos logit contributions
bis+3.730
uay+3.605
 Maher+3.160
MIT+3.120
prints+3.080
Neg logit contributions
ropolitan-3.366
ascar-3.357
mph-3.279
aned-3.221
rolet-3.211
Token the
Token ID262
Feature activation+5.27e+00

Pos logit contributions
bis+2.624
uay+2.568
 Maher+2.285
MIT+2.256
 Labrador+2.236
Neg logit contributions
ropolitan-1.671
ascar-1.646
mph-1.610
aned-1.564
mith-1.552
Token price
Token ID2756
Feature activation+1.01e+01

Pos logit contributions
bis+4.180
uay+4.076
 Maher+3.622
 Labrador+3.543
MIT+3.523
Neg logit contributions
ropolitan-3.169
ascar-3.166
mph-3.095
rolet-2.972
mith-2.968
Token of
Token ID286
Feature activation+4.24e+00

Pos logit contributions
bis+7.033
uay+6.739
 quo+6.093
 Maher+5.987
 Labrador+5.966
Neg logit contributions
ropolitan-6.629
ascar-6.605
mph-6.404
rolet-6.398
aned-6.285
Token established
Token ID4920
Feature activation-2.06e+00

Pos logit contributions
bis+3.179
uay+3.087
 Maher+2.722
MIT+2.680
 Labrador+2.671
Neg logit contributions
ropolitan-2.759
ascar-2.726
mph-2.679
rolet-2.598
mith-2.597
Token dwellings
Token ID50078
Feature activation+2.09e+01

Pos logit contributions
ropolitan+1.083
ascar+1.030
aned+1.022
mph+1.022
 ED+0.985
Neg logit contributions
bis-1.822
uay-1.800
 Maher-1.585
MIT-1.582
isine-1.576
Token gets
Token ID3011
Feature activation-3.14e+00

Pos logit contributions
bis+12.041
uay+11.073
 quo+11.041
 mismatch+10.159
 Labrador+10.011
Neg logit contributions
ropolitan-12.700
ascar-12.560
rolet-12.339
mph-12.081
cture-12.059
Token a
Token ID257
Feature activation+1.00e-01

Pos logit contributions
ropolitan+1.807
ascar+1.789
mph+1.783
aned+1.762
mith+1.729
Neg logit contributions
bis-2.570
uay-2.517
MIT-2.219
isine-2.199
 Maher-2.168
Token boost
Token ID5750
Feature activation+2.55e+00

Pos logit contributions
bis+0.091
uay+0.089
 Maher+0.079
MIT+0.079
isine+0.078
Neg logit contributions
ropolitan-0.050
ascar-0.049
mph-0.048
aned-0.047
mith-0.047
Token,
Token ID11
Feature activation+3.61e+00

Pos logit contributions
bis+1.891
uay+1.845
 Maher+1.605
MIT+1.589
isine+1.571
Neg logit contributions
ropolitan-1.693
ascar-1.670
mph-1.642
aned-1.608
mith-1.592
Token investors
Token ID7713
Feature activation-4.67e+00

Pos logit contributions
bis+2.766
uay+2.696
 Maher+2.376
MIT+2.329
 Labrador+2.310
Neg logit contributions
ropolitan-2.292
ascar-2.272
mph-2.234
aned-2.173
rolet-2.164
Token way
Token ID835
Feature activation-1.17e+00

Pos logit contributions
bis+2.427
uay+2.363
 Maher+2.047
MIT+2.030
isine+2.003
Neg logit contributions
ropolitan-2.195
ascar-2.158
mph-2.113
aned-2.073
mith-2.065
Token will
Token ID481
Feature activation+7.45e+00

Pos logit contributions
ropolitan+0.723
ascar+0.721
mph+0.704
aned+0.700
mith+0.692
Neg logit contributions
bis-0.919
uay-0.900
MIT-0.787
 Maher-0.780
isine-0.779
Token be
Token ID307
Feature activation+6.90e+00

Pos logit contributions
bis+5.823
uay+5.575
 Maher+4.936
MIT+4.870
 Labrador+4.829
Neg logit contributions
ropolitan-4.521
ascar-4.405
mph-4.370
Lex-4.246
aned-4.245
Token in
Token ID287
Feature activation+1.10e+01

Pos logit contributions
bis+5.359
uay+5.266
 Maher+4.705
 Labrador+4.534
prints+4.476
Neg logit contributions
ropolitan-4.273
ascar-4.134
mph-4.045
rolet-3.972
ruction-3.911
Token full
Token ID1336
Feature activation+1.33e+01

Pos logit contributions
bis+7.932
uay+7.826
 Maher+6.969
 Labrador+6.890
prints+6.827
Neg logit contributions
ascar-6.711
ropolitan-6.675
mph-6.547
aned-6.296
rolet-6.242
Token uniform
Token ID8187
Feature activation+2.07e+01

Pos logit contributions
bis+9.777
uay+9.449
prints+8.575
 Maher+8.520
 Rossi+8.457
Neg logit contributions
ascar-7.592
ropolitan-7.551
mph-7.451
cture-7.251
rolet-7.219
Token,
Token ID11
Feature activation+7.39e+00

Pos logit contributions
bis+12.312
uay+10.872
 quo+10.007
prints+9.983
 Maher+9.931
Neg logit contributions
mph-12.282
cture-12.151
ropolitan-12.104
ascar-12.004
aned-11.940
Token will
Token ID481
Feature activation+1.09e+01

Pos logit contributions
bis+5.652
uay+5.465
 Maher+4.875
 Labrador+4.721
MIT+4.716
Neg logit contributions
ropolitan-4.585
ascar-4.506
mph-4.454
rolet-4.284
Lex-4.262
Token take
Token ID1011
Feature activation+1.57e+01

Pos logit contributions
bis+8.320
uay+7.869
 Maher+7.066
MIT+7.011
 Labrador+6.920
Neg logit contributions
ropolitan-6.437
ascar-6.296
mph-6.224
Lex-6.080
aned-6.010
Token over
Token ID625
Feature activation+1.23e+01

Pos logit contributions
bis+8.401
uay+8.289
 Maher+7.420
MIT+7.269
prints+7.175
Neg logit contributions
ropolitan-11.625
ascar-11.365
mph-11.204
mith-11.024
inth-10.775
Token the
Token ID262
Feature activation+5.63e+00

Pos logit contributions
bis+8.427
uay+8.205
 Maher+7.587
 Labrador+7.315
prints+7.281
Neg logit contributions
ropolitan-7.737
mph-7.658
ascar-7.629
rolet-7.310
aned-7.294
Token
Token ID198
Feature activation+3.59e+00

Pos logit contributions
mph+2.329
ropolitan+2.326
ascar+2.285
mith+2.258
Lex+2.230
Neg logit contributions
bis-2.899
uay-2.863
icter-2.563
�醒-2.516
isine-2.514
TokenOnce
Token ID7454
Feature activation+6.59e-01

Pos logit contributions
bis+2.697
uay+2.595
MIT+2.296
 Maher+2.242
prints+2.230
Neg logit contributions
ropolitan-2.388
ascar-2.344
mph-2.264
rolet-2.239
aned-2.238
Token the
Token ID262
Feature activation+4.68e+00

Pos logit contributions
bis+0.526
uay+0.516
 Maher+0.450
MIT+0.449
isine+0.443
Neg logit contributions
ropolitan-0.401
ascar-0.395
mph-0.390
aned-0.381
mith-0.378
Token coffee
Token ID6891
Feature activation+9.93e+00

Pos logit contributions
bis+3.663
uay+3.551
 Maher+3.143
 Labrador+3.093
MIT+3.074
Neg logit contributions
ropolitan-2.920
ascar-2.871
mph-2.779
rolet-2.738
aned-2.718
Token and
Token ID290
Feature activation+2.71e+00

Pos logit contributions
bis+7.047
uay+6.618
timer+6.028
 Maher+6.024
 Labrador+5.932
Neg logit contributions
ropolitan-6.498
ascar-6.380
rolet-6.260
mph-6.217
mith-5.999
Token cakes
Token ID30849
Feature activation+2.07e+01

Pos logit contributions
bis+2.259
uay+2.204
 Maher+1.948
MIT+1.928
isine+1.912
Neg logit contributions
ropolitan-1.566
ascar-1.535
mph-1.508
aned-1.469
mith-1.458
Token are
Token ID389
Feature activation+7.97e+00

Pos logit contributions
bis+11.629
uay+10.455
timer+9.852
 Maher+9.806
 quo+9.664
Neg logit contributions
ropolitan-13.225
ascar-13.064
rolet-12.942
mph-12.673
Lex-12.584
Token consumed
Token ID13529
Feature activation+7.33e+00

Pos logit contributions
bis+6.420
uay+6.317
 Maher+5.709
 Labrador+5.575
 Rossi+5.486
Neg logit contributions
ropolitan-4.628
ascar-4.459
mph-4.359
rolet-4.252
Lex-4.178
Token I
Token ID314
Feature activation+9.36e+00

Pos logit contributions
bis+5.120
uay+4.861
 Maher+4.361
MIT+4.256
isine+4.234
Neg logit contributions
ropolitan-4.995
ascar-4.939
mph-4.835
aned-4.725
rolet-4.706
Token get
Token ID651
Feature activation-3.24e-01

Pos logit contributions
bis+7.479
uay+7.151
 Maher+6.364
 Labrador+6.264
 quo+6.233
Neg logit contributions
ropolitan-5.412
ascar-5.346
rolet-5.034
mph-5.021
Lex-4.964
Token up
Token ID510
Feature activation+2.74e+00

Pos logit contributions
ropolitan+0.191
ascar+0.190
mph+0.187
aned+0.183
mith+0.181
Neg logit contributions
bis-0.264
uay-0.258
MIT-0.226
isine-0.224
 Maher-0.223
Token to
Token ID284
Feature activation+8.92e+00

Pos logit contributions
bis+1.255
uay+1.226
 Maher+1.073
MIT+1.066
isine+1.055
Neg logit contributions
ropolitan-0.978
ascar-0.963
mph-0.946
aned-0.925
mith-0.918
Token throw
Token ID3714
Feature activation+9.68e+00

Pos logit contributions
bis+6.995
uay+6.796
 Maher+6.032
 quo+5.980
MIT+5.941
Neg logit contributions
ropolitan-5.399
ascar-5.181
rolet-4.942
weekly-4.914
aned-4.912
Token.
Token ID13
Feature activation+1.40e+00

Pos logit contributions
bis+6.609
uay+6.332
 Maher+5.610
 Labrador+5.458
 Rossi+5.444
Neg logit contributions
ropolitan-6.879
ascar-6.549
rolet-6.503
aned-6.320
weekly-6.258
Token If
Token ID1002
Feature activation-2.87e-02

Pos logit contributions
bis+1.085
uay+1.061
 Maher+0.923
MIT+0.918
isine+0.914
Neg logit contributions
ropolitan-0.889
ascar-0.878
mph-0.864
aned-0.843
mith-0.840
Token the
Token ID262
Feature activation+6.69e+00

Pos logit contributions
ropolitan+0.016
ascar+0.016
mph+0.016
aned+0.016
mith+0.016
Neg logit contributions
bis-0.024
uay-0.023
 Maher-0.020
MIT-0.020
isine-0.020
Token ball
Token ID2613
Feature activation+2.03e+01

Pos logit contributions
bis+4.535
uay+4.448
 Maher+3.777
MIT+3.737
 Labrador+3.719
Neg logit contributions
ropolitan-4.886
ascar-4.714
rolet-4.582
aned-4.531
mph-4.520
Token gets
Token ID3011
Feature activation+1.87e+00

Pos logit contributions
bis+12.393
uay+11.867
prints+10.411
 Rossi+10.315
 quo+10.273
Neg logit contributions
ropolitan-12.863
rolet-12.555
ascar-12.173
aned-11.544
ruction-11.424
Token hit
Token ID2277
Feature activation+2.92e+00

Pos logit contributions
bis+1.440
uay+1.405
 Maher+1.224
MIT+1.216
isine+1.204
Neg logit contributions
ropolitan-1.195
ascar-1.178
mph-1.159
aned-1.134
mith-1.126
Token in
Token ID287
Feature activation+8.41e+00

Pos logit contributions
bis+2.160
uay+2.103
 Maher+1.835
MIT+1.816
isine+1.796
Neg logit contributions
ropolitan-1.943
ascar-1.913
mph-1.869
aned-1.838
rolet-1.827
Token the
Token ID262
Feature activation+1.82e+00

Pos logit contributions
bis+6.183
uay+5.993
 Maher+5.265
 Labrador+5.201
MIT+5.149
Neg logit contributions
ropolitan-5.505
ascar-5.325
rolet-5.240
weekly-5.107
aned-5.073
Token air
Token ID1633
Feature activation+8.93e+00

Pos logit contributions
bis+1.480
uay+1.446
 Maher+1.270
MIT+1.262
isine+1.251
Neg logit contributions
ropolitan-1.082
ascar-1.067
mph-1.048
aned-1.023
mith-1.016
Token.
Token ID13
Feature activation-1.84e+00

Pos logit contributions
ropolitan+1.122
mph+1.117
ascar+1.117
mith+1.089
aned+1.079
Neg logit contributions
bis-1.560
uay-1.520
MIT-1.312
isine-1.308
 Maher-1.305
Token D
Token ID360
Feature activation-8.74e-01

Pos logit contributions
ropolitan+1.089
ascar+1.083
mph+1.073
mith+1.044
 ED+1.042
Neg logit contributions
bis-1.481
uay-1.446
isine-1.270
MIT-1.243
prints-1.238
TokenIV
Token ID3824
Feature activation-1.90e+00

Pos logit contributions
ropolitan+0.406
ascar+0.406
mph+0.393
aned+0.381
mith+0.374
Neg logit contributions
bis-0.823
uay-0.809
 Maher-0.724
MIT-0.718
isine-0.711
TokenIDE
Token ID14114
Feature activation+4.00e+00

Pos logit contributions
ropolitan+1.044
ascar+1.035
mph+1.019
aned+0.984
Lex+0.975
Neg logit contributions
bis-1.617
uay-1.587
 Maher-1.406
isine-1.381
 Labrador-1.371
Token AND
Token ID5357
Feature activation+8.42e+00

Pos logit contributions
bis+3.207
uay+3.127
 Maher+2.774
MIT+2.749
prints+2.702
Neg logit contributions
ropolitan-2.408
ascar-2.346
mph-2.316
aned-2.250
rolet-2.234
Token CON
Token ID7102
Feature activation+2.00e+01

Pos logit contributions
bis+5.727
uay+5.505
MIT+4.950
 Maher+4.874
 Labrador+4.795
Neg logit contributions
ropolitan-5.852
ascar-5.705
mph-5.640
aned-5.542
mith-5.481
TokenQU
Token ID10917
Feature activation+1.93e+01

Pos logit contributions
MIT+8.179
bis+8.098
uay+7.394
SIGN+6.354
vier+6.123
Neg logit contributions
ropolitan-16.836
aned-16.061
ascar-15.687
 tempted-15.547
mph-15.442
TokenER
Token ID1137
Feature activation+5.53e-01

Pos logit contributions
MIT+5.073
bis+4.682
uay+4.645
IRO+3.594
timer+3.157
Neg logit contributions
ropolitan-18.927
ascar-18.153
rolet-18.117
 tempted-17.989
aned-17.919
Token was
Token ID373
Feature activation-9.16e-01

Pos logit contributions
bis+0.430
uay+0.420
 Maher+0.365
MIT+0.362
isine+0.359
Neg logit contributions
ropolitan-0.348
ascar-0.344
mph-0.338
aned-0.332
mith-0.330
Token about
Token ID546
Feature activation-2.69e+00

Pos logit contributions
ropolitan+0.548
ascar+0.546
mph+0.540
aned+0.530
mith+0.525
Neg logit contributions
bis-0.736
uay-0.715
MIT-0.623
isine-0.618
 Maher-0.616
Token introducing
Token ID16118
Feature activation-9.53e-01

Pos logit contributions
ascar+1.497
ropolitan+1.492
mph+1.474
 ED+1.437
aned+1.435
Neg logit contributions
bis-2.262
uay-2.204
MIT-1.944
isine-1.922
 Maher-1.896
Token:
Token ID25
Feature activation-2.17e+00

Pos logit contributions
ropolitan+0.242
ascar+0.239
mph+0.237
aned+0.231
mith+0.230
Neg logit contributions
bis-0.275
uay-0.269
 Maher-0.233
MIT-0.231
isine-0.230
Token47
Token ID2857
Feature activation+3.24e+00

Pos logit contributions
ropolitan+1.039
ascar+1.031
mph+1.023
mith+0.983
Lex+0.974
Neg logit contributions
bis-1.993
uay-1.964
 Maher-1.751
isine-1.751
MIT-1.734
Token]
Token ID60
Feature activation+2.86e+00

Pos logit contributions
bis+2.122
uay+2.040
MIT+1.737
 Maher+1.735
timer+1.691
Neg logit contributions
ropolitan-2.445
ascar-2.424
mph-2.345
aned-2.336
rolet-2.333
Token <
Token ID1279
Feature activation-7.61e+00

Pos logit contributions
bis+2.316
uay+2.264
 Maher+1.990
MIT+1.979
isine+1.953
Neg logit contributions
ropolitan-1.714
ascar-1.682
mph-1.647
aned-1.613
mith-1.603
Tokenok
Token ID482
Feature activation-5.43e+00

Pos logit contributions
mph+5.023
ropolitan+4.958
ascar+4.956
mith+4.945
aned+4.843
Neg logit contributions
bis-5.188
uay-5.155
 Maher-4.738
 Labrador-4.551
 Rossi-4.458
Tokenclock
Token ID15750
Feature activation+1.98e+01

Pos logit contributions
mph+3.937
ascar+3.929
ropolitan+3.925
mith+3.831
inth+3.822
Neg logit contributions
uay-3.523
bis-3.457
 Maher-3.066
 Labrador-3.043
MIT-2.930
Tokenzy
Token ID7357
Feature activation+1.20e+00

Pos logit contributions
bis+8.611
uay+7.880
timer+6.533
ozy+6.289
versions+5.969
Neg logit contributions
ropolitan-16.239
 Scion-16.026
GGGGGGGG-15.969
ascar-15.839
IONS-15.607
Token>
Token ID29
Feature activation-5.76e+00

Pos logit contributions
bis+0.725
uay+0.702
 Maher+0.585
MIT+0.582
prints+0.568
Neg logit contributions
ropolitan-0.972
ascar-0.960
mph-0.940
aned-0.929
rolet-0.923
Token lol
Token ID19462
Feature activation-4.63e+00

Pos logit contributions
mph+3.224
ropolitan+3.213
 ED+3.209
ascar+3.200
mith+3.159
Neg logit contributions
bis-4.661
uay-4.577
isine-3.982
prints-3.965
MIT-3.926
Token m
Token ID285
Feature activation-5.44e+00

Pos logit contributions
ropolitan+2.452
mph+2.448
ascar+2.419
mith+2.390
aned+2.340
Neg logit contributions
bis-3.945
uay-3.905
prints-3.393
isine-3.382
 Maher-3.347
Token2
Token ID17
Feature activation+6.39e+00

Pos logit contributions
ascar+3.289
ropolitan+3.205
mph+3.203
aned+3.109
mith+3.059
Neg logit contributions
bis-4.236
uay-4.178
 Maher-3.711
 Labrador-3.693
isine-3.649
Token-
Token ID12
Feature activation+2.80e+00

Pos logit contributions
ropolitan+0.397
ascar+0.391
mph+0.386
aned+0.377
mith+0.376
Neg logit contributions
bis-0.457
uay-0.446
 Maher-0.387
MIT-0.384
isine-0.382
TokenCl
Token ID2601
Feature activation+6.81e+00

Pos logit contributions
bis+2.175
uay+2.121
 Maher+1.853
MIT+1.847
isine+1.813
Neg logit contributions
ropolitan-1.769
ascar-1.735
mph-1.703
aned-1.669
mith-1.655
Tokenover
Token ID2502
Feature activation+5.46e+00

Pos logit contributions
bis+5.129
uay+5.065
 Maher+4.323
isine+4.323
timer+4.264
Neg logit contributions
ropolitan-4.198
ascar-4.164
mph-4.090
mith-4.006
rolet-3.991
Tokenfield
Token ID3245
Feature activation+3.71e+00

Pos logit contributions
bis+3.227
uay+3.126
 Maher+2.632
MIT+2.604
prints+2.585
Neg logit contributions
ropolitan-4.364
ascar-4.331
mph-4.230
aned-4.215
mith-4.128
Token-
Token ID12
Feature activation+1.31e+00

Pos logit contributions
bis+2.746
uay+2.679
 Maher+2.332
MIT+2.301
isine+2.275
Neg logit contributions
ropolitan-2.463
ascar-2.429
mph-2.391
aned-2.343
mith-2.320
TokenBob
Token ID18861
Feature activation+1.98e+01

Pos logit contributions
bis+1.027
uay+1.004
 Maher+0.876
MIT+0.868
isine+0.863
Neg logit contributions
ropolitan-0.821
ascar-0.811
mph-0.798
aned-0.779
mith-0.775
Token Grant
Token ID12181
Feature activation+1.25e+01

Pos logit contributions
bis+13.691
uay+13.201
 Maher+12.894
 Rossi+12.268
 Labrador+11.743
Neg logit contributions
ascar-10.025
ropolitan-9.912
 suffice-9.700
 tempted-9.512
mph-9.323
Token-
Token ID12
Feature activation+2.42e+00

Pos logit contributions
bis+8.986
uay+8.696
 Maher+7.836
timer+7.367
MIT+7.349
Neg logit contributions
ropolitan-7.736
ascar-7.514
mph-7.493
rolet-7.324
Lex-7.278
TokenR
Token ID49
Feature activation+8.35e-01

Pos logit contributions
bis+1.895
uay+1.849
 Maher+1.616
MIT+1.611
isine+1.584
Neg logit contributions
ropolitan-1.510
ascar-1.482
mph-1.454
aned-1.424
mith-1.413
Tokenac
Token ID330
Feature activation+1.31e+00

Pos logit contributions
bis+0.706
uay+0.691
 Maher+0.610
MIT+0.606
isine+0.600
Neg logit contributions
ropolitan-0.471
ascar-0.464
mph-0.455
aned-0.443
mith-0.440
Tokenism
Token ID1042
Feature activation+1.17e+01

Pos logit contributions
bis+0.834
uay+0.811
 Maher+0.683
MIT+0.678
isine+0.668
Neg logit contributions
ropolitan-1.012
ascar-1.000
mph-0.986
aned-0.968
mith-0.963
Token to
Token ID284
Feature activation-7.26e-01

Pos logit contributions
bis+2.366
uay+2.301
 Maher+2.013
MIT+1.990
prints+1.968
Neg logit contributions
ropolitan-1.987
ascar-1.945
mph-1.904
aned-1.864
rolet-1.851
Token see
Token ID766
Feature activation+3.96e+00

Pos logit contributions
ropolitan+0.365
ascar+0.359
mph+0.356
aned+0.346
mith+0.345
Neg logit contributions
bis-0.651
uay-0.642
isine-0.568
 Maher-0.567
MIT-0.566
Token if
Token ID611
Feature activation+3.18e+00

Pos logit contributions
bis+2.886
uay+2.801
 Maher+2.449
MIT+2.405
prints+2.398
Neg logit contributions
ropolitan-2.688
ascar-2.634
mph-2.574
aned-2.540
rolet-2.521
Token the
Token ID262
Feature activation+7.65e+00

Pos logit contributions
bis+2.495
uay+2.419
 Maher+2.131
MIT+2.106
prints+2.080
Neg logit contributions
ropolitan-2.003
ascar-1.961
mph-1.921
aned-1.877
rolet-1.872
Token R
Token ID371
Feature activation+5.13e+00

Pos logit contributions
bis+5.666
uay+5.349
 Maher+4.823
 Labrador+4.682
MIT+4.661
Neg logit contributions
ropolitan-5.091
ascar-4.855
mph-4.807
rolet-4.692
Lex-4.643
TokenFI
Token ID11674
Feature activation+1.96e+01

Pos logit contributions
bis+3.140
uay+2.976
MIT+2.525
prints+2.473
timer+2.447
Neg logit contributions
ropolitan-4.161
ascar-4.029
rolet-3.939
mph-3.902
aned-3.877
Token is
Token ID318
Feature activation+1.45e+01

Pos logit contributions
bis+12.272
uay+10.777
 quo+10.449
prints+10.416
 mismatch+10.329
Neg logit contributions
ropolitan-12.618
ascar-11.774
rolet-11.727
mph-11.154
aned-11.121
Token affected
Token ID5676
Feature activation+4.18e+00

Pos logit contributions
bis+9.917
uay+9.227
 Maher+8.558
 Rossi+8.535
 Labrador+8.486
Neg logit contributions
ropolitan-9.477
ascar-8.868
rolet-8.463
mph-8.425
cture-8.232
Token.
Token ID13
Feature activation+3.43e+00

Pos logit contributions
bis+3.108
uay+2.998
 Maher+2.616
MIT+2.600
isine+2.567
Neg logit contributions
ropolitan-2.770
ascar-2.719
mph-2.675
aned-2.615
mith-2.594
Token Recon
Token ID23419
Feature activation-4.08e-01

Pos logit contributions
bis+2.603
uay+2.512
 Maher+2.218
MIT+2.192
timer+2.157
Neg logit contributions
ropolitan-2.245
ascar-2.199
mph-2.153
aned-2.112
rolet-2.101
Tokennect
Token ID1606
Feature activation+6.16e+00

Pos logit contributions
ropolitan+0.272
ascar+0.267
mph+0.264
mith+0.256
aned+0.256
Neg logit contributions
bis-0.301
uay-0.295
 Maher-0.256
isine-0.252
MIT-0.251
Tokenkm
Token ID13276
Feature activation-1.31e+00

Pos logit contributions
bis+4.016
uay+3.890
 Maher+3.424
MIT+3.407
isine+3.369
Neg logit contributions
ropolitan-2.917
ascar-2.890
rolet-2.749
mph-2.733
aned-2.728
Token (
Token ID357
Feature activation-4.52e-01

Pos logit contributions
ropolitan+0.732
ascar+0.722
mph+0.715
aned+0.697
rolet+0.683
Neg logit contributions
bis-1.104
uay-1.091
 Maher-0.956
MIT-0.955
prints-0.947
Token30
Token ID1270
Feature activation+4.20e-01

Pos logit contributions
ropolitan+0.259
ascar+0.255
mph+0.254
aned+0.246
mith+0.244
Neg logit contributions
bis-0.375
uay-0.368
 Maher-0.325
isine-0.321
MIT-0.321
Token miles
Token ID4608
Feature activation-5.36e+00

Pos logit contributions
bis+0.451
uay+0.443
 Maher+0.405
MIT+0.402
isine+0.399
Neg logit contributions
ropolitan-0.141
mph-0.138
ascar-0.136
aned-0.127
mith-0.125
Token)
Token ID8
Feature activation+3.31e-01

Pos logit contributions
ropolitan+3.079
mph+3.039
ascar+2.965
mith+2.894
 ►+2.888
Neg logit contributions
bis-4.346
uay-4.257
�醒-3.881
icter-3.861
isine-3.815
Token from
Token ID422
Feature activation+1.95e+01

Pos logit contributions
bis+0.274
uay+0.268
 Maher+0.236
MIT+0.236
isine+0.233
Neg logit contributions
ropolitan-0.191
ascar-0.188
mph-0.186
aned-0.181
mith-0.179
Token the
Token ID262
Feature activation+1.09e+01

Pos logit contributions
bis+11.431
uay+10.660
 Maher+10.498
 Bash+10.141
 Labrador+9.972
Neg logit contributions
ascar-12.605
ropolitan-12.429
rolet-12.158
Lex-12.124
weekly-11.760
Token central
Token ID4318
Feature activation+1.26e+01

Pos logit contributions
bis+7.239
uay+6.819
 Maher+6.313
 Labrador+6.085
 Bash+5.754
Neg logit contributions
ropolitan-7.737
ascar-7.562
mith-7.293
rolet-7.258
mph-7.182
Token city
Token ID1748
Feature activation+1.35e+01

Pos logit contributions
bis+8.557
uay+7.800
 Maher+7.394
 Labrador+7.300
 quo+6.799
Neg logit contributions
ropolitan-8.554
ascar-8.523
rolet-8.166
mph-8.084
mith-7.989
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
bis+8.195
uay+7.506
 Maher+7.026
 Labrador+6.612
 quo+6.536
Neg logit contributions
ascar-9.912
ropolitan-9.650
rolet-9.340
mph-9.275
Lex-9.149
Token B
Token ID347
Feature activation+1.14e+01

Pos logit contributions
bis+8.579
uay+7.922
 Maher+7.689
 Labrador+7.203
 Bash+7.198
Neg logit contributions
ascar-8.953
ropolitan-8.815
rolet-8.515
Lex-8.334
weekly-8.279
Token New
Token ID968
Feature activation+1.96e+00

Pos logit contributions
ropolitan+2.100
ascar+2.023
mph+2.019
mith+1.975
aned+1.975
Neg logit contributions
bis-3.052
uay-2.983
isine-2.629
MIT-2.592
timer-2.587
Token England
Token ID4492
Feature activation+2.91e-01

Pos logit contributions
bis+1.368
uay+1.332
 Maher+1.142
MIT+1.133
isine+1.120
Neg logit contributions
ropolitan-1.399
ascar-1.381
mph-1.360
aned-1.333
mith-1.326
Token,
Token ID11
Feature activation-1.99e+00

Pos logit contributions
bis+0.224
uay+0.219
MIT+0.189
 Maher+0.189
isine+0.187
Neg logit contributions
ropolitan-0.187
ascar-0.184
mph-0.180
aned-0.177
mith-0.176
Token according
Token ID1864
Feature activation+2.47e+00

Pos logit contributions
ropolitan+1.174
ascar+1.147
mph+1.137
aned+1.108
mith+1.107
Neg logit contributions
bis-1.625
uay-1.587
isine-1.386
MIT-1.380
prints-1.371
Token to
Token ID284
Feature activation+8.84e-01

Pos logit contributions
bis+1.849
uay+1.808
 Maher+1.589
MIT+1.568
 Labrador+1.534
Neg logit contributions
ropolitan-1.623
ascar-1.606
mph-1.564
aned-1.543
rolet-1.529
Token Mon
Token ID2892
Feature activation+1.93e+01

Pos logit contributions
bis+0.716
uay+0.700
 Maher+0.613
MIT+0.609
isine+0.604
Neg logit contributions
ropolitan-0.530
ascar-0.521
mph-0.512
aned-0.500
mith-0.496
Tokennat
Token ID32353
Feature activation+8.27e-01

Pos logit contributions
bis+6.314
uay+5.183
ité+3.798
hum+3.778
isine+3.666
Neg logit contributions
GGGGGGGG-18.399
 ED-17.823
ropolitan-17.785
-17.640
 suffice-17.637
Token
Token ID447
Feature activation+3.39e+00

Pos logit contributions
bis+0.635
uay+0.621
 Maher+0.539
MIT+0.537
isine+0.530
Neg logit contributions
ropolitan-0.532
ascar-0.523
mph-0.514
aned-0.502
mith-0.500
Token
Token ID247
Feature activation+3.31e+00

Pos logit contributions
bis+2.553
uay+2.514
 Maher+2.185
MIT+2.166
isine+2.120
Neg logit contributions
ropolitan-2.199
ascar-2.172
mph-2.138
aned-2.095
rolet-2.077
Tokens
Token ID82
Feature activation-1.18e+00

Pos logit contributions
bis+1.896
uay+1.831
 Maher+1.507
MIT+1.496
isine+1.473
Neg logit contributions
ropolitan-2.758
ascar-2.736
mph-2.689
aned-2.656
rolet-2.646
Token analysis
Token ID3781
Feature activation-4.76e+00

Pos logit contributions
ropolitan+0.709
ascar+0.690
mph+0.682
mith+0.665
aned+0.662
Neg logit contributions
bis-0.953
uay-0.943
 Maher-0.818
MIT-0.812
isine-0.811
Token D
Token ID360
Feature activation-8.74e-01

Pos logit contributions
ropolitan+1.089
ascar+1.083
mph+1.073
mith+1.044
 ED+1.042
Neg logit contributions
bis-1.481
uay-1.446
isine-1.270
MIT-1.243
prints-1.238
TokenIV
Token ID3824
Feature activation-1.90e+00

Pos logit contributions
ropolitan+0.406
ascar+0.406
mph+0.393
aned+0.381
mith+0.374
Neg logit contributions
bis-0.823
uay-0.809
 Maher-0.724
MIT-0.718
isine-0.711
TokenIDE
Token ID14114
Feature activation+4.00e+00

Pos logit contributions
ropolitan+1.044
ascar+1.035
mph+1.019
aned+0.984
Lex+0.975
Neg logit contributions
bis-1.617
uay-1.587
 Maher-1.406
isine-1.381
 Labrador-1.371
Token AND
Token ID5357
Feature activation+8.42e+00

Pos logit contributions
bis+3.207
uay+3.127
 Maher+2.774
MIT+2.749
prints+2.702
Neg logit contributions
ropolitan-2.408
ascar-2.346
mph-2.316
aned-2.250
rolet-2.234
Token CON
Token ID7102
Feature activation+2.00e+01

Pos logit contributions
bis+5.727
uay+5.505
MIT+4.950
 Maher+4.874
 Labrador+4.795
Neg logit contributions
ropolitan-5.852
ascar-5.705
mph-5.640
aned-5.542
mith-5.481
TokenQU
Token ID10917
Feature activation+1.93e+01

Pos logit contributions
MIT+8.179
bis+8.098
uay+7.394
SIGN+6.354
vier+6.123
Neg logit contributions
ropolitan-16.836
aned-16.061
ascar-15.687
 tempted-15.547
mph-15.442
TokenER
Token ID1137
Feature activation+5.53e-01

Pos logit contributions
MIT+5.073
bis+4.682
uay+4.645
IRO+3.594
timer+3.157
Neg logit contributions
ropolitan-18.927
ascar-18.153
rolet-18.117
 tempted-17.989
aned-17.919
Token was
Token ID373
Feature activation-9.16e-01

Pos logit contributions
bis+0.430
uay+0.420
 Maher+0.365
MIT+0.362
isine+0.359
Neg logit contributions
ropolitan-0.348
ascar-0.344
mph-0.338
aned-0.332
mith-0.330
Token about
Token ID546
Feature activation-2.69e+00

Pos logit contributions
ropolitan+0.548
ascar+0.546
mph+0.540
aned+0.530
mith+0.525
Neg logit contributions
bis-0.736
uay-0.715
MIT-0.623
isine-0.618
 Maher-0.616
Token introducing
Token ID16118
Feature activation-9.53e-01

Pos logit contributions
ascar+1.497
ropolitan+1.492
mph+1.474
 ED+1.437
aned+1.435
Neg logit contributions
bis-2.262
uay-2.204
MIT-1.944
isine-1.922
 Maher-1.896
Token the
Token ID262
Feature activation+1.41e+00

Pos logit contributions
ropolitan+0.537
ascar+0.530
mph+0.522
aned+0.510
mith+0.506
Neg logit contributions
bis-0.804
uay-0.783
MIT-0.690
isine-0.685
 Maher-0.681
Token.
Token ID13
Feature activation+6.84e+00

Pos logit contributions
bis+0.907
uay+0.889
 Maher+0.775
MIT+0.771
isine+0.763
Neg logit contributions
ropolitan-0.719
ascar-0.709
mph-0.697
aned-0.683
mith-0.678
Token
Token ID198
Feature activation+3.74e+00

Pos logit contributions
bis+4.758
uay+4.546
 Maher+4.057
MIT+3.961
 Labrador+3.935
Neg logit contributions
ropolitan-4.764
ascar-4.747
mph-4.622
aned-4.582
rolet-4.497
Token
Token ID198
Feature activation+7.29e+00

Pos logit contributions
bis+2.381
uay+2.297
 Maher+1.952
MIT+1.946
prints+1.895
Neg logit contributions
ropolitan-2.890
ascar-2.847
rolet-2.756
mph-2.755
aned-2.742
TokenWhen
Token ID2215
Feature activation+2.43e+00

Pos logit contributions
bis+5.456
uay+5.150
MIT+4.717
prints+4.498
timer+4.427
Neg logit contributions
ropolitan-4.830
ascar-4.732
rolet-4.531
mph-4.529
aned-4.499
Token interest
Token ID1393
Feature activation+3.89e+00

Pos logit contributions
bis+1.935
uay+1.888
 Maher+1.656
MIT+1.643
isine+1.625
Neg logit contributions
ropolitan-1.488
ascar-1.467
mph-1.439
aned-1.406
mith-1.397
Token rates
Token ID3965
Feature activation+1.92e+01

Pos logit contributions
bis+2.884
uay+2.792
 Maher+2.439
MIT+2.412
isine+2.404
Neg logit contributions
ropolitan-2.566
ascar-2.534
mph-2.476
rolet-2.428
aned-2.422
Token rise
Token ID4485
Feature activation+7.00e+00

Pos logit contributions
bis+11.844
uay+10.529
 quo+10.366
 mismatch+9.696
 Maher+9.685
Neg logit contributions
ropolitan-12.150
ascar-11.911
rolet-11.827
jew-11.339
Lex-11.288
Token,
Token ID11
Feature activation+4.86e+00

Pos logit contributions
bis+4.887
uay+4.678
 Maher+4.121
MIT+4.050
 quo+4.017
Neg logit contributions
ropolitan-4.846
ascar-4.786
mph-4.687
rolet-4.589
aned-4.535
Token the
Token ID262
Feature activation+4.21e+00

Pos logit contributions
bis+3.796
uay+3.679
 Maher+3.264
MIT+3.211
prints+3.184
Neg logit contributions
ropolitan-3.006
ascar-2.976
mph-2.911
aned-2.830
rolet-2.826
Token cost
Token ID1575
Feature activation+1.16e+01

Pos logit contributions
bis+3.340
uay+3.253
 Maher+2.882
MIT+2.829
 Labrador+2.809
Neg logit contributions
ropolitan-2.567
ascar-2.534
mph-2.476
aned-2.401
rolet-2.389
Token of
Token ID286
Feature activation+2.30e+00

Pos logit contributions
bis+7.123
uay+6.746
 Maher+5.952
prints+5.947
 quo+5.930
Neg logit contributions
ropolitan-8.417
ascar-8.293
mph-8.080
rolet-7.921
aned-7.909
Token claimed
Token ID4752
Feature activation+7.69e+00

Pos logit contributions
ropolitan+1.025
ascar+1.011
mph+1.008
aned+0.992
mith+0.975
Neg logit contributions
bis-1.524
uay-1.501
MIT-1.319
isine-1.305
prints-1.290
Token the
Token ID262
Feature activation-1.66e-01

Pos logit contributions
bis+5.601
uay+5.484
 Maher+4.976
 Labrador+4.785
 quo+4.714
Neg logit contributions
ropolitan-5.021
ascar-4.953
mph-4.760
rolet-4.744
mith-4.674
Token lives
Token ID3160
Feature activation+3.19e+00

Pos logit contributions
ropolitan+0.091
ascar+0.090
mph+0.089
aned+0.087
mith+0.086
Neg logit contributions
bis-0.143
uay-0.139
MIT-0.123
 Maher-0.122
isine-0.122
Token of
Token ID286
Feature activation+9.87e+00

Pos logit contributions
bis+2.355
uay+2.292
 Maher+2.000
MIT+1.971
isine+1.948
Neg logit contributions
ropolitan-2.139
ascar-2.104
mph-2.065
aned-2.029
rolet-2.008
Token over
Token ID625
Feature activation+9.38e+00

Pos logit contributions
bis+6.785
uay+6.729
 Maher+6.246
 Labrador+5.858
 quo+5.742
Neg logit contributions
ropolitan-6.663
ascar-6.503
mph-6.237
rolet-6.223
cture-6.099
Token 1
Token ID352
Feature activation+1.92e+01

Pos logit contributions
bis+6.189
uay+5.827
 Maher+5.284
prints+4.982
MIT+4.948
Neg logit contributions
ropolitan-6.739
ascar-6.664
rolet-6.314
mph-6.292
aned-6.221
Token million
Token ID1510
Feature activation+6.24e+00

Pos logit contributions
bis+9.710
uay+8.745
 Maher+7.654
MIT+7.570
 Labrador+7.206
Neg logit contributions
ropolitan-14.534
ascar-14.227
rolet-13.750
aned-13.412
 suffice-13.395
Token Iraqis
Token ID34956
Feature activation+3.81e+00

Pos logit contributions
bis+4.457
uay+4.304
 Maher+3.855
 Labrador+3.750
 quo+3.696
Neg logit contributions
ropolitan-4.251
ascar-4.178
mph-4.018
rolet-3.986
mith-3.946
Token.
Token ID13
Feature activation+4.94e+00

Pos logit contributions
bis+2.855
uay+2.774
 Maher+2.439
MIT+2.390
isine+2.381
Neg logit contributions
ropolitan-2.503
ascar-2.460
mph-2.404
aned-2.354
rolet-2.336
Token
Token ID198
Feature activation+7.73e-01

Pos logit contributions
bis+3.574
uay+3.465
 Maher+3.082
MIT+2.991
 Labrador+2.973
Neg logit contributions
ropolitan-3.344
ascar-3.310
mph-3.235
aned-3.190
mith-3.159
Token
Token ID198
Feature activation+5.97e+00

Pos logit contributions
bis+0.537
uay+0.522
 Maher+0.448
MIT+0.445
isine+0.437
Neg logit contributions
ropolitan-0.554
ascar-0.547
mph-0.536
aned-0.527
mith-0.523
Token.
Token ID13
Feature activation-2.22e+00

Pos logit contributions
ropolitan+1.518
ascar+1.510
mph+1.509
mith+1.456
aned+1.447
Neg logit contributions
bis-2.232
uay-2.199
MIT-1.914
 Maher-1.899
prints-1.890
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
ropolitan+1.314
ascar+1.304
mph+1.304
 ►+1.256
mith+1.253
Neg logit contributions
bis-1.766
uay-1.754
isine-1.525
prints-1.496
 Maher-1.494
Token
Token ID198
Feature activation-2.47e+00

Pos logit contributions
ropolitan+0.865
ascar+0.855
mph+0.849
mith+0.827
aned+0.826
Neg logit contributions
bis-0.923
uay-0.903
 Maher-0.777
isine-0.771
MIT-0.770
TokenThe
Token ID464
Feature activation+3.27e+00

Pos logit contributions
mph+1.487
ropolitan+1.480
ascar+1.466
Lex+1.440
mith+1.425
Neg logit contributions
bis-1.934
uay-1.922
 Maher-1.699
 Labrador-1.658
isine-1.655
Token door
Token ID3420
Feature activation+8.30e+00

Pos logit contributions
bis+2.584
uay+2.520
 Maher+2.204
MIT+2.186
isine+2.168
Neg logit contributions
ropolitan-2.021
ascar-1.988
mph-1.938
aned-1.904
rolet-1.892
Tokenbell
Token ID7923
Feature activation+1.91e+01

Pos logit contributions
bis+5.329
uay+5.155
 Maher+4.417
MIT+4.362
timer+4.303
Neg logit contributions
ropolitan-6.201
ascar-6.142
rolet-5.997
aned-5.879
ruction-5.763
Token rang
Token ID28077
Feature activation+3.80e+00

Pos logit contributions
bis+9.397
 quo+8.245
uay+8.171
prints+8.057
 Rossi+7.967
Neg logit contributions
ascar-14.489
rolet-14.358
ropolitan-13.882
cture-13.113
aned-12.897
Token while
Token ID981
Feature activation-2.90e+00

Pos logit contributions
bis+2.829
uay+2.743
 Maher+2.407
MIT+2.363
prints+2.347
Neg logit contributions
ascar-2.500
ropolitan-2.499
mph-2.396
aned-2.364
rolet-2.359
Token I
Token ID314
Feature activation+2.40e+00

Pos logit contributions
ropolitan+1.579
mph+1.548
ascar+1.534
mith+1.487
 ED+1.479
Neg logit contributions
bis-2.471
uay-2.434
MIT-2.152
isine-2.108
 Maher-2.099
Token was
Token ID373
Feature activation+3.05e+00

Pos logit contributions
bis+1.901
uay+1.855
 Maher+1.624
MIT+1.607
isine+1.595
Neg logit contributions
ropolitan-1.479
ascar-1.460
mph-1.426
aned-1.392
rolet-1.386
Token preparing
Token ID10629
Feature activation+4.59e+00

Pos logit contributions
bis+2.407
uay+2.357
 Maher+2.070
MIT+2.030
isine+2.030
Neg logit contributions
ropolitan-1.879
ascar-1.855
mph-1.796
rolet-1.764
aned-1.761
Token Wat
Token ID12242
Feature activation-3.73e-01

Pos logit contributions
bis+5.617
uay+5.437
 Maher+4.895
 Labrador+4.798
prints+4.739
Neg logit contributions
ropolitan-4.407
ascar-4.250
mph-4.147
rolet-4.060
aned-4.047
Tokenerville
Token ID33487
Feature activation+5.91e+00

Pos logit contributions
ropolitan+0.228
ascar+0.224
mph+0.220
aned+0.216
mith+0.214
Neg logit contributions
bis-0.298
uay-0.289
 Maher-0.255
MIT-0.253
isine-0.250
Token Hotel
Token ID12696
Feature activation+6.39e+00

Pos logit contributions
bis+4.635
uay+4.534
 Maher+3.961
MIT+3.913
 Labrador+3.887
Neg logit contributions
ropolitan-3.623
ascar-3.539
mph-3.465
rolet-3.416
aned-3.400
Token (
Token ID357
Feature activation+1.58e+00

Pos logit contributions
bis+4.692
uay+4.558
 Maher+3.974
MIT+3.909
 Labrador+3.873
Neg logit contributions
ropolitan-4.227
ascar-4.138
mph-4.050
rolet-3.991
aned-3.974
Tokennow
Token ID2197
Feature activation+8.78e+00

Pos logit contributions
bis+1.235
uay+1.205
 Maher+1.051
MIT+1.047
isine+1.033
Neg logit contributions
ropolitan-0.991
ascar-0.976
mph-0.957
aned-0.937
mith-0.930
Token the
Token ID262
Feature activation+1.90e+01

Pos logit contributions
bis+6.747
uay+6.516
 Maher+5.900
MIT+5.729
 Labrador+5.642
Neg logit contributions
ropolitan-5.304
ascar-5.282
mph-5.046
rolet-5.009
mith-4.916
Token Wat
Token ID12242
Feature activation+3.14e+00

Pos logit contributions
bis+13.453
uay+13.311
 Maher+12.210
 Rossi+11.853
MIT+11.783
Neg logit contributions
ropolitan-9.750
ascar-9.586
rolet-9.209
mph-8.959
ruction-8.862
Tokenerville
Token ID33487
Feature activation+1.15e+01

Pos logit contributions
bis+2.518
uay+2.473
 Maher+2.163
MIT+2.157
isine+2.130
Neg logit contributions
ropolitan-1.876
ascar-1.858
mph-1.820
aned-1.787
mith-1.762
Token Tavern
Token ID32693
Feature activation+1.29e+01

Pos logit contributions
bis+8.565
uay+8.405
 Maher+7.346
MIT+7.279
 Labrador+7.151
Neg logit contributions
ropolitan-6.906
ascar-6.823
rolet-6.675
mph-6.607
aned-6.543
Token)
Token ID8
Feature activation+7.06e+00

Pos logit contributions
bis+8.074
uay+7.681
 Maher+6.667
MIT+6.572
isine+6.566
Neg logit contributions
ascar-8.951
ropolitan-8.878
rolet-8.798
mph-8.755
aned-8.569
Token that
Token ID326
Feature activation+5.74e+00

Pos logit contributions
bis+5.208
uay+5.074
 Maher+4.423
MIT+4.341
isine+4.294
Neg logit contributions
ropolitan-4.646
ascar-4.514
mph-4.428
aned-4.335
rolet-4.321
Tokenrat
Token ID10366
Feature activation+1.08e+01

Pos logit contributions
bis+5.316
uay+5.070
isine+4.404
MIT+4.385
timer+4.363
Neg logit contributions
ropolitan-4.195
ascar-4.166
mith-4.074
aned-4.008
mph-3.997
Tokenrice
Token ID20970
Feature activation+5.56e+00

Pos logit contributions
bis+8.128
uay+7.829
ité+6.883
MIT+6.836
 quo+6.802
Neg logit contributions
ascar-6.373
ropolitan-6.362
mith-6.343
mph-6.295
aned-6.244
Token,
Token ID11
Feature activation+8.25e+00

Pos logit contributions
bis+4.376
uay+4.238
MIT+3.741
 Maher+3.741
isine+3.663
Neg logit contributions
ropolitan-3.392
ascar-3.320
mph-3.277
aned-3.209
mith-3.187
TokenA
Token ID32
Feature activation+4.69e+00

Pos logit contributions
bis+6.432
uay+6.211
 Maher+5.605
 Labrador+5.516
 quo+5.503
Neg logit contributions
ropolitan-4.974
ascar-4.860
mph-4.739
mith-4.615
aned-4.601
Tokenu
Token ID84
Feature activation+1.56e+00

Pos logit contributions
bis+3.722
uay+3.602
 Maher+3.148
MIT+3.125
isine+3.115
Neg logit contributions
ropolitan-2.881
ascar-2.827
mph-2.772
aned-2.718
mith-2.691
Token cr
Token ID1067
Feature activation+1.89e+01

Pos logit contributions
bis+1.243
uay+1.214
 Maher+1.064
MIT+1.057
isine+1.047
Neg logit contributions
ropolitan-0.948
ascar-0.934
mph-0.917
aned-0.896
mith-0.890
Tokené
Token ID2634
Feature activation+6.57e+00

Pos logit contributions
bis+12.368
uay+12.072
ieu+10.314
isine+10.224
ité+9.960
Neg logit contributions
ropolitan-11.666
mith-10.632
rolet-10.615
mph-10.571
ascar-10.550
Tokenp
Token ID79
Feature activation+3.31e+00

Pos logit contributions
bis+4.741
uay+4.588
isine+3.931
MIT+3.907
 Maher+3.903
Neg logit contributions
ropolitan-4.452
ascar-4.323
mph-4.213
mith-4.194
aned-4.172
Tokenusc
Token ID16241
Feature activation+3.99e+00

Pos logit contributions
bis+2.529
uay+2.462
 Maher+2.135
isine+2.120
MIT+2.117
Neg logit contributions
ropolitan-2.130
ascar-2.080
mph-2.052
aned-2.013
mith-2.010
Tokenule
Token ID2261
Feature activation+9.18e+00

Pos logit contributions
bis+2.792
uay+2.745
 Maher+2.333
MIT+2.314
isine+2.309
Neg logit contributions
ropolitan-2.809
ascar-2.772
mph-2.716
mith-2.670
aned-2.656
Token de
Token ID390
Feature activation+6.40e+00

Pos logit contributions
bis+7.116
uay+6.834
 Maher+6.054
MIT+6.000
 quo+5.959
Neg logit contributions
ropolitan-5.528
ascar-5.308
mph-5.226
mith-5.146
rolet-5.145
Token series
Token ID2168
Feature activation-5.90e+00

Pos logit contributions
ascar+4.340
mph+4.273
ropolitan+4.233
 ED+4.058
weekly+4.043
Neg logit contributions
bis-6.237
uay-6.131
MIT-5.488
�醒-5.440
isine-5.438
Token.
Token ID13
Feature activation-8.47e-01

Pos logit contributions
ascar+3.256
ropolitan+3.207
mph+3.201
 ED+3.101
Lex+3.085
Neg logit contributions
bis-4.859
uay-4.765
isine-4.243
MIT-4.211
timer-4.141
Token
Token ID198
Feature activation-3.27e+00

Pos logit contributions
ropolitan+0.544
ascar+0.539
mph+0.534
aned+0.518
rolet+0.517
Neg logit contributions
bis-0.641
uay-0.630
isine-0.550
MIT-0.543
 Maher-0.539
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
ropolitan+2.047
mph+2.044
ascar+2.022
mith+1.985
aned+1.964
Neg logit contributions
bis-2.482
uay-2.444
icter-2.168
isine-2.137
�醒-2.131
TokenThe
Token ID464
Feature activation-4.01e+00

Pos logit contributions
mph+1.169
ropolitan+1.156
ascar+1.155
Lex+1.142
mith+1.125
Neg logit contributions
bis-1.711
uay-1.692
 Maher-1.506
isine-1.496
 Labrador-1.467
Token high
Token ID1029
Feature activation-2.12e+01

Pos logit contributions
mph+2.303
ascar+2.284
ropolitan+2.269
aned+2.227
Lex+2.220
Neg logit contributions
bis-3.211
uay-3.160
isine-2.802
MIT-2.794
timer-2.748
Token-
Token ID12
Feature activation-1.85e+01

Pos logit contributions
mph+8.269
 ED+8.079
Lex+7.696
 Scion+7.696
 IM+7.579
Neg logit contributions
bis-16.475
uay-16.372
MIT-15.168
isine-15.109
�醒-14.781
Tokenoutput
Token ID22915
Feature activation-1.11e+01

Pos logit contributions
mph+10.028
Lex+9.374
weekly+9.283
mith+8.908
jew+8.871
Neg logit contributions
uay-12.644
bis-12.404
 Maher-12.377
�醒-11.758
 quo-11.543
Token 3
Token ID513
Feature activation-4.03e+00

Pos logit contributions
 ED+5.594
mph+5.495
 Scion+5.466
Lex+5.446
 Lith+5.369
Neg logit contributions
uay-9.018
bis-8.811
isine-8.099
MIT-8.027
icter-7.991
Token.
Token ID13
Feature activation-2.63e+00

Pos logit contributions
mph+2.260
ropolitan+2.236
ascar+2.219
mith+2.161
Lex+2.159
Neg logit contributions
bis-3.333
uay-3.289
isine-2.901
 Maher-2.889
icter-2.862
Token5
Token ID20
Feature activation-7.93e+00

Pos logit contributions
mph+1.445
ropolitan+1.444
ascar+1.441
mith+1.378
Lex+1.369
Neg logit contributions
bis-2.218
uay-2.194
 Maher-1.938
isine-1.929
MIT-1.913
Token few
Token ID1178
Feature activation-4.56e+00

Pos logit contributions
ropolitan+1.838
ascar+1.832
mph+1.808
aned+1.765
 ED+1.743
Neg logit contributions
bis-2.623
uay-2.540
MIT-2.227
isine-2.214
 Maher-2.195
Token people
Token ID661
Feature activation-2.06e+00

Pos logit contributions
ropolitan+2.484
ascar+2.476
mph+2.473
aned+2.415
 ED+2.390
Neg logit contributions
bis-3.889
uay-3.752
isine-3.323
MIT-3.307
 Maher-3.231
Token on
Token ID319
Feature activation-4.92e+00

Pos logit contributions
ropolitan+1.145
ascar+1.137
mph+1.134
aned+1.102
mith+1.093
Neg logit contributions
bis-1.746
uay-1.696
MIT-1.498
isine-1.480
 Maher-1.467
Token Donald
Token ID3759
Feature activation-4.68e+00

Pos logit contributions
ropolitan+2.451
ascar+2.440
mph+2.404
aned+2.336
 ED+2.335
Neg logit contributions
bis-4.424
uay-4.305
isine-3.799
MIT-3.785
prints-3.718
Token Trump
Token ID1301
Feature activation-1.09e+01

Pos logit contributions
ropolitan+1.501
ascar+1.483
mph+1.459
aned+1.369
 ED+1.362
Neg logit contributions
bis-4.984
uay-4.941
isine-4.459
MIT-4.412
icter-4.389
Token's
Token ID338
Feature activation-2.07e+01

Pos logit contributions
ascar+4.400
mph+4.322
ropolitan+4.215
 ED+4.093
aned+4.012
Neg logit contributions
bis-10.076
uay-10.000
MIT-9.046
prints-8.840
�醒-8.808
Token short
Token ID1790
Feature activation-9.18e+00

Pos logit contributions
 ED+10.190
ascar+9.625
 div+9.506
 twe+9.431
 demons+9.424
Neg logit contributions
bis-15.021
uay-14.374
�醒-13.826
isine-13.050
prints-13.029
Token list
Token ID1351
Feature activation-7.07e+00

Pos logit contributions
ascar+3.737
mph+3.604
aned+3.575
ropolitan+3.532
 ED+3.493
Neg logit contributions
uay-8.693
bis-8.685
MIT-7.726
isine-7.724
 Maher-7.651
Token to
Token ID284
Feature activation-5.27e+00

Pos logit contributions
ropolitan+3.589
ascar+3.552
mph+3.507
 ►+3.447
mith+3.436
Neg logit contributions
bis-6.051
uay-5.912
prints-5.189
MIT-5.155
mbuds-5.110
Token be
Token ID307
Feature activation-1.12e+01

Pos logit contributions
ascar+2.614
ropolitan+2.599
aned+2.582
mph+2.570
 ED+2.523
Neg logit contributions
bis-4.631
uay-4.558
prints-4.049
MIT-3.995
icter-3.983
Token running
Token ID2491
Feature activation+3.22e+00

Pos logit contributions
 ED+5.119
 tempted+5.091
aned+5.015
 Mn+5.009
ascar+4.941
Neg logit contributions
bis-9.944
uay-9.622
MIT-8.720
isine-8.437
icter-8.408
Token give
Token ID1577
Feature activation-3.50e+00

Pos logit contributions
ropolitan+0.231
ascar+0.227
mph+0.223
aned+0.219
mith+0.217
Neg logit contributions
bis-0.290
uay-0.283
 Maher-0.248
MIT-0.246
isine-0.244
Token us
Token ID514
Feature activation-6.46e+00

Pos logit contributions
ropolitan+1.625
ascar+1.597
mph+1.572
aned+1.527
mith+1.519
Neg logit contributions
bis-3.261
uay-3.189
isine-2.862
 Maher-2.841
MIT-2.838
Token back
Token ID736
Feature activation-1.06e+01

Pos logit contributions
ascar+2.553
mph+2.508
aned+2.494
 ED+2.486
mith+2.459
Neg logit contributions
bis-6.379
uay-6.039
icter-5.688
isine-5.656
MIT-5.585
Token our
Token ID674
Feature activation-9.08e+00

Pos logit contributions
 ED+3.411
ropolitan+3.397
 ►+3.364
ascar+3.302
mph+3.276
Neg logit contributions
bis-10.991
uay-10.476
icter-10.094
isine-9.821
MIT-9.708
Token rights
Token ID2489
Feature activation-8.95e+00

Pos logit contributions
ascar+3.656
 ED+3.639
ropolitan+3.563
rous+3.493
mph+3.488
Neg logit contributions
bis-8.641
uay-8.496
icter-7.862
�醒-7.781
timer-7.711
Token.
Token ID13
Feature activation-1.96e+01

Pos logit contributions
ropolitan+4.285
mith+4.246
ascar+4.145
mph+4.138
 ►+4.135
Neg logit contributions
bis-7.821
uay-7.638
isine-6.699
prints-6.647
MIT-6.613
Token We
Token ID775
Feature activation-1.23e+01

Pos logit contributions
 ►+8.729
ascar+8.256
ropolitan+7.925
 ED+7.896
 IM+7.781
Neg logit contributions
bis-15.398
uay-15.229
isine-13.650
prints-13.317
timer-13.090
Token need
Token ID761
Feature activation-1.53e+01

Pos logit contributions
mith+2.802
 ►+2.627
ascar+2.588
 ED+2.577
 IM+2.566
Neg logit contributions
uay-13.547
bis-13.369
�醒-12.430
isine-12.285
icter-12.215
Token the
Token ID262
Feature activation-9.63e+00

Pos logit contributions
 ED+5.218
 IM+5.009
ascar+4.954
mph+4.805
ropolitan+4.789
Neg logit contributions
bis-14.055
uay-13.942
icter-13.827
�醒-13.751
isine-13.097
Token Travel
Token ID13524
Feature activation+7.54e-01

Pos logit contributions
ascar+4.343
ropolitan+4.338
mph+4.238
mith+4.129
 ED+4.116
Neg logit contributions
uay-8.497
bis-8.478
MIT-7.499
isine-7.404
 Labrador-7.394
Token Ban
Token ID10274
Feature activation-7.51e+00

Pos logit contributions
bis+0.702
uay+0.688
 Maher+0.616
MIT+0.611
isine+0.603
Neg logit contributions
ropolitan-0.363
ascar-0.354
mph-0.347
aned-0.337
rolet-0.333
Token of
Token ID286
Feature activation-1.02e+01

Pos logit contributions
ropolitan+1.117
ascar+1.104
mph+1.090
aned+1.065
mith+1.063
Neg logit contributions
bis-1.381
uay-1.348
MIT-1.175
 Maher-1.173
isine-1.165
Token terrain
Token ID15510
Feature activation-2.78e+00

Pos logit contributions
mph+5.321
 ED+5.243
ascar+5.089
 Scion+4.987
aned+4.964
Neg logit contributions
bis-8.548
uay-8.207
MIT-7.626
isine-7.438
icter-7.411
Token at
Token ID379
Feature activation-5.50e+00

Pos logit contributions
ropolitan+1.711
mph+1.698
ascar+1.697
aned+1.637
mith+1.628
Neg logit contributions
bis-2.174
uay-2.121
MIT-1.861
isine-1.836
 Maher-1.835
Token low
Token ID1877
Feature activation-1.82e+01

Pos logit contributions
ropolitan+3.067
mph+3.040
ascar+2.976
 ED+2.919
aned+2.909
Neg logit contributions
bis-4.580
uay-4.451
MIT-4.037
isine-3.975
timer-3.888
Token and
Token ID290
Feature activation-8.83e+00

Pos logit contributions
mph+8.357
 ED+7.815
ascar+7.510
rous+7.355
ropolitan+7.260
Neg logit contributions
bis-15.040
uay-14.284
MIT-13.725
isine-13.337
mbuds-13.046
Token high
Token ID1029
Feature activation-1.92e+01

Pos logit contributions
mph+4.336
ropolitan+4.135
aned+4.048
ascar+4.026
 ED+3.962
Neg logit contributions
bis-7.867
uay-7.761
MIT-7.075
isine-6.951
icter-6.848
Token speeds
Token ID12055
Feature activation-6.31e-01

Pos logit contributions
mph+8.173
 ED+7.825
ascar+7.110
rous+7.097
 depths+7.053
Neg logit contributions
bis-16.225
uay-15.374
MIT-14.861
isine-14.455
icter-14.315
Token
Token ID784
Feature activation-2.89e+00

Pos logit contributions
ropolitan+0.373
ascar+0.369
mph+0.365
mith+0.356
aned+0.355
Neg logit contributions
bis-0.515
uay-0.503
MIT-0.442
 Maher-0.441
isine-0.434
Token both
Token ID1111
Feature activation-5.59e+00

Pos logit contributions
ropolitan+1.705
mph+1.694
ascar+1.688
aned+1.649
mith+1.623
Neg logit contributions
bis-2.313
uay-2.266
MIT-1.985
isine-1.983
 Maher-1.968
Token on
Token ID319
Feature activation-5.95e+00

Pos logit contributions
mph+3.133
ropolitan+3.091
ascar+3.059
aned+3.037
 ED+3.022
Neg logit contributions
bis-4.621
uay-4.425
MIT-4.053
isine-4.042
�醒-3.917
Token-
Token ID12
Feature activation-9.34e-01

Pos logit contributions
ropolitan+3.266
mph+3.218
ascar+3.215
aned+3.162
 ED+3.064
Neg logit contributions
bis-4.949
uay-4.803
MIT-4.399
isine-4.348
 Maher-4.239
Token at
Token ID379
Feature activation-1.34e+01

Pos logit contributions
ropolitan+4.029
mith+3.941
ascar+3.925
mph+3.883
aned+3.872
Neg logit contributions
bis-5.487
uay-5.321
MIT-4.800
isine-4.703
prints-4.683
Token West
Token ID2688
Feature activation-7.95e-01

Pos logit contributions
 ED+6.572
ropolitan+6.311
 ►+6.299
 IM+6.178
ascar+6.119
Neg logit contributions
bis-10.761
uay-10.694
timer-9.844
�醒-9.557
isine-9.517
Token Brom
Token ID31455
Feature activation-1.02e+00

Pos logit contributions
ropolitan+0.406
ascar+0.396
mph+0.391
mith+0.379
aned+0.379
Neg logit contributions
bis-0.711
uay-0.699
 Maher-0.621
MIT-0.620
isine-0.617
Tokenwich
Token ID11451
Feature activation-7.62e+00

Pos logit contributions
ropolitan+0.651
ascar+0.638
mph+0.627
mith+0.618
aned+0.615
Neg logit contributions
bis-0.787
uay-0.774
MIT-0.676
 Maher-0.676
isine-0.667
Token Albion
Token ID47995
Feature activation+1.14e-01

Pos logit contributions
ropolitan+2.390
mith+2.252
mph+2.214
ascar+2.201
 ►+2.157
Neg logit contributions
bis-8.045
uay-7.946
isine-7.372
MIT-7.261
timer-7.220
Token and
Token ID290
Feature activation-1.92e+01

Pos logit contributions
bis+0.088
uay+0.087
MIT+0.076
 Maher+0.075
isine+0.074
Neg logit contributions
ropolitan-0.071
ascar-0.070
mph-0.069
mith-0.068
aned-0.068
Token Stoke
Token ID36178
Feature activation+4.82e-02

Pos logit contributions
 ED+9.191
 Queens+8.782
 ►+8.673
mith+8.656
 tempted+8.569
Neg logit contributions
uay-13.569
bis-13.561
icter-12.908
�醒-12.793
isine-12.750
Token City
Token ID2254
Feature activation+1.54e+00

Pos logit contributions
bis+0.034
uay+0.033
 Maher+0.029
MIT+0.028
isine+0.028
Neg logit contributions
ropolitan-0.034
ascar-0.033
mph-0.033
aned-0.032
mith-0.032
Token achieved
Token ID8793
Feature activation-2.88e+00

Pos logit contributions
bis+1.177
uay+1.148
 Maher+0.999
MIT+0.991
isine+0.981
Neg logit contributions
ropolitan-0.991
ascar-0.978
mph-0.961
aned-0.940
mith-0.934
Token without
Token ID1231
Feature activation-3.41e+00

Pos logit contributions
ropolitan+1.711
ascar+1.674
mph+1.655
mith+1.618
aned+1.608
Neg logit contributions
bis-2.321
uay-2.286
MIT-2.008
 Maher-1.971
isine-1.970
Token players
Token ID1938
Feature activation-5.46e-03

Pos logit contributions
ropolitan+1.887
ascar+1.865
mph+1.829
aned+1.810
mith+1.776
Neg logit contributions
bis-2.867
uay-2.788
MIT-2.495
isine-2.469
timer-2.417
TokenBest
Token ID13014
Feature activation-1.02e+01

Pos logit contributions
ropolitan+0.445
ascar+0.439
mph+0.431
mith+0.423
aned+0.419
Neg logit contributions
bis-0.646
uay-0.637
 Maher-0.560
MIT-0.553
isine-0.552
TokenT
Token ID51
Feature activation-1.50e+01

Pos logit contributions
Lex+6.052
mith+5.698
weekly+5.690
jew+5.633
aned+5.619
Neg logit contributions
bis-7.523
uay-7.431
isine-6.433
�醒-6.429
 Maher-6.420
Tokenreek
Token ID10316
Feature activation-8.68e+00

Pos logit contributions
ropolitan+8.871
inth+8.831
aned+8.802
ascar+8.737
ruction+8.633
Neg logit contributions
bis-9.992
uay-9.670
 Labrador-8.742
 Maher-8.651
�醒-8.534
TokenAs
Token ID1722
Feature activation-3.75e+00

Pos logit contributions
mith+5.340
ascar+5.339
ropolitan+5.271
mph+5.266
Lex+5.241
Neg logit contributions
bis-6.199
uay-5.974
 Maher-5.284
 Labrador-5.274
isine-5.227
Tokenyu
Token ID24767
Feature activation-9.70e+00

Pos logit contributions
ropolitan+1.769
mph+1.734
ascar+1.729
aned+1.727
mith+1.671
Neg logit contributions
bis-3.417
uay-3.358
 Maher-3.021
MIT-3.003
 Labrador-2.995
TokenK
Token ID42
Feature activation-1.92e+01

Pos logit contributions
Lex+5.821
mith+5.539
ascar+5.505
jew+5.504
mph+5.428
Neg logit contributions
bis-7.099
uay-7.065
�醒-6.235
icter-6.168
isine-6.160
Tokenong
Token ID506
Feature activation-7.23e+00

Pos logit contributions
aned+7.324
ascar+7.245
inth+7.194
ropolitan+6.842
mph+6.840
Neg logit contributions
uay-14.911
bis-14.911
�醒-14.666
 Maher-14.590
 Rossi-14.219
TokenCh
Token ID1925
Feature activation-2.43e+00

Pos logit contributions
Lex+3.979
ascar+3.908
mith+3.864
mph+3.813
jew+3.746
Neg logit contributions
uay-5.803
bis-5.686
 Labrador-5.043
isine-5.032
�醒-5.030
Tokenoya
Token ID23790
Feature activation-1.06e+01

Pos logit contributions
ropolitan+1.266
ascar+1.248
mph+1.211
aned+1.192
rolet+1.173
Neg logit contributions
bis-2.165
uay-2.088
 Maher-1.883
MIT-1.883
isine-1.855
TokenWeek
Token ID20916
Feature activation-1.62e+01

Pos logit contributions
Lex+6.257
ascar+5.892
jew+5.876
mph+5.869
aned+5.858
Neg logit contributions
uay-7.864
bis-7.742
�醒-6.878
isine-6.813
 Maher-6.788
Tokenend
Token ID437
Feature activation-8.15e+00

Pos logit contributions
ropolitan+5.465
weekly+5.147
mph+5.114
aned+5.017
hem+4.948
Neg logit contributions
bis-15.599
uay-14.733
icter-14.455
�醒-14.248
 Labrador-13.942
Token demonstrate
Token ID10176
Feature activation-1.10e+00

Pos logit contributions
ropolitan+0.728
ascar+0.712
mph+0.699
aned+0.688
mith+0.686
Neg logit contributions
bis-1.127
uay-1.104
 Maher-0.974
MIT-0.972
isine-0.964
Token that
Token ID326
Feature activation+1.67e+00

Pos logit contributions
ropolitan+0.626
ascar+0.615
mph+0.604
aned+0.589
mith+0.589
Neg logit contributions
bis-0.922
uay-0.904
MIT-0.793
 Maher-0.791
isine-0.784
Token trans
Token ID1007
Feature activation+2.82e+00

Pos logit contributions
bis+1.361
uay+1.331
 Maher+1.172
MIT+1.162
isine+1.151
Neg logit contributions
ropolitan-0.988
ascar-0.973
mph-0.955
aned-0.933
mith-0.925
Tokenval
Token ID2100
Feature activation-2.30e+00

Pos logit contributions
bis+2.066
uay+2.014
 Maher+1.734
MIT+1.719
isine+1.705
Neg logit contributions
ropolitan-1.903
ascar-1.877
mph-1.851
aned-1.816
mith-1.808
Tokenuation
Token ID2288
Feature activation-7.28e+00

Pos logit contributions
ropolitan+1.340
ascar+1.289
mph+1.283
aned+1.245
ruction+1.231
Neg logit contributions
bis-1.892
uay-1.836
 Maher-1.662
MIT-1.662
prints-1.620
Token does
Token ID857
Feature activation-1.90e+01

Pos logit contributions
ascar+4.028
ropolitan+3.968
mith+3.925
mph+3.835
 ►+3.833
Neg logit contributions
bis-5.841
uay-5.751
MIT-5.174
 Maher-5.095
timer-5.014
Token occur
Token ID3051
Feature activation-6.34e+00

Pos logit contributions
 suffice+7.155
ascar+6.879
ropolitan+6.848
hem+6.772
mith+6.669
Neg logit contributions
uay-16.419
bis-15.673
MIT-14.045
icter-13.980
isine-13.970
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
ropolitan+3.362
ascar+3.309
mph+3.256
mith+3.254
 ►+3.214
Neg logit contributions
bis-5.330
uay-5.273
MIT-4.679
 Maher-4.605
isine-4.578
Token Brief
Token ID22821
Feature activation-6.44e+00

Pos logit contributions
ropolitan+1.035
ascar+1.020
mph+1.005
aned+0.980
mith+0.979
Neg logit contributions
bis-1.355
uay-1.333
isine-1.161
MIT-1.152
 Maher-1.145
Tokenly
Token ID306
Feature activation-6.41e+00

Pos logit contributions
ropolitan+2.867
ascar+2.803
mph+2.738
aned+2.695
Lex+2.689
Neg logit contributions
uay-5.875
bis-5.867
MIT-5.312
isine-5.235
 Maher-5.229
Token,
Token ID11
Feature activation-9.02e-01

Pos logit contributions
mph+3.488
ropolitan+3.486
ascar+3.455
aned+3.385
Lex+3.365
Neg logit contributions
bis-5.200
uay-5.155
MIT-4.548
isine-4.429
timer-4.425
Token)
Token ID8
Feature activation-4.09e+00

Pos logit contributions
bis+1.774
uay+1.726
 Maher+1.497
MIT+1.487
isine+1.469
Neg logit contributions
ropolitan-1.631
ascar-1.610
mph-1.581
aned-1.547
mith-1.539
Token and
Token ID290
Feature activation+2.36e+00

Pos logit contributions
ropolitan+2.499
ascar+2.494
mph+2.453
mith+2.437
aned+2.420
Neg logit contributions
bis-3.190
uay-3.124
MIT-2.704
 Maher-2.704
isine-2.650
Token wh
Token ID348
Feature activation+2.00e+00

Pos logit contributions
bis+1.941
uay+1.890
 Maher+1.671
MIT+1.658
isine+1.639
Neg logit contributions
ropolitan-1.389
ascar-1.364
mph-1.334
aned-1.300
mith-1.293
Tokeniz
Token ID528
Feature activation-5.00e+00

Pos logit contributions
bis+1.599
uay+1.563
 Maher+1.367
MIT+1.358
isine+1.347
Neg logit contributions
ropolitan-1.215
ascar-1.195
mph-1.173
aned-1.146
mith-1.139
Token on
Token ID319
Feature activation-4.77e+00

Pos logit contributions
mph+2.858
ascar+2.858
ropolitan+2.792
mith+2.727
aned+2.722
Neg logit contributions
bis-4.035
uay-3.910
 Maher-3.479
isine-3.429
MIT-3.396
Token high
Token ID1029
Feature activation-1.90e+01

Pos logit contributions
ascar+2.576
mph+2.511
ropolitan+2.506
mith+2.456
aned+2.446
Neg logit contributions
bis-4.086
uay-3.999
 Maher-3.468
isine-3.442
MIT-3.434
Token for
Token ID329
Feature activation-8.09e+00

Pos logit contributions
 ED+8.318
ascar+8.029
 IM+7.974
mph+7.925
 suffice+7.760
Neg logit contributions
bis-15.119
uay-14.907
MIT-13.437
�醒-13.395
isine-13.300
Token a
Token ID257
Feature activation-4.89e+00

Pos logit contributions
 ED+4.067
mph+4.010
ascar+3.931
mith+3.918
 tempted+3.900
Neg logit contributions
bis-6.870
uay-6.796
MIT-5.943
isine-5.929
icter-5.891
Token minute
Token ID5664
Feature activation-6.37e+00

Pos logit contributions
ascar+2.591
ropolitan+2.586
mph+2.582
hem+2.547
mith+2.536
Neg logit contributions
bis-4.169
uay-4.038
MIT-3.585
isine-3.498
 Maher-3.491
Token or
Token ID393
Feature activation-8.95e+00

Pos logit contributions
mph+3.335
ropolitan+3.245
ascar+3.239
mith+3.154
aned+3.126
Neg logit contributions
bis-5.402
uay-5.277
MIT-4.733
 Maher-4.680
isine-4.662
Token so
Token ID523
Feature activation-1.02e+01

Pos logit contributions
mph+3.674
ascar+3.608
mith+3.559
 ED+3.536
aned+3.518
Neg logit contributions
uay-8.272
bis-8.252
prints-7.460
isine-7.341
�醒-7.273
Token Only
Token ID5514
Feature activation-5.97e+00

Pos logit contributions
ascar+4.436
 ED+4.404
mph+4.341
 ►+4.336
ropolitan+4.321
Neg logit contributions
uay-6.190
bis-6.126
isine-5.532
�醒-5.456
 Maher-5.364
Token a
Token ID257
Feature activation-4.94e+00

Pos logit contributions
ropolitan+3.399
mph+3.338
ascar+3.322
 ED+3.282
aned+3.279
Neg logit contributions
bis-4.689
uay-4.665
isine-4.190
�醒-4.167
 Maher-4.068
Token single
Token ID2060
Feature activation-5.64e+00

Pos logit contributions
ropolitan+2.895
ascar+2.836
mph+2.780
aned+2.764
rolet+2.729
Neg logit contributions
bis-3.906
uay-3.895
isine-3.436
 Maher-3.411
MIT-3.339
Token back
Token ID736
Feature activation-7.68e+00

Pos logit contributions
ropolitan+3.128
ascar+3.090
mph+3.067
 ED+3.023
aned+2.999
Neg logit contributions
bis-4.564
uay-4.561
isine-4.069
 Maher-4.015
�醒-3.892
Tokensl
Token ID6649
Feature activation-3.85e+00

Pos logit contributions
ropolitan+4.880
mph+4.819
ascar+4.687
weekly+4.627
rolet+4.593
Neg logit contributions
bis-5.519
uay-5.445
 Maher-4.961
isine-4.916
�醒-4.803
Tokenash
Token ID1077
Feature activation-1.89e+01

Pos logit contributions
ascar+2.487
ropolitan+2.483
mph+2.427
aned+2.386
mith+2.343
Neg logit contributions
bis-2.887
uay-2.810
 Maher-2.509
MIT-2.463
isine-2.445
Token before
Token ID878
Feature activation-9.58e+00

Pos logit contributions
mith+7.667
 suffice+7.645
mph+7.431
rous+7.361
ascar+7.360
Neg logit contributions
uay-14.432
isine-14.385
�醒-14.163
bis-14.105
icter-13.267
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
ascar+4.438
 ED+4.407
mph+4.330
ropolitan+4.243
aned+4.149
Neg logit contributions
uay-8.132
bis-7.957
isine-7.347
�醒-7.215
 Maher-7.168
Token '
Token ID705
Feature activation-3.29e+00

Pos logit contributions
ascar+0.677
ropolitan+0.675
mph+0.662
aned+0.644
mith+0.638
Neg logit contributions
bis-1.130
uay-1.113
 Maher-0.988
isine-0.986
MIT-0.980
Token:'
Token ID32105
Feature activation-7.44e+00

Pos logit contributions
ascar+1.954
mph+1.938
ropolitan+1.919
mith+1.856
aned+1.847
Neg logit contributions
bis-2.584
uay-2.565
 Maher-2.316
isine-2.246
MIT-2.233
Token is
Token ID318
Feature activation-1.20e+01

Pos logit contributions
ascar+4.045
mph+4.036
ropolitan+3.987
mith+3.935
 ED+3.873
Neg logit contributions
uay-5.878
bis-5.780
isine-5.331
 Maher-5.206
�醒-5.175
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
bis+1.058
uay+1.033
 Maher+0.909
MIT+0.902
isine+0.893
Neg logit contributions
ropolitan-0.778
ascar-0.766
mph-0.752
aned-0.734
mith-0.728
Token former
Token ID1966
Feature activation-5.95e+00

Pos logit contributions
bis+0.975
uay+0.953
 Maher+0.839
MIT+0.833
isine+0.824
Neg logit contributions
ropolitan-0.702
ascar-0.691
mph-0.678
aned-0.662
mith-0.657
Token is
Token ID318
Feature activation-6.52e-01

Pos logit contributions
ropolitan+3.293
ascar+3.266
mph+3.229
mith+3.222
 ED+3.152
Neg logit contributions
uay-4.860
bis-4.814
isine-4.236
MIT-4.219
�醒-4.164
Token truly
Token ID4988
Feature activation-6.94e+00

Pos logit contributions
ropolitan+0.373
ascar+0.369
mph+0.363
aned+0.356
mith+0.354
Neg logit contributions
bis-0.543
uay-0.532
MIT-0.468
 Maher-0.465
isine-0.462
Token coming
Token ID2406
Feature activation-6.24e+00

Pos logit contributions
mph+3.721
ropolitan+3.710
aned+3.680
ascar+3.677
mith+3.661
Neg logit contributions
bis-5.657
uay-5.632
MIT-4.987
isine-4.934
�醒-4.889
Token to
Token ID284
Feature activation-1.88e+01

Pos logit contributions
ropolitan+3.107
mph+3.094
mith+3.076
ascar+2.984
 ED+2.970
Neg logit contributions
bis-5.537
uay-5.339
isine-4.760
�醒-4.750
MIT-4.725
Token fruition
Token ID41675
Feature activation-2.52e+00

Pos logit contributions
aned+7.909
 ED+7.806
ropolitan+7.616
ascar+7.522
mph+7.439
Neg logit contributions
bis-15.593
uay-14.828
timer-13.604
�醒-13.221
icter-13.012
Token.
Token ID13
Feature activation-1.34e+00

Pos logit contributions
ropolitan+1.446
ascar+1.425
mph+1.405
mith+1.390
aned+1.366
Neg logit contributions
bis-2.076
uay-2.051
MIT-1.793
 Maher-1.777
isine-1.764
Token
Token ID198
Feature activation-2.41e+00

Pos logit contributions
ropolitan+0.875
ascar+0.864
mph+0.851
mith+0.834
 ►+0.822
Neg logit contributions
bis-1.006
uay-0.992
isine-0.857
MIT-0.840
prints-0.836
Token
Token ID198
Feature activation-7.56e-01

Pos logit contributions
ropolitan+1.570
mph+1.549
ascar+1.545
mith+1.505
aned+1.496
Neg logit contributions
bis-1.797
uay-1.763
icter-1.527
isine-1.525
 Maher-1.519
TokenIndeed
Token ID17854
Feature activation-5.20e+00

Pos logit contributions
ropolitan+0.459
ascar+0.455
mph+0.452
mith+0.439
aned+0.438
Neg logit contributions
bis-0.598
uay-0.589
 Maher-0.516
isine-0.510
 Labrador-0.502
Token destroyed
Token ID6572
Feature activation-8.22e-01

Pos logit contributions
aned+4.987
mith+4.756
 tempted+4.755
 ED+4.726
mph+4.701
Neg logit contributions
bis-8.376
uay-8.362
MIT-7.340
�醒-7.278
isine-7.273
Token,
Token ID11
Feature activation-6.20e+00

Pos logit contributions
ropolitan+0.511
ascar+0.505
mph+0.498
mith+0.488
aned+0.486
Neg logit contributions
bis-0.643
uay-0.631
MIT-0.547
 Maher-0.546
isine-0.540
Token but
Token ID475
Feature activation-1.01e+00

Pos logit contributions
ascar+3.338
ropolitan+3.300
mph+3.289
aned+3.259
mith+3.256
Neg logit contributions
bis-5.057
uay-5.050
MIT-4.410
isine-4.367
�醒-4.351
Token that
Token ID326
Feature activation-1.93e+00

Pos logit contributions
ropolitan+0.626
ascar+0.616
mph+0.612
aned+0.597
mith+0.595
Neg logit contributions
bis-0.792
uay-0.776
MIT-0.675
isine-0.669
 Maher-0.668
Token can
Token ID460
Feature activation-1.34e+01

Pos logit contributions
ropolitan+1.146
ascar+1.138
mph+1.125
mith+1.100
aned+1.092
Neg logit contributions
bis-1.549
uay-1.523
MIT-1.326
isine-1.320
 Maher-1.299
Token only
Token ID691
Feature activation-1.88e+01

Pos logit contributions
mith+5.746
 suffice+5.733
ascar+5.618
hem+5.521
mph+5.472
Neg logit contributions
uay-11.627
bis-11.523
prints-10.325
MIT-10.317
icter-10.307
Token be
Token ID307
Feature activation-1.60e+01

Pos logit contributions
 suffice+7.360
 doom+6.986
 ED+6.364
hem+6.098
ascar+6.058
Neg logit contributions
uay-16.457
bis-16.399
icter-15.068
MIT-14.815
prints-14.812
Token done
Token ID1760
Feature activation-8.52e+00

Pos logit contributions
 tempted+5.869
aned+5.615
 ED+5.499
hem+5.325
 Scion+5.272
Neg logit contributions
bis-14.804
uay-14.428
�醒-13.365
prints-13.136
isine-13.114
Token by
Token ID416
Feature activation-1.08e+01

Pos logit contributions
mith+4.367
ropolitan+4.362
mph+4.357
ascar+4.353
 ED+4.232
Neg logit contributions
bis-6.998
uay-6.881
�醒-6.174
MIT-6.078
icter-6.014
Token sending
Token ID7216
Feature activation-5.17e+00

Pos logit contributions
 ED+5.692
 Scion+5.517
mph+5.478
 tempted+5.451
ascar+5.435
Neg logit contributions
bis-8.680
uay-8.549
MIT-7.633
�醒-7.520
isine-7.476
Token it
Token ID340
Feature activation+1.36e+00

Pos logit contributions
ropolitan+2.907
ascar+2.881
mph+2.856
mith+2.811
 ED+2.789
Neg logit contributions
bis-4.233
uay-4.174
isine-3.664
MIT-3.659
timer-3.596
Token pleasing
Token ID28790
Feature activation-7.24e-02

Pos logit contributions
mph+2.948
ropolitan+2.903
ascar+2.875
aned+2.865
 ►+2.819
Neg logit contributions
uay-4.055
bis-4.010
 Maher-3.579
isine-3.565
MIT-3.490
Token placeholder
Token ID46076
Feature activation-1.07e+01

Pos logit contributions
ropolitan+0.046
ascar+0.046
mph+0.045
aned+0.044
mith+0.044
Neg logit contributions
bis-0.056
uay-0.054
 Maher-0.047
MIT-0.047
isine-0.047
Token
Token ID3556
Feature activation-1.43e+01

Pos logit contributions
ascar+6.833
mph+6.770
 ED+6.719
ropolitan+6.685
 div+6.660
Neg logit contributions
uay-7.027
bis-7.012
isine-6.094
�醒-5.930
 Maher-5.921
Tokenp
Token ID79
Feature activation-3.15e+00

Pos logit contributions
mph+5.376
ropolitan+5.159
weekly+5.073
aned+5.068
ascar+5.004
Neg logit contributions
uay-12.799
�醒-12.528
bis-12.367
 Maher-12.296
icter-12.067
Token>
Token ID29
Feature activation-1.04e+01

Pos logit contributions
ropolitan+2.208
ascar+2.186
mph+2.164
mith+2.143
aned+2.119
Neg logit contributions
bis-2.175
uay-2.112
MIT-1.810
 Maher-1.801
isine-1.784
Token
Token ID7359
Feature activation-1.85e+01

Pos logit contributions
mph+4.230
ropolitan+4.193
 ►+4.172
 ED+4.144
ascar+4.139
Neg logit contributions
uay-9.281
bis-9.237
icter-8.268
isine-8.195
MIT-8.178
Tokenli
Token ID4528
Feature activation-4.56e+00

Pos logit contributions
mph+4.088
aned+3.611
hem+3.579
jew+3.578
ascar+3.528
Neg logit contributions
uay-17.811
bis-17.747
�醒-17.466
 Maher-17.192
 Reilly-16.756
Token>
Token ID29
Feature activation-1.22e+01

Pos logit contributions
ropolitan+3.138
ascar+3.102
mph+3.071
mith+3.047
aned+3.034
Neg logit contributions
bis-3.145
uay-3.066
icter-2.663
MIT-2.638
isine-2.622
Token
Token ID7359
Feature activation-1.33e+01

Pos logit contributions
ropolitan+4.479
 ED+4.459
mph+4.445
 ►+4.431
ascar+4.339
Neg logit contributions
uay-11.056
bis-11.031
icter-9.935
isine-9.815
MIT-9.784
Tokenul
Token ID377
Feature activation-4.60e-01

Pos logit contributions
aned+3.554
mph+3.505
ropolitan+3.291
ascar+3.050
hem+3.049
Neg logit contributions
bis-13.658
�醒-13.586
uay-13.075
 Maher-12.918
 Labrador-12.789
Token>
Token ID29
Feature activation-1.21e+01

Pos logit contributions
ropolitan+0.359
ascar+0.355
mph+0.350
aned+0.344
mith+0.343
Neg logit contributions
bis-0.288
uay-0.280
 Maher-0.236
MIT-0.234
isine-0.231
Token said
Token ID531
Feature activation-7.58e+00

Pos logit contributions
ropolitan+1.606
ascar+1.594
mph+1.575
mith+1.543
aned+1.537
Neg logit contributions
bis-2.064
uay-2.032
MIT-1.763
 Maher-1.761
isine-1.753
Token Klopp
Token ID43461
Feature activation+1.10e+00

Pos logit contributions
ropolitan+3.677
ascar+3.660
mith+3.545
mph+3.538
aned+3.537
Neg logit contributions
bis-6.553
uay-6.489
MIT-5.740
prints-5.697
isine-5.595
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
bis+0.861
uay+0.843
 Maher+0.735
MIT+0.732
isine+0.721
Neg logit contributions
ropolitan-0.686
ascar-0.676
mph-0.664
aned-0.651
mith-0.647
Token whose
Token ID3025
Feature activation-1.03e+01

Pos logit contributions
bis+0.159
uay+0.156
MIT+0.138
 Maher+0.137
isine+0.136
Neg logit contributions
ropolitan-0.097
ascar-0.096
mph-0.094
aned-0.092
mith-0.091
Token side
Token ID1735
Feature activation-5.06e+00

Pos logit contributions
 ED+4.712
ascar+4.606
mph+4.556
 weekly+4.508
aned+4.481
Neg logit contributions
bis-9.125
uay-8.738
icter-8.025
�醒-7.979
MIT-7.967
Token face
Token ID1986
Feature activation-1.85e+01

Pos logit contributions
ropolitan+2.879
mph+2.828
ascar+2.818
mith+2.803
aned+2.782
Neg logit contributions
bis-4.067
uay-4.047
MIT-3.601
 Maher-3.503
isine-3.500
Token Crystal
Token ID12969
Feature activation+4.83e+00

Pos logit contributions
 ED+9.542
 ►+9.203
 tempted+9.026
 IM+9.022
 Queens+8.886
Neg logit contributions
bis-13.116
uay-12.763
icter-11.752
MIT-11.650
�醒-11.646
Token Palace
Token ID15301
Feature activation-4.63e+00

Pos logit contributions
bis+2.807
uay+2.696
 Maher+2.275
MIT+2.207
 Labrador+2.180
Neg logit contributions
ropolitan-3.954
ascar-3.916
mph-3.845
aned-3.825
rolet-3.768
Token at
Token ID379
Feature activation-2.89e+00

Pos logit contributions
ropolitan+2.557
ascar+2.464
mith+2.435
mph+2.429
 ►+2.374
Neg logit contributions
bis-3.891
uay-3.835
MIT-3.390
 Maher-3.358
prints-3.346
Token Anfield
Token ID44303
Feature activation+3.35e+00

Pos logit contributions
ropolitan+1.516
ascar+1.472
mph+1.465
 ED+1.445
mith+1.427
Neg logit contributions
bis-2.521
uay-2.480
timer-2.182
isine-2.173
MIT-2.172
Token on
Token ID319
Feature activation-2.91e+00

Pos logit contributions
bis+2.553
uay+2.484
 Maher+2.176
MIT+2.143
isine+2.135
Neg logit contributions
ropolitan-2.141
ascar-2.123
mph-2.081
aned-2.044
rolet-2.006
Token.
Token ID13
Feature activation-8.47e-01

Pos logit contributions
ascar+3.256
ropolitan+3.207
mph+3.201
 ED+3.101
Lex+3.085
Neg logit contributions
bis-4.859
uay-4.765
isine-4.243
MIT-4.211
timer-4.141
Token
Token ID198
Feature activation-3.27e+00

Pos logit contributions
ropolitan+0.544
ascar+0.539
mph+0.534
aned+0.518
rolet+0.517
Neg logit contributions
bis-0.641
uay-0.630
isine-0.550
MIT-0.543
 Maher-0.539
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
ropolitan+2.047
mph+2.044
ascar+2.022
mith+1.985
aned+1.964
Neg logit contributions
bis-2.482
uay-2.444
icter-2.168
isine-2.137
�醒-2.131
TokenThe
Token ID464
Feature activation-4.01e+00

Pos logit contributions
mph+1.169
ropolitan+1.156
ascar+1.155
Lex+1.142
mith+1.125
Neg logit contributions
bis-1.711
uay-1.692
 Maher-1.506
isine-1.496
 Labrador-1.467
Token high
Token ID1029
Feature activation-2.12e+01

Pos logit contributions
mph+2.303
ascar+2.284
ropolitan+2.269
aned+2.227
Lex+2.220
Neg logit contributions
bis-3.211
uay-3.160
isine-2.802
MIT-2.794
timer-2.748
Token-
Token ID12
Feature activation-1.85e+01

Pos logit contributions
mph+8.269
 ED+8.079
Lex+7.696
 Scion+7.696
 IM+7.579
Neg logit contributions
bis-16.475
uay-16.372
MIT-15.168
isine-15.109
�醒-14.781
Tokenoutput
Token ID22915
Feature activation-1.11e+01

Pos logit contributions
mph+10.028
Lex+9.374
weekly+9.283
mith+8.908
jew+8.871
Neg logit contributions
uay-12.644
bis-12.404
 Maher-12.377
�醒-11.758
 quo-11.543
Token 3
Token ID513
Feature activation-4.03e+00

Pos logit contributions
 ED+5.594
mph+5.495
 Scion+5.466
Lex+5.446
 Lith+5.369
Neg logit contributions
uay-9.018
bis-8.811
isine-8.099
MIT-8.027
icter-7.991
Token.
Token ID13
Feature activation-2.63e+00

Pos logit contributions
mph+2.260
ropolitan+2.236
ascar+2.219
mith+2.161
Lex+2.159
Neg logit contributions
bis-3.333
uay-3.289
isine-2.901
 Maher-2.889
icter-2.862
Token5
Token ID20
Feature activation-7.93e+00

Pos logit contributions
mph+1.445
ropolitan+1.444
ascar+1.441
mith+1.378
Lex+1.369
Neg logit contributions
bis-2.218
uay-2.194
 Maher-1.938
isine-1.929
MIT-1.913
Token-
Token ID12
Feature activation-9.93e+00

Pos logit contributions
mph+4.138
ropolitan+3.936
ascar+3.930
Lex+3.894
rolet+3.877
Neg logit contributions
uay-6.657
bis-6.533
isine-5.837
MIT-5.801
 Maher-5.795
Token pieces
Token ID5207
Feature activation-2.39e+00

Pos logit contributions
ropolitan+0.905
ascar+0.889
mph+0.870
aned+0.852
 ED+0.834
Neg logit contributions
bis-2.155
uay-2.134
MIT-1.910
isine-1.898
 Maher-1.895
Token?
Token ID30
Feature activation+3.29e+00

Pos logit contributions
ropolitan+1.342
ascar+1.311
mph+1.298
mith+1.282
aned+1.276
Neg logit contributions
bis-2.007
uay-1.968
MIT-1.728
isine-1.726
 Maher-1.704
Token half
Token ID2063
Feature activation-1.81e+00

Pos logit contributions
bis+2.728
uay+2.658
 Maher+2.356
MIT+2.319
prints+2.309
Neg logit contributions
ropolitan-1.904
ascar-1.863
mph-1.829
mith-1.778
aned-1.773
Token_
Token ID62
Feature activation+1.87e+00

Pos logit contributions
ascar+1.040
ropolitan+1.038
mph+1.017
aned+0.995
mith+0.985
Neg logit contributions
bis-1.480
uay-1.470
 Maher-1.293
isine-1.267
MIT-1.263
Tokenm
Token ID76
Feature activation-9.90e+00

Pos logit contributions
bis+1.456
uay+1.421
 Maher+1.241
MIT+1.233
isine+1.220
Neg logit contributions
ropolitan-1.172
ascar-1.155
mph-1.134
aned-1.109
mith-1.102
Tokenoves
Token ID5241
Feature activation-1.84e+01

Pos logit contributions
ascar+6.026
ropolitan+5.696
aned+5.684
ruction+5.605
mph+5.514
Neg logit contributions
bis-7.650
uay-7.223
�醒-6.582
MIT-6.521
 Labrador-6.499
Token :
Token ID1058
Feature activation+1.00e+00

Pos logit contributions
mith+6.481
ascar+6.452
 ►+6.241
weekly+6.062
mph+6.034
Neg logit contributions
uay-15.487
bis-15.414
 Maher-14.437
icter-13.978
�醒-13.779
Token u
Token ID334
Feature activation+3.63e+00

Pos logit contributions
bis+0.817
uay+0.799
 Maher+0.701
MIT+0.697
isine+0.692
Neg logit contributions
ropolitan-0.595
ascar-0.586
mph-0.576
aned-0.563
mith-0.558
Token16
Token ID1433
Feature activation-3.11e+00

Pos logit contributions
bis+2.780
uay+2.699
 Maher+2.344
MIT+2.343
isine+2.315
Neg logit contributions
ropolitan-2.339
ascar-2.302
mph-2.218
mith-2.185
aned-2.177
Token,
Token ID837
Feature activation+4.37e+00

Pos logit contributions
ascar+1.763
ropolitan+1.737
mph+1.729
aned+1.675
mith+1.668
Neg logit contributions
bis-2.533
uay-2.512
 Maher-2.199
MIT-2.196
isine-2.183
Token //
Token ID3373
Feature activation+1.26e-01

Pos logit contributions
bis+2.843
uay+2.747
 Maher+2.341
MIT+2.298
prints+2.277
Neg logit contributions
ropolitan-3.301
ascar-3.250
mph-3.203
mith-3.139
aned-3.132
Tokenbind
Token ID21653
Feature activation-2.76e+00

Pos logit contributions
bis+0.373
uay+0.364
 Maher+0.315
MIT+0.311
isine+0.308
Neg logit contributions
ropolitan-0.377
ascar-0.373
mph-0.369
aned-0.362
mith-0.359
Token="
Token ID2625
Feature activation+6.33e-01

Pos logit contributions
ropolitan+1.471
ascar+1.452
mph+1.435
mith+1.400
aned+1.399
Neg logit contributions
bis-2.357
uay-2.317
 Maher-2.067
isine-2.029
MIT-2.024
Tokenphone
Token ID4862
Feature activation+3.73e+00

Pos logit contributions
bis+0.487
uay+0.477
 Maher+0.418
MIT+0.411
isine+0.409
Neg logit contributions
ropolitan-0.402
ascar-0.397
mph-0.392
aned-0.382
mith-0.381
Token.
Token ID13
Feature activation+3.03e+00

Pos logit contributions
bis+2.714
uay+2.645
 Maher+2.286
MIT+2.265
isine+2.228
Neg logit contributions
ropolitan-2.530
ascar-2.493
mph-2.454
aned-2.410
rolet-2.388
Tokenname
Token ID3672
Feature activation+4.64e+00

Pos logit contributions
bis+1.936
uay+1.873
 Maher+1.566
MIT+1.564
isine+1.548
Neg logit contributions
ropolitan-2.330
ascar-2.301
mph-2.260
aned-2.223
mith-2.210
Token">
Token ID23984
Feature activation-1.84e+01

Pos logit contributions
bis+2.839
uay+2.735
 Maher+2.309
MIT+2.288
isine+2.245
Neg logit contributions
ropolitan-3.676
ascar-3.617
mph-3.569
aned-3.509
rolet-3.483
Tokenspan
Token ID12626
Feature activation+2.93e+00

Pos logit contributions
mph+7.150
hem+6.980
aned+6.750
mith+6.577
weekly+6.555
Neg logit contributions
�醒-15.838
uay-15.635
 Maher-14.955
icter-14.823
 Labrador-14.812
Token>
Token ID29
Feature activation-5.43e+00

Pos logit contributions
bis+1.773
uay+1.719
 Maher+1.437
MIT+1.420
isine+1.400
Neg logit contributions
ropolitan-2.353
ascar-2.320
mph-2.288
aned-2.248
rolet-2.226
Token <
Token ID1279
Feature activation-1.08e+01

Pos logit contributions
ropolitan+3.904
ascar+3.892
mph+3.888
mith+3.809
aned+3.805
Neg logit contributions
bis-3.484
uay-3.431
 Maher-2.878
isine-2.859
icter-2.831
Tokenp
Token ID79
Feature activation-9.85e+00

Pos logit contributions
ascar+5.795
mph+5.724
ropolitan+5.460
aned+5.412
weekly+5.385
Neg logit contributions
uay-8.300
bis-8.241
 Maher-7.792
isine-7.470
�醒-7.392
Token ng
Token ID23370
Feature activation-2.68e-01

Pos logit contributions
ascar+5.867
ropolitan+5.779
mph+5.752
mith+5.722
aned+5.670
Neg logit contributions
bis-7.217
uay-7.026
MIT-6.179
 Maher-6.119
 Labrador-5.954
Token Rapt
Token ID21301
Feature activation+4.23e+00

Pos logit contributions
ropolitan+0.741
ascar+0.729
mph+0.723
aned+0.705
mith+0.702
Neg logit contributions
bis-0.757
uay-0.747
 Maher-0.639
MIT-0.638
isine-0.636
Tokenor
Token ID273
Feature activation+7.96e-01

Pos logit contributions
bis+3.201
uay+3.104
 Maher+2.690
timer+2.643
MIT+2.630
Neg logit contributions
ropolitan-2.714
ascar-2.673
mph-2.629
mith-2.598
aned-2.562
Token
Token ID784
Feature activation-2.17e+00

Pos logit contributions
bis+0.623
uay+0.611
 Maher+0.532
MIT+0.530
isine+0.525
Neg logit contributions
ropolitan-0.497
ascar-0.489
mph-0.483
aned-0.471
mith-0.468
Token the
Token ID262
Feature activation+6.38e-01

Pos logit contributions
ropolitan+1.222
ascar+1.203
mph+1.198
aned+1.164
rolet+1.152
Neg logit contributions
bis-1.803
uay-1.778
 Maher-1.560
isine-1.559
MIT-1.556
Token ultimate
Token ID8713
Feature activation-1.92e+00

Pos logit contributions
bis+0.500
uay+0.488
 Maher+0.426
MIT+0.424
isine+0.421
Neg logit contributions
ropolitan-0.398
ascar-0.393
mph-0.387
aned-0.378
mith-0.375
Token high
Token ID1029
Feature activation-1.83e+01

Pos logit contributions
ropolitan+1.112
ascar+1.104
mph+1.094
aned+1.060
 ED+1.058
Neg logit contributions
bis-1.578
uay-1.537
MIT-1.360
isine-1.346
 Maher-1.345
Token-
Token ID12
Feature activation-1.52e+01

Pos logit contributions
mph+7.121
 ED+6.661
ropolitan+6.599
rolet+6.570
ascar+6.534
Neg logit contributions
bis-15.258
uay-15.146
MIT-14.251
 Maher-14.096
mbuds-13.786
Tokenperformance
Token ID26585
Feature activation-3.52e+00

Pos logit contributions
mph+7.656
Lex+7.166
ascar+6.978
weekly+6.849
ropolitan+6.836
Neg logit contributions
uay-11.734
bis-11.566
 Maher-11.515
�醒-11.014
 quo-10.627
Token off
Token ID572
Feature activation+7.09e-01

Pos logit contributions
ascar+1.976
ropolitan+1.958
mph+1.946
 ED+1.931
mith+1.888
Neg logit contributions
bis-2.898
uay-2.855
MIT-2.530
isine-2.493
 Maher-2.486
Token-
Token ID12
Feature activation+2.14e+00

Pos logit contributions
bis+0.538
uay+0.524
 Maher+0.456
MIT+0.453
isine+0.449
Neg logit contributions
ropolitan-0.461
ascar-0.456
mph-0.448
aned-0.438
mith-0.435
Tokenroad
Token ID6344
Feature activation-7.96e+00

Pos logit contributions
bis+1.782
uay+1.743
 Maher+1.525
MIT+1.517
prints+1.512
Neg logit contributions
ropolitan-1.238
ascar-1.214
mph-1.184
aned-1.162
mith-1.160
Token blog
Token ID4130
Feature activation+4.32e+00

Pos logit contributions
ascar+2.248
ropolitan+2.230
mith+2.188
mph+2.156
 ►+2.136
Neg logit contributions
bis-3.142
uay-3.111
isine-2.737
MIT-2.691
 Maher-2.685
Token should
Token ID815
Feature activation-2.19e-01

Pos logit contributions
bis+3.435
uay+3.353
 Maher+2.957
MIT+2.909
isine+2.874
Neg logit contributions
ropolitan-2.617
ascar-2.574
mph-2.524
rolet-2.459
aned-2.458
Token also
Token ID635
Feature activation-1.59e+00

Pos logit contributions
ropolitan+0.120
ascar+0.117
mph+0.115
aned+0.112
mith+0.111
Neg logit contributions
bis-0.189
uay-0.186
 Maher-0.164
MIT-0.164
isine-0.162
Token firmly
Token ID14245
Feature activation-1.40e+00

Pos logit contributions
ropolitan+0.825
ascar+0.809
mph+0.790
mith+0.771
aned+0.771
Neg logit contributions
bis-1.413
uay-1.387
MIT-1.237
 Maher-1.231
isine-1.221
Token put
Token ID1234
Feature activation-6.94e+00

Pos logit contributions
ropolitan+0.731
ascar+0.711
mph+0.701
aned+0.683
mith+0.675
Neg logit contributions
bis-1.232
uay-1.209
 Maher-1.080
MIT-1.074
isine-1.068
Token to
Token ID284
Feature activation-1.83e+01

Pos logit contributions
ropolitan+3.723
ascar+3.694
 ED+3.602
mph+3.592
mith+3.537
Neg logit contributions
bis-5.803
uay-5.599
isine-4.976
�醒-4.922
timer-4.876
Token bed
Token ID3996
Feature activation-8.13e+00

Pos logit contributions
 IM+6.305
ropolitan+6.272
hem+6.216
 ED+6.013
aned+5.989
Neg logit contributions
bis-16.497
uay-15.775
�醒-14.601
isine-14.108
icter-14.027
Token claims
Token ID3667
Feature activation-4.79e+00

Pos logit contributions
ascar+3.846
ropolitan+3.814
 ED+3.753
mph+3.655
mith+3.653
Neg logit contributions
bis-7.157
uay-6.930
isine-6.293
timer-6.177
�醒-6.006
Token that
Token ID326
Feature activation-1.68e+00

Pos logit contributions
ascar+2.594
ropolitan+2.568
mith+2.539
mph+2.494
aned+2.464
Neg logit contributions
bis-4.040
uay-3.946
isine-3.492
MIT-3.434
timer-3.421
Token Facebook
Token ID3203
Feature activation-4.34e-01

Pos logit contributions
ropolitan+0.964
ascar+0.961
mph+0.934
aned+0.918
mith+0.917
Neg logit contributions
bis-1.382
uay-1.351
isine-1.188
 Maher-1.178
MIT-1.177
Token comments
Token ID3651
Feature activation-8.39e+00

Pos logit contributions
ropolitan+0.263
ascar+0.261
mph+0.254
aned+0.249
mith+0.249
Neg logit contributions
bis-0.348
uay-0.340
 Maher-0.297
MIT-0.296
isine-0.294
Token she
Token ID673
Feature activation+2.32e+00

Pos logit contributions
 tempted+4.317
ropolitan+4.264
mph+4.248
 ED+4.232
 ►+4.154
Neg logit contributions
bis-7.501
uay-7.399
�醒-6.584
MIT-6.568
isine-6.460
Token's
Token ID338
Feature activation+1.06e+00

Pos logit contributions
bis+1.830
uay+1.784
 Maher+1.566
MIT+1.537
 Labrador+1.527
Neg logit contributions
ropolitan-1.448
ascar-1.418
mph-1.391
rolet-1.356
aned-1.356
Token got
Token ID1392
Feature activation-7.70e+00

Pos logit contributions
bis+0.853
uay+0.834
 Maher+0.733
MIT+0.726
isine+0.719
Neg logit contributions
ropolitan-0.636
ascar-0.626
mph-0.614
aned-0.599
mith-0.595
Token this
Token ID428
Feature activation-6.75e+00

Pos logit contributions
ropolitan+3.922
 ED+3.846
mph+3.802
ascar+3.769
 ►+3.727
Neg logit contributions
bis-6.589
uay-6.397
MIT-5.755
isine-5.753
�醒-5.670
Token huge
Token ID3236
Feature activation-6.30e+00

Pos logit contributions
 ED+3.773
ropolitan+3.766
ascar+3.754
mph+3.750
mith+3.673
Neg logit contributions
bis-5.510
uay-5.350
MIT-4.685
isine-4.635
�醒-4.598
Token negotiation
Token ID24462
Feature activation-1.83e+01

Pos logit contributions
ropolitan+3.383
 ED+3.358
ascar+3.327
mph+3.290
mith+3.228
Neg logit contributions
bis-5.316
uay-5.200
MIT-4.555
isine-4.519
prints-4.477
Token coming
Token ID2406
Feature activation-1.03e+01

Pos logit contributions
 twe+8.494
mith+8.405
 weekly+8.331
mph+8.302
 ED+8.282
Neg logit contributions
bis-14.299
uay-14.133
�醒-12.800
isine-12.637
MIT-12.590
Token up
Token ID510
Feature activation-1.45e+01

Pos logit contributions
mith+6.769
mph+6.715
Lex+6.626
 ED+6.625
ropolitan+6.619
Neg logit contributions
bis-6.998
uay-6.755
�醒-5.943
mbuds-5.877
icter-5.788
Token,"
Token ID553
Feature activation-1.25e+01

Pos logit contributions
 tempted+5.927
 IM+5.907
 ED+5.890
mph+5.843
hem+5.778
Neg logit contributions
uay-12.625
bis-12.532
�醒-11.390
icter-11.151
mbuds-11.094
Token said
Token ID531
Feature activation-8.71e+00

Pos logit contributions
 ED+6.238
 Mn+6.219
ropolitan+6.045
mith+5.988
aned+5.973
Neg logit contributions
bis-9.846
uay-9.731
�醒-9.007
icter-8.558
mbuds-8.519
Token Quentin
Token ID42447
Feature activation-1.20e+00

Pos logit contributions
ropolitan+4.934
 ED+4.895
ascar+4.796
 Mn+4.755
mph+4.745
Neg logit contributions
bis-6.719
uay-6.630
�醒-5.758
prints-5.688
isine-5.688
Tokenk
Token ID74
Feature activation+2.24e-01

Pos logit contributions
bis+4.998
uay+4.756
isine+4.159
MIT+4.130
prints+4.123
Neg logit contributions
ropolitan-3.922
ascar-3.825
mph-3.736
rolet-3.673
Lex-3.657
Tokenoul
Token ID2852
Feature activation+1.62e+00

Pos logit contributions
bis+0.167
uay+0.163
 Maher+0.142
MIT+0.142
isine+0.140
Neg logit contributions
ropolitan-0.147
ascar-0.145
mph-0.142
aned-0.140
mith-0.139
Tokenas
Token ID292
Feature activation-3.32e+00

Pos logit contributions
bis+1.158
uay+1.129
 Maher+0.973
MIT+0.967
isine+0.955
Neg logit contributions
ropolitan-1.121
ascar-1.108
mph-1.089
aned-1.069
mith-1.061
Token is
Token ID318
Feature activation-2.96e+00

Pos logit contributions
ascar+1.984
ropolitan+1.972
mith+1.936
mph+1.911
aned+1.909
Neg logit contributions
bis-2.627
uay-2.569
MIT-2.223
 Maher-2.216
isine-2.215
Token a
Token ID257
Feature activation-4.13e+00

Pos logit contributions
ropolitan+1.537
ascar+1.499
mph+1.460
aned+1.451
mith+1.449
Neg logit contributions
bis-2.569
uay-2.566
 Maher-2.233
isine-2.232
MIT-2.223
Token research
Token ID2267
Feature activation-1.83e+01

Pos logit contributions
ropolitan+2.131
ascar+2.059
aned+2.012
mph+2.005
mith+1.996
Neg logit contributions
bis-3.621
uay-3.560
isine-3.132
MIT-3.112
 Maher-3.101
Token fellow
Token ID5891
Feature activation-6.61e+00

Pos logit contributions
 ED+6.112
ropolitan+5.893
 twe+5.843
mith+5.792
 weekly+5.494
Neg logit contributions
uay-16.448
bis-16.354
versions-14.669
isine-14.586
timer-14.271
Token at
Token ID379
Feature activation-1.19e+00

Pos logit contributions
ropolitan+3.289
mith+3.089
mph+3.049
ascar+3.038
 ►+3.002
Neg logit contributions
bis-5.880
uay-5.808
isine-5.096
MIT-5.046
prints-5.042
Token Per
Token ID2448
Feature activation+2.26e+00

Pos logit contributions
ropolitan+0.690
ascar+0.671
mph+0.658
aned+0.646
mith+0.637
Neg logit contributions
bis-0.975
uay-0.962
isine-0.838
MIT-0.835
 Maher-0.832
Token Cap
Token ID4476
Feature activation+6.84e+00

Pos logit contributions
bis+1.781
uay+1.737
 Maher+1.521
MIT+1.511
isine+1.495
Neg logit contributions
ropolitan-1.395
ascar-1.377
mph-1.352
aned-1.321
mith-1.312
Tokenita
Token ID5350
Feature activation+2.12e+00

Pos logit contributions
bis+4.464
uay+4.222
 Maher+3.700
 Labrador+3.617
MIT+3.614
Neg logit contributions
ropolitan-5.004
mph-4.993
ascar-4.954
aned-4.838
mith-4.817
Token
Token ID119
Feature activation+7.95e+00

Pos logit contributions
ropolitan+0.521
ascar+0.511
mph+0.504
aned+0.489
mith+0.486
Neg logit contributions
bis-0.873
uay-0.855
 Maher-0.759
MIT-0.754
isine-0.748
Tokeno
Token ID78
Feature activation+2.72e+00

Pos logit contributions
bis+5.813
uay+5.791
isine+4.880
MIT+4.851
 Maher+4.819
Neg logit contributions
ropolitan-5.110
ascar-5.033
rolet-4.853
mph-4.831
 Scion-4.810
Token
Token ID220
Feature activation+6.71e+00

Pos logit contributions
bis+2.086
uay+2.033
 Maher+1.778
MIT+1.758
isine+1.740
Neg logit contributions
ropolitan-1.743
ascar-1.718
mph-1.683
aned-1.644
mith-1.637
Tokenia
Token ID544
Feature activation+4.29e+00

Pos logit contributions
bis+6.194
uay+6.127
 Maher+5.406
isine+5.389
MIT+5.367
Neg logit contributions
ropolitan-3.138
ascar-3.034
rolet-2.940
mph-2.898
aned-2.822
Token e
Token ID304
Feature activation+5.98e+00

Pos logit contributions
bis+3.450
uay+3.368
 Maher+2.972
MIT+2.924
isine+2.898
Neg logit contributions
ropolitan-2.582
ascar-2.549
mph-2.477
rolet-2.422
aned-2.417
Token pa
Token ID14187
Feature activation+1.34e+01

Pos logit contributions
bis+4.694
uay+4.559
 Maher+3.998
MIT+3.941
isine+3.909
Neg logit contributions
ropolitan-3.692
ascar-3.626
mph-3.514
rolet-3.455
aned-3.437
Token
Token ID134
Feature activation+1.50e+00

Pos logit contributions
bis+9.803
uay+9.688
 Maher+8.505
isine+8.489
 quo+8.425
Neg logit contributions
ropolitan-7.745
ascar-7.487
rolet-7.465
mph-7.205
mith-7.066
Token
Token ID119
Feature activation+6.51e+00

Pos logit contributions
bis+1.296
uay+1.269
 Maher+1.123
MIT+1.117
isine+1.106
Neg logit contributions
ropolitan-0.818
ascar-0.805
mph-0.787
aned-0.768
mith-0.761
Tokena
Token ID64
Feature activation+3.79e+00

Pos logit contributions
bis+5.041
uay+4.982
isine+4.256
MIT+4.248
 Maher+4.221
Neg logit contributions
ropolitan-3.997
ascar-3.932
mph-3.773
rolet-3.769
Lex-3.710
Token he
Token ID339
Feature activation+1.10e+01

Pos logit contributions
bis+2.974
uay+2.905
 Maher+2.536
MIT+2.513
isine+2.499
Neg logit contributions
ropolitan-2.351
ascar-2.307
mph-2.262
rolet-2.203
aned-2.201
Token p
Token ID279
Feature activation+1.22e+01

Pos logit contributions
bis+8.309
uay+8.124
 quo+6.925
 Maher+6.890
MIT+6.879
Neg logit contributions
ropolitan-6.542
ascar-6.408
rolet-6.277
mph-6.088
Lex-6.068
Token many
Token ID867
Feature activation+8.51e+00

Pos logit contributions
bis+9.173
uay+8.915
 Maher+8.434
 Labrador+8.063
 Bash+7.671
Neg logit contributions
ropolitan-10.234
rolet-10.221
ascar-10.123
Lex-9.751
mith-9.718
Token southern
Token ID8372
Feature activation+5.47e+00

Pos logit contributions
bis+6.044
uay+5.809
 Maher+5.308
 Labrador+5.207
 quo+5.062
Neg logit contributions
ropolitan-5.654
ascar-5.608
rolet-5.479
Lex-5.389
mph-5.364
Token and
Token ID290
Feature activation-3.97e-01

Pos logit contributions
bis+4.106
uay+3.933
 Maher+3.565
 Labrador+3.471
 quo+3.375
Neg logit contributions
ropolitan-3.562
ascar-3.540
mph-3.456
rolet-3.442
Lex-3.365
Token central
Token ID4318
Feature activation+1.02e+01

Pos logit contributions
ropolitan+0.236
ascar+0.232
mph+0.228
aned+0.225
mith+0.223
Neg logit contributions
bis-0.323
uay-0.314
MIT-0.277
isine-0.275
timer-0.272
Token parts
Token ID3354
Feature activation+7.00e+00

Pos logit contributions
bis+6.754
uay+6.236
 Maher+5.826
 Labrador+5.797
 quo+5.378
Neg logit contributions
ascar-7.257
ropolitan-7.221
rolet-7.127
mph-7.028
Lex-6.950
Token of
Token ID286
Feature activation+1.63e+01

Pos logit contributions
bis+4.544
uay+4.349
 Maher+3.857
 Labrador+3.687
 quo+3.589
Neg logit contributions
ropolitan-5.159
ascar-5.136
rolet-5.018
mph-5.018
aned-4.889
Token Somalia
Token ID23918
Feature activation-4.49e-01

Pos logit contributions
bis+8.310
uay+7.809
 Maher+7.378
 Labrador+7.208
 Bash+6.771
Neg logit contributions
ascar-12.524
rolet-12.454
ropolitan-12.443
Lex-12.260
mph-12.144
Token.
Token ID13
Feature activation+2.21e+00

Pos logit contributions
ropolitan+0.277
ascar+0.272
mph+0.269
aned+0.265
mith+0.261
Neg logit contributions
bis-0.353
uay-0.349
MIT-0.305
isine-0.300
 Maher-0.300
Token
Token ID198
Feature activation+9.32e+00

Pos logit contributions
bis+1.624
uay+1.588
 Maher+1.366
MIT+1.362
isine+1.355
Neg logit contributions
ropolitan-1.493
ascar-1.472
mph-1.449
aned-1.419
mith-1.409
Token
Token ID198
Feature activation+4.76e+00

Pos logit contributions
bis+4.737
uay+4.469
 Maher+3.837
MIT+3.803
timer+3.756
Neg logit contributions
ropolitan-7.940
ascar-7.919
GGGGGGGG-7.796
rolet-7.643
 tempted-7.617
TokenBut
Token ID1537
Feature activation+1.66e+00

Pos logit contributions
bis+3.731
uay+3.606
MIT+3.215
 Maher+3.127
prints+3.091
Neg logit contributions
ropolitan-3.020
ascar-2.953
mph-2.840
rolet-2.830
aned-2.801
Token will
Token ID481
Feature activation+3.07e+00

Pos logit contributions
bis+5.278
uay+5.113
 Maher+4.439
MIT+4.406
 Labrador+4.385
Neg logit contributions
ropolitan-4.574
ascar-4.464
mph-4.341
rolet-4.232
Lex-4.223
Token update
Token ID4296
Feature activation+3.16e+00

Pos logit contributions
bis+2.559
uay+2.484
MIT+2.187
 Maher+2.182
prints+2.146
Neg logit contributions
ropolitan-1.777
ascar-1.743
mph-1.708
aned-1.663
rolet-1.647
Token this
Token ID428
Feature activation-7.11e+00

Pos logit contributions
bis+2.381
uay+2.311
 Maher+2.014
MIT+2.007
prints+1.972
Neg logit contributions
ropolitan-2.068
ascar-2.031
mph-1.996
aned-1.962
rolet-1.942
Token section
Token ID2665
Feature activation-2.49e+00

Pos logit contributions
ascar+3.573
weekly+3.521
mph+3.511
 ED+3.507
ropolitan+3.498
Neg logit contributions
uay-6.081
bis-6.044
isine-5.325
 Maher-5.308
MIT-5.208
Token when
Token ID618
Feature activation+4.08e+00

Pos logit contributions
ropolitan+1.429
ascar+1.420
mph+1.401
aned+1.377
weekly+1.377
Neg logit contributions
bis-2.028
uay-2.004
MIT-1.748
isine-1.739
 Maher-1.738
Token we
Token ID356
Feature activation+1.44e+01

Pos logit contributions
bis+3.244
uay+3.127
 Maher+2.736
MIT+2.728
prints+2.699
Neg logit contributions
ropolitan-2.522
ascar-2.446
mph-2.410
rolet-2.371
aned-2.347
Token can
Token ID460
Feature activation+5.12e+00

Pos logit contributions
bis+9.637
uay+8.533
MIT+7.752
 Rossi+7.684
 Labrador+7.680
Neg logit contributions
ropolitan-9.570
ascar-9.148
mph-8.944
rolet-8.926
GGGGGGGG-8.754
Token add
Token ID751
Feature activation+3.48e+00

Pos logit contributions
bis+3.891
uay+3.723
MIT+3.292
 Maher+3.269
prints+3.210
Neg logit contributions
ropolitan-3.282
ascar-3.211
mph-3.166
aned-3.095
rolet-3.077
Token more
Token ID517
Feature activation-2.41e-01

Pos logit contributions
bis+2.627
uay+2.553
 Maher+2.212
MIT+2.205
prints+2.172
Neg logit contributions
ropolitan-2.271
ascar-2.215
mph-2.184
aned-2.146
rolet-2.140
Token platforms
Token ID9554
Feature activation+2.99e+00

Pos logit contributions
ropolitan+0.147
ascar+0.146
mph+0.143
aned+0.139
mith+0.138
Neg logit contributions
bis-0.192
uay-0.189
 Maher-0.165
MIT-0.164
isine-0.163
Token.
Token ID13
Feature activation+1.67e+00

Pos logit contributions
bis+2.287
uay+2.225
 Maher+1.937
MIT+1.921
isine+1.901
Neg logit contributions
ropolitan-1.916
ascar-1.886
mph-1.850
aned-1.818
mith-1.793
Token woman
Token ID2415
Feature activation-1.97e+00

Pos logit contributions
mph+2.320
ascar+2.278
ropolitan+2.272
aned+2.245
 ED+2.204
Neg logit contributions
bis-4.111
uay-3.995
isine-3.605
 Maher-3.555
MIT-3.545
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
ropolitan+1.153
ascar+1.149
mph+1.143
aned+1.122
mith+1.109
Neg logit contributions
bis-1.594
uay-1.549
MIT-1.373
isine-1.362
 Maher-1.345
Token whose
Token ID3025
Feature activation-1.48e+00

Pos logit contributions
ropolitan+0.616
ascar+0.609
mph+0.606
aned+0.589
mith+0.586
Neg logit contributions
bis-0.929
uay-0.905
MIT-0.797
isine-0.792
 Maher-0.789
Token name
Token ID1438
Feature activation+1.06e+01

Pos logit contributions
ropolitan+0.978
ascar+0.972
mph+0.963
aned+0.946
mith+0.938
Neg logit contributions
bis-1.098
uay-1.071
MIT-0.921
 Maher-0.920
isine-0.913
Token has
Token ID468
Feature activation+1.77e+01

Pos logit contributions
bis+6.863
uay+6.388
 Maher+5.896
 Rossi+5.660
MIT+5.538
Neg logit contributions
ropolitan-7.390
ascar-7.300
mph-7.270
rolet-7.139
aned-7.073
Token not
Token ID407
Feature activation+1.68e+01

Pos logit contributions
bis+9.649
uay+8.552
 Rossi+8.174
 Maher+8.109
 Labrador+7.566
Neg logit contributions
ropolitan-12.714
mph-12.607
ascar-12.396
inth-12.154
rolet-11.811
Token been
Token ID587
Feature activation+1.60e+01

Pos logit contributions
bis+7.481
uay+6.550
 Maher+5.286
 Rossi+5.095
prints+4.890
Neg logit contributions
ropolitan-14.282
mph-14.012
ascar-13.881
rolet-13.658
GGGGGGGG-13.574
Token released
Token ID2716
Feature activation+5.42e+00

Pos logit contributions
bis+8.713
uay+7.927
 Maher+6.885
 Rossi+6.460
 quo+6.379
Neg logit contributions
ropolitan-12.416
ascar-12.121
mph-11.565
ixels-11.563
ruction-11.497
Token,
Token ID11
Feature activation-4.45e+00

Pos logit contributions
bis+3.709
uay+3.596
 Maher+3.115
MIT+3.058
isine+3.031
Neg logit contributions
ropolitan-3.835
ascar-3.801
mph-3.757
aned-3.659
ruction-3.624
Token rode
Token ID22075
Feature activation+1.02e-02

Pos logit contributions
mph+2.494
ascar+2.472
ropolitan+2.450
aned+2.450
mith+2.414
Neg logit contributions
bis-3.641
uay-3.534
isine-3.179
MIT-3.155
�醒-3.113
Token her
Token ID607
Feature activation-3.08e+00

Pos logit contributions
bis+0.008
uay+0.008
MIT+0.007
 Maher+0.007
isine+0.007
Neg logit contributions
ropolitan-0.006
ascar-0.006
mph-0.006
aned-0.006
mith-0.006
Tokenpositive
Token ID24561
Feature activation+6.47e+00

Pos logit contributions
bis+9.025
uay+8.206
hum+7.571
MIT+7.407
timer+7.243
Neg logit contributions
ascar-10.645
ropolitan-10.636
mph-10.212
Lex-9.982
cture-9.956
Token (
Token ID357
Feature activation+5.04e+00

Pos logit contributions
bis+4.653
uay+4.487
 Maher+3.969
MIT+3.904
 Labrador+3.844
Neg logit contributions
ropolitan-4.370
ascar-4.256
mph-4.192
aned-4.114
rolet-4.072
TokenG
Token ID38
Feature activation-2.33e+00

Pos logit contributions
bis+3.828
uay+3.708
MIT+3.265
 Maher+3.226
prints+3.157
Neg logit contributions
ropolitan-3.294
ascar-3.209
mph-3.115
aned-3.058
rolet-3.048
Token 1
Token ID352
Feature activation+3.82e+00

Pos logit contributions
ropolitan+1.457
ascar+1.450
mph+1.420
aned+1.396
mith+1.375
Neg logit contributions
bis-1.794
uay-1.756
 Maher-1.525
isine-1.519
MIT-1.514
Token:
Token ID25
Feature activation+7.13e+00

Pos logit contributions
bis+2.924
uay+2.845
 Maher+2.483
MIT+2.461
isine+2.421
Neg logit contributions
ropolitan-2.461
ascar-2.409
mph-2.357
aned-2.326
mith-2.301
Token the
Token ID262
Feature activation+1.36e+01

Pos logit contributions
bis+5.246
uay+5.017
 Maher+4.428
MIT+4.388
 Labrador+4.319
Neg logit contributions
ropolitan-4.759
ascar-4.624
mph-4.480
mith-4.418
aned-4.379
Token IPCC
Token ID35814
Feature activation-6.43e-01

Pos logit contributions
bis+10.018
uay+9.428
 Maher+8.900
 Labrador+8.656
 Rossi+8.531
Neg logit contributions
ropolitan-8.187
ascar-7.934
mph-7.590
Lex-7.469
rolet-7.347
Token
Token ID447
Feature activation+9.16e-01

Pos logit contributions
ropolitan+0.384
ascar+0.376
mph+0.373
aned+0.366
mith+0.364
Neg logit contributions
bis-0.517
uay-0.508
isine-0.442
MIT-0.441
 Maher-0.440
Token
Token ID247
Feature activation+8.34e+00

Pos logit contributions
bis+0.724
uay+0.707
 Maher+0.618
MIT+0.614
isine+0.608
Neg logit contributions
ropolitan-0.567
ascar-0.558
mph-0.548
aned-0.536
mith-0.533
Tokens
Token ID82
Feature activation+5.80e+00

Pos logit contributions
bis+4.546
uay+4.271
 Maher+3.564
MIT+3.540
prints+3.469
Neg logit contributions
ropolitan-7.042
ascar-7.029
rolet-6.856
mph-6.679
mith-6.668
Token implicit
Token ID16992
Feature activation+4.95e+00

Pos logit contributions
bis+4.553
uay+4.403
 Maher+3.955
MIT+3.862
 Labrador+3.816
Neg logit contributions
ropolitan-3.568
ascar-3.548
mph-3.419
rolet-3.353
aned-3.326
Token theories
Token ID10946
Feature activation+6.42e+00

Pos logit contributions
bis+2.963
uay+2.890
 Maher+2.541
MIT+2.504
prints+2.461
Neg logit contributions
ropolitan-2.468
ascar-2.444
mph-2.383
rolet-2.328
aned-2.318
Token are
Token ID389
Feature activation-5.36e-01

Pos logit contributions
bis+4.825
uay+4.653
 Maher+4.149
MIT+4.018
 Labrador+3.991
Neg logit contributions
ropolitan-4.125
ascar-4.119
mph-4.026
rolet-3.900
aned-3.895
Token No
Token ID1400
Feature activation+1.34e+00

Pos logit contributions
ropolitan+0.330
ascar+0.325
mph+0.320
aned+0.316
mith+0.314
Neg logit contributions
bis-0.421
uay-0.412
MIT-0.358
isine-0.357
 Maher-0.354
Tokenz
Token ID89
Feature activation+2.28e+00

Pos logit contributions
bis+1.010
uay+0.986
 Maher+0.855
MIT+0.850
isine+0.840
Neg logit contributions
ropolitan-0.881
ascar-0.870
mph-0.855
aned-0.837
mith-0.831
Tokenick
Token ID624
Feature activation-1.73e+00

Pos logit contributions
bis+1.712
uay+1.670
 Maher+1.451
MIT+1.444
isine+1.429
Neg logit contributions
ropolitan-1.492
ascar-1.473
mph-1.449
aned-1.420
mith-1.415
Token's
Token ID338
Feature activation+4.70e+00

Pos logit contributions
ropolitan+1.016
ascar+0.997
mph+0.977
aned+0.961
mith+0.959
Neg logit contributions
bis-1.407
uay-1.380
MIT-1.219
 Maher-1.206
isine-1.201
Token account
Token ID1848
Feature activation+2.07e+00

Pos logit contributions
bis+3.740
uay+3.617
 Maher+3.212
MIT+3.153
isine+3.120
Neg logit contributions
ropolitan-2.862
ascar-2.841
mph-2.772
aned-2.704
rolet-2.684
Token of
Token ID286
Feature activation+7.36e+00

Pos logit contributions
bis+1.568
uay+1.529
 Maher+1.329
MIT+1.318
isine+1.305
Neg logit contributions
ropolitan-1.354
ascar-1.336
mph-1.312
aned-1.284
mith-1.274
Token rationality
Token ID45627
Feature activation+6.70e+00

Pos logit contributions
bis+5.644
uay+5.478
 Maher+4.972
 Labrador+4.786
isine+4.748
Neg logit contributions
ropolitan-4.580
ascar-4.458
mph-4.375
aned-4.260
rolet-4.258
Token as
Token ID355
Feature activation+4.36e+00

Pos logit contributions
bis+4.815
uay+4.645
 Maher+4.081
MIT+3.966
 quo+3.951
Neg logit contributions
ropolitan-4.528
ascar-4.463
mph-4.339
aned-4.254
rolet-4.234
Token an
Token ID281
Feature activation+1.67e+00

Pos logit contributions
bis+3.418
uay+3.309
 Maher+2.937
MIT+2.893
isine+2.865
Neg logit contributions
ropolitan-2.703
ascar-2.663
mph-2.597
rolet-2.532
aned-2.520
TokenFriday
Token ID20610
Feature activation-6.70e+00

Pos logit contributions
bis+3.302
uay+3.199
MIT+2.841
 Maher+2.761
prints+2.752
Neg logit contributions
ropolitan-2.624
ascar-2.558
mph-2.480
rolet-2.451
aned-2.446
Token,
Token ID11
Feature activation-5.71e+00

Pos logit contributions
ascar+3.664
ropolitan+3.661
mph+3.622
aned+3.588
 ►+3.544
Neg logit contributions
bis-5.373
uay-5.291
isine-4.709
MIT-4.649
�醒-4.643
Token April
Token ID3035
Feature activation+3.87e-01

Pos logit contributions
ropolitan+2.233
mph+2.218
 ED+2.192
ascar+2.191
aned+2.158
Neg logit contributions
bis-5.540
uay-5.442
isine-4.971
�醒-4.960
MIT-4.889
Token 3
Token ID513
Feature activation+1.30e+00

Pos logit contributions
bis+0.290
uay+0.283
 Maher+0.245
MIT+0.244
isine+0.242
Neg logit contributions
ropolitan-0.255
ascar-0.252
mph-0.248
aned-0.243
mith-0.241
Tokenrd
Token ID4372
Feature activation-5.97e-01

Pos logit contributions
bis+0.986
uay+0.965
 Maher+0.837
MIT+0.831
isine+0.824
Neg logit contributions
ropolitan-0.845
ascar-0.835
mph-0.821
aned-0.803
mith-0.799
Token,
Token ID11
Feature activation+2.25e+00

Pos logit contributions
ropolitan+0.369
ascar+0.365
mph+0.360
aned+0.352
mith+0.351
Neg logit contributions
bis-0.467
uay-0.458
 Maher-0.397
MIT-0.396
isine-0.395
Token 2015
Token ID1853
Feature activation+1.33e+00

Pos logit contributions
bis+1.896
uay+1.856
 Maher+1.642
MIT+1.628
isine+1.608
Neg logit contributions
ropolitan-1.277
ascar-1.255
mph-1.229
aned-1.197
mith-1.187
Token
Token ID198
Feature activation+6.98e+00

Pos logit contributions
bis+1.001
uay+0.976
 Maher+0.847
MIT+0.841
isine+0.833
Neg logit contributions
ropolitan-0.875
ascar-0.864
mph-0.849
aned-0.831
mith-0.827
Token
Token ID198
Feature activation+8.04e+00

Pos logit contributions
bis+5.182
uay+5.044
MIT+4.504
 Maher+4.368
timer+4.292
Neg logit contributions
ropolitan-4.522
ascar-4.442
mph-4.299
aned-4.250
rolet-4.205
TokenFR
Token ID10913
Feature activation+2.36e+00

Pos logit contributions
bis+6.223
uay+5.970
MIT+5.475
prints+5.224
timer+5.219
Neg logit contributions
ropolitan-5.013
ascar-4.840
rolet-4.637
aned-4.584
mph-4.581
TokenES
Token ID1546
Feature activation+1.49e+00

Pos logit contributions
bis+1.941
uay+1.901
 Maher+1.672
MIT+1.666
isine+1.640
Neg logit contributions
ropolitan-1.380
ascar-1.358
mph-1.331
aned-1.299
mith-1.290
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
ropolitan+0.274
ascar+0.271
mph+0.266
mith+0.259
aned+0.259
Neg logit contributions
bis-0.361
uay-0.354
 Maher-0.310
MIT-0.305
isine-0.305
Token
Token ID447
Feature activation+4.34e-01

Pos logit contributions
bis+0.963
uay+0.940
 Maher+0.814
MIT+0.808
isine+0.801
Neg logit contributions
ropolitan-0.865
ascar-0.854
mph-0.840
aned-0.823
mith-0.818
Token
Token ID251
Feature activation+6.36e+00

Pos logit contributions
bis+0.306
uay+0.298
 Maher+0.255
MIT+0.254
isine+0.253
Neg logit contributions
ropolitan-0.304
ascar-0.301
mph-0.297
aned-0.291
mith-0.288
Token If
Token ID1002
Feature activation+1.57e+00

Pos logit contributions
bis+4.465
uay+4.301
 Maher+3.778
MIT+3.741
timer+3.647
Neg logit contributions
ropolitan-4.443
ascar-4.344
mph-4.214
aned-4.189
rolet-4.148
Token it
Token ID340
Feature activation+1.14e+01

Pos logit contributions
bis+1.249
uay+1.222
 Maher+1.067
MIT+1.060
isine+1.052
Neg logit contributions
ropolitan-0.968
ascar-0.955
mph-0.939
aned-0.916
mith-0.912
Token is
Token ID318
Feature activation+7.85e+00

Pos logit contributions
bis+8.032
uay+7.894
prints+6.726
MIT+6.722
 Maher+6.705
Neg logit contributions
ropolitan-7.214
ascar-6.958
rolet-6.906
mph-6.830
aned-6.727
Token,
Token ID11
Feature activation+3.11e+00

Pos logit contributions
bis+5.939
uay+5.684
MIT+5.078
 Maher+5.050
timer+4.974
Neg logit contributions
ropolitan-4.969
ascar-4.849
mph-4.635
rolet-4.619
aned-4.528
Token run
Token ID1057
Feature activation+1.69e+00

Pos logit contributions
bis+2.497
uay+2.433
 Maher+2.150
MIT+2.132
timer+2.088
Neg logit contributions
ropolitan-1.897
ascar-1.861
mph-1.816
aned-1.772
rolet-1.764
Token the
Token ID262
Feature activation+5.48e+00

Pos logit contributions
bis+1.396
uay+1.366
 Maher+1.201
MIT+1.194
isine+1.184
Neg logit contributions
ropolitan-0.979
ascar-0.966
mph-0.947
aned-0.924
mith-0.919
Token power
Token ID1176
Feature activation+4.37e+00

Pos logit contributions
bis+3.665
uay+3.496
 Maher+3.060
MIT+2.972
timer+2.970
Neg logit contributions
ropolitan-4.079
ascar-3.952
mph-3.909
aned-3.835
rolet-3.814
Token off
Token ID572
Feature activation-4.82e-01

Pos logit contributions
bis+3.415
uay+3.314
 Maher+2.918
MIT+2.901
timer+2.876
Neg logit contributions
ropolitan-2.729
ascar-2.677
mph-2.605
aned-2.562
rolet-2.547
Tokenth
Token ID400
Feature activation-1.09e+01

Pos logit contributions
mph+2.564
ropolitan+2.540
ascar+2.428
aned+2.413
mith+2.363
Neg logit contributions
bis-3.649
uay-3.616
 Maher-3.205
MIT-3.148
isine-3.135
Token-
Token ID12
Feature activation-1.16e+01

Pos logit contributions
mph+5.419
ropolitan+5.378
 ED+5.263
aned+5.208
ascar+5.164
Neg logit contributions
uay-8.995
bis-8.885
isine-7.982
MIT-7.914
icter-7.809
Tokensecond
Token ID12227
Feature activation-2.26e+00

Pos logit contributions
mph+3.393
weekly+3.156
aned+2.880
jew+2.859
hem+2.842
Neg logit contributions
uay-12.353
bis-11.758
 Maher-11.731
�醒-11.683
isine-11.489
Token lead
Token ID1085
Feature activation+6.37e+00

Pos logit contributions
ropolitan+0.760
ascar+0.738
mph+0.736
aned+0.711
mith+0.690
Neg logit contributions
bis-2.406
uay-2.372
MIT-2.144
isine-2.132
 Maher-2.128
Token.
Token ID13
Feature activation+3.84e+00

Pos logit contributions
bis+4.579
uay+4.441
 Maher+3.904
MIT+3.788
isine+3.765
Neg logit contributions
ropolitan-4.316
ascar-4.280
mph-4.108
aned-4.047
rolet-4.008
Token When
Token ID1649
Feature activation+2.90e+00

Pos logit contributions
bis+2.848
uay+2.768
 Maher+2.436
MIT+2.391
 Labrador+2.372
Neg logit contributions
ropolitan-2.563
ascar-2.525
mph-2.460
aned-2.435
rolet-2.393
Token Bolton
Token ID35293
Feature activation-4.38e-01

Pos logit contributions
bis+2.277
uay+2.222
 Maher+1.952
MIT+1.921
isine+1.904
Neg logit contributions
ropolitan-1.807
ascar-1.777
mph-1.738
aned-1.706
rolet-1.688
Token only
Token ID691
Feature activation-8.06e+00

Pos logit contributions
ropolitan+0.254
ascar+0.249
mph+0.248
aned+0.242
mith+0.242
Neg logit contributions
bis-0.360
uay-0.354
MIT-0.312
 Maher-0.310
isine-0.309
Token semi
Token ID10663
Feature activation-6.78e+00

Pos logit contributions
aned+4.275
 tempted+4.204
mith+4.174
ropolitan+4.171
mph+4.152
Neg logit contributions
bis-6.535
uay-6.524
MIT-5.923
isine-5.890
icter-5.844
Token-
Token ID12
Feature activation-4.54e+00

Pos logit contributions
ropolitan+3.838
aned+3.816
ascar+3.807
mph+3.771
weekly+3.661
Neg logit contributions
bis-5.428
uay-5.287
 Maher-4.710
MIT-4.700
isine-4.659
Tokencle
Token ID2375
Feature activation-7.93e+00

Pos logit contributions
mph+2.852
aned+2.844
ropolitan+2.812
weekly+2.785
ascar+2.779
Neg logit contributions
uay-3.351
bis-3.334
 Maher-3.064
isine-2.971
 Labrador-2.908
Token.
Token ID13
Feature activation-2.10e-02

Pos logit contributions
bis+2.032
uay+1.977
 Maher+1.728
MIT+1.707
isine+1.695
Neg logit contributions
ropolitan-1.743
ascar-1.725
mph-1.696
aned-1.656
mith-1.639
Token Alex
Token ID4422
Feature activation+2.56e+00

Pos logit contributions
ropolitan+0.013
ascar+0.013
mph+0.013
aned+0.012
mith+0.012
Neg logit contributions
bis-0.016
uay-0.016
isine-0.014
MIT-0.014
 Maher-0.014
Tokenei
Token ID20295
Feature activation+7.05e-01

Pos logit contributions
bis+1.531
uay+1.486
 Maher+1.243
MIT+1.223
isine+1.204
Neg logit contributions
ropolitan-2.065
ascar-2.047
mph-2.018
aned-1.978
mith-1.973
Token Naval
Token ID20818
Feature activation+4.15e+00

Pos logit contributions
bis+0.499
uay+0.486
 Maher+0.416
MIT+0.415
isine+0.411
Neg logit contributions
ropolitan-0.494
ascar-0.487
mph-0.478
aned-0.470
mith-0.467
Tokenny
Token ID3281
Feature activation-3.09e+00

Pos logit contributions
bis+3.666
uay+3.602
 Maher+3.113
timer+3.094
MIT+3.087
Neg logit contributions
ropolitan-2.170
ascar-2.146
mph-2.065
rolet-2.022
mith-2.008
Token has
Token ID468
Feature activation+6.77e+00

Pos logit contributions
ropolitan+1.894
ascar+1.881
mph+1.834
aned+1.809
mith+1.806
Neg logit contributions
bis-2.399
uay-2.335
MIT-2.038
isine-2.032
 Maher-2.029
Token been
Token ID587
Feature activation+7.88e-01

Pos logit contributions
bis+4.723
uay+4.535
 Maher+4.002
 Labrador+3.858
MIT+3.838
Neg logit contributions
ropolitan-4.760
ascar-4.648
mph-4.583
rolet-4.481
aned-4.464
Token the
Token ID262
Feature activation+3.74e+00

Pos logit contributions
bis+0.718
uay+0.703
 Maher+0.627
MIT+0.624
isine+0.619
Neg logit contributions
ropolitan-0.391
ascar-0.385
mph-0.377
aned-0.367
mith-0.363
Token least
Token ID1551
Feature activation-1.02e+00

Pos logit contributions
bis+2.429
uay+2.382
 Maher+2.031
MIT+2.001
 Labrador+1.967
Neg logit contributions
ropolitan-2.818
ascar-2.775
mph-2.744
rolet-2.668
aned-2.666
Token lucky
Token ID9670
Feature activation+5.98e+00

Pos logit contributions
ropolitan+0.598
ascar+0.592
mph+0.581
aned+0.571
mith+0.564
Neg logit contributions
bis-0.843
uay-0.821
 Maher-0.718
isine-0.716
MIT-0.716
Token:
Token ID25
Feature activation-1.20e+00

Pos logit contributions
bis+4.398
uay+4.292
 Maher+3.782
MIT+3.734
 Labrador+3.676
Neg logit contributions
ropolitan-3.931
ascar-3.878
mph-3.805
aned-3.731
rolet-3.706
Token meeting
Token ID3249
Feature activation+4.67e+00

Pos logit contributions
bis+3.050
uay+2.969
 Maher+2.638
MIT+2.616
isine+2.579
Neg logit contributions
ropolitan-2.059
ascar-2.046
mph-1.989
aned-1.946
rolet-1.925
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
bis+3.479
uay+3.378
 Maher+2.975
MIT+2.926
timer+2.894
Neg logit contributions
ropolitan-3.034
ascar-3.023
mph-2.952
aned-2.907
rolet-2.864
Token
Token ID198
Feature activation-2.12e+00

Pos logit contributions
bis+0.782
uay+0.765
 Maher+0.655
MIT+0.653
isine+0.650
Neg logit contributions
ropolitan-0.744
ascar-0.734
mph-0.724
mith-0.707
aned-0.707
Token
Token ID198
Feature activation+8.41e-02

Pos logit contributions
ropolitan+1.384
ascar+1.369
mph+1.367
mith+1.332
aned+1.325
Neg logit contributions
bis-1.572
uay-1.543
isine-1.335
 Maher-1.333
icter-1.327
Token"
Token ID1
Feature activation-4.94e+00

Pos logit contributions
bis+0.065
uay+0.064
 Maher+0.056
isine+0.055
MIT+0.055
Neg logit contributions
ropolitan-0.053
ascar-0.052
mph-0.052
aned-0.050
mith-0.050
TokenThe
Token ID464
Feature activation-1.79e+00

Pos logit contributions
mph+2.713
Lex+2.678
ascar+2.673
ropolitan+2.657
mith+2.650
Neg logit contributions
bis-4.069
uay-4.030
isine-3.610
 Maher-3.537
icter-3.529
Token real
Token ID1103
Feature activation-8.37e-01

Pos logit contributions
ropolitan+1.067
ascar+1.048
mph+1.044
aned+1.018
mith+1.016
Neg logit contributions
bis-1.439
uay-1.406
MIT-1.230
isine-1.230
 Maher-1.219
Token decision
Token ID2551
Feature activation-2.84e+00

Pos logit contributions
ropolitan+0.541
ascar+0.534
mph+0.525
mith+0.513
aned+0.513
Neg logit contributions
bis-0.637
uay-0.622
MIT-0.536
 Maher-0.536
isine-0.534
Token is
Token ID318
Feature activation-1.96e+00

Pos logit contributions
ropolitan+1.702
ascar+1.670
mph+1.642
mith+1.625
aned+1.595
Neg logit contributions
bis-2.279
uay-2.237
isine-1.944
MIT-1.939
 Maher-1.914
Token whether
Token ID1771
Feature activation-5.67e+00

Pos logit contributions
ropolitan+1.098
mph+1.084
ascar+1.081
mith+1.053
aned+1.049
Neg logit contributions
bis-1.640
uay-1.608
MIT-1.413
isine-1.410
 Maher-1.389
Token to
Token ID284
Feature activation+2.31e+00

Pos logit contributions
ropolitan+2.976
mph+2.961
ascar+2.905
 ED+2.900
mith+2.874
Neg logit contributions
bis-4.857
uay-4.752
isine-4.262
MIT-4.178
�醒-4.074
Token building
Token ID2615
Feature activation+6.58e+00

Pos logit contributions
bis+7.188
uay+7.072
 Maher+6.174
 Labrador+6.134
 Rossi+6.039
Neg logit contributions
ropolitan-5.649
ascar-5.533
mph-5.212
aned-5.164
rolet-5.151
Token a
Token ID257
Feature activation+7.69e+00

Pos logit contributions
bis+5.080
uay+4.931
 Maher+4.380
 Labrador+4.330
prints+4.307
Neg logit contributions
ropolitan-4.103
ascar-4.007
mph-3.889
rolet-3.850
aned-3.823
Token conflict
Token ID5358
Feature activation-4.25e-01

Pos logit contributions
bis+5.945
uay+5.898
 Labrador+5.186
 Maher+5.122
prints+5.105
Neg logit contributions
ropolitan-4.603
ascar-4.538
mph-4.408
rolet-4.334
aned-4.310
Token between
Token ID1022
Feature activation-3.09e+00

Pos logit contributions
ropolitan+0.263
ascar+0.258
mph+0.255
aned+0.249
mith+0.248
Neg logit contributions
bis-0.335
uay-0.328
MIT-0.286
 Maher-0.286
isine-0.284
Token Mid
Token ID7215
Feature activation-6.01e+00

Pos logit contributions
ropolitan+1.726
ascar+1.704
mph+1.684
 ED+1.646
aned+1.639
Neg logit contributions
bis-2.588
uay-2.517
MIT-2.228
isine-2.209
timer-2.188
Tokenn
Token ID77
Feature activation-3.94e+00

Pos logit contributions
ropolitan+3.763
ascar+3.641
mith+3.584
mph+3.522
aned+3.473
Neg logit contributions
bis-4.620
uay-4.410
isine-3.958
MIT-3.934
 Maher-3.934
Tokenighter
Token ID4799
Feature activation-3.80e+00

Pos logit contributions
ascar+1.715
ropolitan+1.639
mph+1.594
aned+1.550
mith+1.535
Neg logit contributions
bis-3.854
uay-3.717
 Maher-3.411
MIT-3.366
isine-3.335
Token and
Token ID290
Feature activation-3.39e+00

Pos logit contributions
ropolitan+2.280
ascar+2.248
mph+2.224
mith+2.177
aned+2.162
Neg logit contributions
bis-2.999
uay-2.934
MIT-2.609
isine-2.550
 Maher-2.541
Token Dick
Token ID11740
Feature activation+1.37e+01

Pos logit contributions
ropolitan+1.969
ascar+1.936
mph+1.925
 ED+1.885
mith+1.878
Neg logit contributions
bis-2.743
uay-2.694
isine-2.357
MIT-2.354
prints-2.307
Token Grayson
Token ID42657
Feature activation+2.60e+00

Pos logit contributions
uay+9.805
bis+9.783
 Maher+8.842
 Labrador+8.559
 Reilly+8.446
Neg logit contributions
ropolitan-8.152
ascar-7.840
aned-7.701
mph-7.687
mith-7.544
Token,
Token ID11
Feature activation+3.77e-01

Pos logit contributions
bis+1.984
uay+1.929
 Maher+1.682
MIT+1.667
isine+1.650
Neg logit contributions
ropolitan-1.680
ascar-1.649
mph-1.619
aned-1.586
mith-1.573
Token remarkable
Token ID11004
Feature activation+2.56e+00

Pos logit contributions
bis+1.171
uay+1.145
 Maher+1.005
MIT+0.999
isine+0.989
Neg logit contributions
ropolitan-0.862
ascar-0.849
mph-0.833
aned-0.814
mith-0.808
Token conc
Token ID1673
Feature activation+2.80e+00

Pos logit contributions
bis+2.142
uay+2.088
 Maher+1.860
MIT+1.838
prints+1.816
Neg logit contributions
ropolitan-1.460
ascar-1.429
mph-1.396
aned-1.363
rolet-1.361
Tokenord
Token ID585
Feature activation-3.26e+00

Pos logit contributions
bis+2.790
uay+2.737
 Maher+2.459
MIT+2.448
isine+2.440
Neg logit contributions
ropolitan-1.148
ascar-1.113
mph-1.087
aned-1.054
rolet-1.045
Tokenances
Token ID1817
Feature activation-2.53e+00

Pos logit contributions
ropolitan+1.430
ascar+1.380
mph+1.355
aned+1.340
ruction+1.298
Neg logit contributions
bis-3.131
uay-3.100
 Maher-2.796
MIT-2.775
timer-2.740
Token between
Token ID1022
Feature activation-1.86e-01

Pos logit contributions
ascar+1.484
ropolitan+1.484
mph+1.472
mith+1.451
aned+1.444
Neg logit contributions
bis-2.021
uay-2.005
MIT-1.740
isine-1.738
 Maher-1.728
Token samples
Token ID8405
Feature activation+9.56e-03

Pos logit contributions
ropolitan+0.111
ascar+0.110
mph+0.108
aned+0.106
mith+0.105
Neg logit contributions
bis-0.150
uay-0.148
MIT-0.128
 Maher-0.128
isine-0.127
Token from
Token ID422
Feature activation+5.71e+00

Pos logit contributions
bis+0.007
uay+0.007
MIT+0.006
 Maher+0.006
isine+0.006
Neg logit contributions
ropolitan-0.006
ascar-0.006
mph-0.006
aned-0.006
mith-0.006
Token different
Token ID1180
Feature activation+7.94e-01

Pos logit contributions
bis+4.225
uay+4.118
 Maher+3.650
 Labrador+3.571
MIT+3.508
Neg logit contributions
ropolitan-3.747
ascar-3.704
mph-3.575
rolet-3.560
mith-3.503
Token fossils
Token ID34066
Feature activation+1.34e+00

Pos logit contributions
bis+0.624
uay+0.611
MIT+0.531
 Maher+0.531
isine+0.524
Neg logit contributions
ropolitan-0.494
ascar-0.487
mph-0.480
aned-0.469
mith-0.465
Token,
Token ID11
Feature activation+8.77e-01

Pos logit contributions
bis+1.034
uay+1.010
 Maher+0.880
MIT+0.875
isine+0.865
Neg logit contributions
ropolitan-0.854
ascar-0.842
mph-0.827
aned-0.809
mith-0.805
Token geographic
Token ID22987
Feature activation-3.55e+00

Pos logit contributions
bis+0.765
uay+0.750
 Maher+0.663
MIT+0.661
isine+0.655
Neg logit contributions
ropolitan-0.470
ascar-0.463
mph-0.454
aned-0.442
mith-0.439
Tokenbuilder
Token ID38272
Feature activation+2.55e+00

Pos logit contributions
bis+5.941
uay+5.735
 Maher+5.127
 Labrador+5.003
isine+4.958
Neg logit contributions
ropolitan-5.106
ascar-4.984
rolet-4.778
aned-4.738
mph-4.710
Token mus
Token ID1928
Feature activation-3.31e+00

Pos logit contributions
bis+2.057
uay+2.012
 Maher+1.774
MIT+1.748
isine+1.737
Neg logit contributions
ropolitan-1.543
ascar-1.512
mph-1.476
aned-1.443
rolet-1.434
Tokening
Token ID278
Feature activation-8.03e+00

Pos logit contributions
mph+1.782
ropolitan+1.773
ascar+1.764
mith+1.737
aned+1.686
Neg logit contributions
bis-2.809
uay-2.753
 Maher-2.466
MIT-2.459
isine-2.425
Token about
Token ID546
Feature activation-4.91e+00

Pos logit contributions
mith+3.780
ascar+3.776
mph+3.775
ropolitan+3.667
 ED+3.611
Neg logit contributions
bis-6.973
uay-6.892
MIT-6.135
isine-6.093
timer-6.056
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
mph+2.716
ascar+2.681
ropolitan+2.658
aned+2.582
mith+2.577
Neg logit contributions
bis-4.064
uay-4.016
MIT-3.561
isine-3.494
timer-3.454
Token ­
Token ID22020
Feature activation+8.39e-01

Pos logit contributions
ropolitan+0.743
ascar+0.739
mph+0.734
aned+0.712
mith+0.709
Neg logit contributions
bis-0.993
uay-0.974
MIT-0.848
 Maher-0.844
isine-0.838
TokenT
Token ID51
Feature activation-3.09e+00

Pos logit contributions
bis+0.645
uay+0.631
 Maher+0.551
MIT+0.544
isine+0.541
Neg logit contributions
ropolitan-0.535
ascar-0.528
mph-0.522
aned-0.508
mith-0.506
Tokenitan
Token ID18642
Feature activation+1.39e+00

Pos logit contributions
ropolitan+1.856
ascar+1.847
mph+1.809
aned+1.789
rolet+1.767
Neg logit contributions
bis-2.437
uay-2.398
 Maher-2.126
MIT-2.099
isine-2.085
Tokenic
Token ID291
Feature activation-2.24e+00

Pos logit contributions
bis+0.989
uay+0.963
 Maher+0.830
MIT+0.823
isine+0.814
Neg logit contributions
ropolitan-0.962
ascar-0.949
mph-0.935
aned-0.916
mith-0.910
Token.
Token ID13
Feature activation-2.47e-01

Pos logit contributions
ropolitan+1.347
ascar+1.335
mph+1.329
aned+1.287
mith+1.278
Neg logit contributions
bis-1.773
uay-1.754
MIT-1.529
 Maher-1.510
isine-1.498
Token No
Token ID1400
Feature activation-1.62e+00

Pos logit contributions
ropolitan+0.161
ascar+0.159
mph+0.156
mith+0.153
aned+0.152
Neg logit contributions
bis-0.187
uay-0.183
isine-0.157
MIT-0.157
 Maher-0.157
Token Orange
Token ID11942
Feature activation+2.01e+00

Pos logit contributions
ropolitan+3.078
mith+2.967
ascar+2.952
mph+2.939
aned+2.821
Neg logit contributions
bis-7.385
uay-7.210
isine-6.541
MIT-6.494
�醒-6.490
Token"
Token ID1
Feature activation-5.40e+00

Pos logit contributions
bis+1.378
uay+1.341
 Maher+1.148
MIT+1.137
isine+1.124
Neg logit contributions
ropolitan-1.452
ascar-1.433
mph-1.412
aned-1.385
mith-1.376
Token and
Token ID290
Feature activation-5.94e+00

Pos logit contributions
ropolitan+3.006
ascar+2.953
mith+2.918
mph+2.904
 ED+2.884
Neg logit contributions
bis-4.454
uay-4.365
MIT-3.881
isine-3.753
timer-3.717
Token "
Token ID366
Feature activation-6.57e+00

Pos logit contributions
ropolitan+3.485
ascar+3.465
mph+3.380
 ED+3.360
mith+3.316
Neg logit contributions
bis-4.739
uay-4.570
MIT-4.015
isine-3.980
timer-3.925
TokenOne
Token ID3198
Feature activation+8.26e+00

Pos logit contributions
Lex+3.752
mph+3.643
ropolitan+3.628
ascar+3.617
mith+3.588
Neg logit contributions
bis-5.230
uay-5.189
isine-4.626
 Maher-4.530
icter-4.498
Token Fle
Token ID12005
Feature activation-6.37e+00

Pos logit contributions
bis+5.467
uay+5.439
 Maher+4.776
MIT+4.629
timer+4.570
Neg logit contributions
ropolitan-5.748
ascar-5.736
mph-5.660
aned-5.629
rolet-5.552
Tokenw
Token ID86
Feature activation-6.61e+00

Pos logit contributions
mph+2.568
ascar+2.522
ropolitan+2.486
aned+2.460
hem+2.441
Neg logit contributions
bis-6.291
uay-6.104
MIT-5.621
�醒-5.529
isine-5.513
Token Over
Token ID3827
Feature activation-1.30e+00

Pos logit contributions
ropolitan+3.863
ascar+3.803
mph+3.735
aned+3.656
weekly+3.615
Neg logit contributions
uay-5.214
bis-5.177
MIT-4.671
�醒-4.479
icter-4.461
Token the
Token ID262
Feature activation-3.07e+00

Pos logit contributions
ropolitan+0.748
ascar+0.733
mph+0.712
aned+0.699
mith+0.689
Neg logit contributions
bis-1.083
uay-1.067
 Maher-0.928
MIT-0.925
isine-0.921
Token C
Token ID327
Feature activation-4.59e+00

Pos logit contributions
ropolitan+1.512
ascar+1.487
aned+1.451
mph+1.435
Lex+1.413
Neg logit contributions
bis-2.790
uay-2.779
isine-2.428
MIT-2.410
 Maher-2.403
Tokenuck
Token ID1347
Feature activation-5.53e-01

Pos logit contributions
ascar+2.396
ropolitan+2.358
aned+2.330
mph+2.281
rous+2.243
Neg logit contributions
bis-3.991
uay-3.990
MIT-3.532
�醒-3.476
 Maher-3.466
Token LGBT
Token ID9916
Feature activation+1.05e+00

Pos logit contributions
ropolitan+0.737
mph+0.723
ascar+0.722
aned+0.704
mith+0.689
Neg logit contributions
bis-1.147
uay-1.132
MIT-0.995
isine-0.987
 Maher-0.982
Token people
Token ID661
Feature activation+2.53e-01

Pos logit contributions
bis+0.875
uay+0.857
 Maher+0.755
MIT+0.750
isine+0.744
Neg logit contributions
ropolitan-0.600
ascar-0.591
mph-0.580
aned-0.566
mith-0.562
Token,
Token ID11
Feature activation+5.57e+00

Pos logit contributions
bis+0.208
uay+0.204
MIT+0.178
 Maher+0.178
isine+0.176
Neg logit contributions
ropolitan-0.148
ascar-0.146
mph-0.144
aned-0.140
mith-0.140
Token who
Token ID508
Feature activation+4.07e+00

Pos logit contributions
bis+4.361
uay+4.217
 Maher+3.802
 Labrador+3.690
isine+3.654
Neg logit contributions
ropolitan-3.426
ascar-3.393
mph-3.243
rolet-3.197
aned-3.152
Token are
Token ID389
Feature activation+4.15e+00

Pos logit contributions
bis+3.087
uay+2.989
 Maher+2.632
MIT+2.581
 Labrador+2.559
Neg logit contributions
ropolitan-2.622
ascar-2.603
mph-2.545
rolet-2.475
aned-2.460
Token fighting
Token ID4330
Feature activation-1.13e+01

Pos logit contributions
bis+3.373
uay+3.296
 Maher+2.945
MIT+2.850
 Labrador+2.842
Neg logit contributions
ropolitan-2.461
ascar-2.413
mph-2.334
rolet-2.297
aned-2.264
Token back
Token ID736
Feature activation+2.01e+00

Pos logit contributions
 ED+5.370
mph+5.340
ropolitan+5.219
Lex+4.937
aned+4.936
Neg logit contributions
bis-9.527
uay-9.522
�醒-8.740
icter-8.629
isine-8.559
Token against
Token ID1028
Feature activation-4.19e+00

Pos logit contributions
bis+1.459
uay+1.418
 Maher+1.230
MIT+1.216
isine+1.206
Neg logit contributions
ropolitan-1.372
ascar-1.358
mph-1.331
aned-1.308
mith-1.295
Token street
Token ID4675
Feature activation-6.32e+00

Pos logit contributions
ropolitan+2.310
mph+2.277
ascar+2.246
 ED+2.206
aned+2.182
Neg logit contributions
bis-3.500
uay-3.496
MIT-3.044
timer-3.008
isine-2.998
Token harassment
Token ID10556
Feature activation-3.84e-01

Pos logit contributions
mph+2.451
ascar+2.366
ropolitan+2.356
 ED+2.324
mith+2.299
Neg logit contributions
bis-6.209
uay-6.198
MIT-5.574
�醒-5.493
timer-5.443
Token.
Token ID13
Feature activation-1.87e+00

Pos logit contributions
ropolitan+0.237
ascar+0.232
mph+0.230
mith+0.224
aned+0.224
Neg logit contributions
bis-0.304
uay-0.299
MIT-0.259
 Maher-0.258
isine-0.255
Token dollar
Token ID8872
Feature activation-1.14e+00

Pos logit contributions
ropolitan+2.270
mph+2.187
ascar+2.178
aned+2.137
mith+2.081
Neg logit contributions
bis-3.872
uay-3.786
 Maher-3.382
MIT-3.368
prints-3.343
Token campaign
Token ID1923
Feature activation-1.15e+00

Pos logit contributions
ropolitan+0.657
ascar+0.650
mph+0.637
aned+0.622
mith+0.620
Neg logit contributions
bis-0.938
uay-0.922
 Maher-0.806
MIT-0.804
isine-0.800
Token to
Token ID284
Feature activation-3.57e+00

Pos logit contributions
ropolitan+0.696
ascar+0.685
mph+0.678
mith+0.662
aned+0.661
Neg logit contributions
bis-0.914
uay-0.897
 Maher-0.779
MIT-0.779
isine-0.766
Token finish
Token ID5461
Feature activation-1.07e+00

Pos logit contributions
ropolitan+1.717
ascar+1.685
mph+1.670
mith+1.639
aned+1.622
Neg logit contributions
bis-3.224
uay-3.194
 Maher-2.834
MIT-2.820
prints-2.816
Token the
Token ID262
Feature activation-4.73e+00

Pos logit contributions
ropolitan+0.641
ascar+0.629
mph+0.623
mith+0.605
aned+0.602
Neg logit contributions
bis-0.856
uay-0.840
MIT-0.731
 Maher-0.728
isine-0.720
Token work
Token ID670
Feature activation-1.36e+01

Pos logit contributions
ascar+2.527
mph+2.501
ropolitan+2.487
mith+2.403
 ED+2.403
Neg logit contributions
bis-3.995
uay-3.954
MIT-3.477
 Maher-3.418
timer-3.412
Token of
Token ID286
Feature activation-4.17e+00

Pos logit contributions
mith+6.319
mph+6.218
ropolitan+6.191
 ►+6.119
ascar+6.096
Neg logit contributions
bis-10.841
uay-10.812
isine-9.445
timer-9.369
MIT-9.283
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
ropolitan+2.341
mph+2.294
ascar+2.278
 ED+2.222
aned+2.220
Neg logit contributions
bis-3.440
uay-3.367
MIT-2.958
timer-2.910
prints-2.906
Token genocide
Token ID20744
Feature activation+1.52e+00

Pos logit contributions
bis+0.791
uay+0.772
 Maher+0.671
MIT+0.667
isine+0.661
Neg logit contributions
ropolitan-0.661
ascar-0.652
mph-0.642
aned-0.628
mith-0.624
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
bis+1.161
uay+1.131
 Maher+0.987
MIT+0.978
isine+0.967
Neg logit contributions
ropolitan-0.980
ascar-0.966
mph-0.947
aned-0.927
mith-0.919
Token
Token ID198
Feature activation-3.11e-01

Pos logit contributions
ropolitan+0.830
ascar+0.818
mph+0.809
mith+0.789
aned+0.787
Neg logit contributions
bis-0.974
uay-0.961
isine-0.826
MIT-0.821
 Maher-0.817
Token losing
Token ID6078
Feature activation+1.28e+00

Pos logit contributions
ropolitan+1.808
mph+1.795
ascar+1.792
aned+1.746
mith+1.739
Neg logit contributions
bis-2.408
uay-2.344
MIT-2.057
isine-2.049
 Maher-2.025
Token 75
Token ID5441
Feature activation+2.18e+00

Pos logit contributions
bis+1.004
uay+0.981
 Maher+0.855
MIT+0.851
isine+0.844
Neg logit contributions
ropolitan-0.797
ascar-0.785
mph-0.773
aned-0.755
mith-0.750
Token billion
Token ID2997
Feature activation-7.76e+00

Pos logit contributions
bis+1.758
uay+1.717
 Maher+1.505
MIT+1.497
isine+1.481
Neg logit contributions
ropolitan-1.317
ascar-1.298
mph-1.272
aned-1.244
mith-1.236
Token tons
Token ID10860
Feature activation-1.16e+01

Pos logit contributions
mph+3.276
ropolitan+3.208
 ►+3.096
 ED+3.063
ascar+3.017
Neg logit contributions
uay-7.228
bis-7.226
isine-6.539
timer-6.482
 Maher-6.432
Token of
Token ID286
Feature activation-4.71e+00

Pos logit contributions
mith+5.189
mph+5.175
weekly+5.163
 ►+5.085
 weekly+5.073
Neg logit contributions
uay-9.749
bis-9.623
mbuds-8.765
 Maher-8.637
�醒-8.559
Token ice
Token ID4771
Feature activation-1.03e+01

Pos logit contributions
mph+3.184
ropolitan+3.175
ascar+3.143
 ED+3.113
aned+3.069
Neg logit contributions
bis-3.321
uay-3.304
MIT-2.794
timer-2.786
isine-2.765
Token every
Token ID790
Feature activation-1.61e+00

Pos logit contributions
mph+5.016
ascar+4.878
weekly+4.868
 ►+4.867
mith+4.783
Neg logit contributions
uay-8.849
bis-8.524
mbuds-7.640
 Maher-7.638
�醒-7.585
Token year
Token ID614
Feature activation-3.23e+00

Pos logit contributions
ropolitan+0.907
ascar+0.898
mph+0.893
aned+0.861
mith+0.854
Neg logit contributions
bis-1.353
uay-1.330
 Maher-1.158
isine-1.153
MIT-1.152
Token]
Token ID60
Feature activation+1.10e+00

Pos logit contributions
ascar+1.994
ropolitan+1.992
mph+1.988
mith+1.935
 ►+1.927
Neg logit contributions
bis-2.464
uay-2.436
 Maher-2.104
MIT-2.096
isine-2.090
Token
Token ID198
Feature activation+6.86e-01

Pos logit contributions
bis+0.764
uay+0.744
 Maher+0.639
MIT+0.634
isine+0.622
Neg logit contributions
ropolitan-0.786
ascar-0.776
mph-0.763
aned-0.750
mith-0.744
Token
Token ID198
Feature activation+2.66e+00

Pos logit contributions
bis+0.474
uay+0.461
 Maher+0.395
MIT+0.392
isine+0.385
Neg logit contributions
ropolitan-0.494
ascar-0.487
mph-0.478
aned-0.470
rolet-0.466
Token that
Token ID326
Feature activation-1.24e+01

Pos logit contributions
ropolitan+4.473
ascar+4.399
 ED+4.382
mph+4.373
aned+4.270
Neg logit contributions
bis-7.333
uay-7.212
isine-6.376
timer-6.292
MIT-6.290
Token claimed
Token ID4752
Feature activation-1.01e+01

Pos logit contributions
 ED+5.903
ascar+5.705
aned+5.671
 tempted+5.595
 twe+5.434
Neg logit contributions
bis-10.559
uay-10.271
�醒-9.330
isine-9.183
prints-9.129
Token the
Token ID262
Feature activation-1.13e+01

Pos logit contributions
ascar+4.849
 ED+4.798
ropolitan+4.689
aned+4.549
 twe+4.538
Neg logit contributions
bis-9.048
uay-8.752
isine-7.667
MIT-7.634
mbuds-7.579
Token life
Token ID1204
Feature activation+5.10e-01

Pos logit contributions
 ED+5.694
ascar+5.663
aned+5.412
 ►+5.336
mph+5.326
Neg logit contributions
bis-9.650
uay-9.261
timer-8.386
mbuds-8.327
 Maher-8.158
Token of
Token ID286
Feature activation-9.49e+00

Pos logit contributions
bis+0.389
uay+0.379
 Maher+0.329
MIT+0.328
isine+0.325
Neg logit contributions
ropolitan-0.329
ascar-0.325
mph-0.319
aned-0.312
mith-0.311
Token activist
Token ID11276
Feature activation-1.52e+01

Pos logit contributions
 ED+4.949
ascar+4.666
aned+4.647
ropolitan+4.630
 twe+4.563
Neg logit contributions
bis-8.229
uay-7.953
prints-7.044
isine-6.969
icter-6.946
Token Heather
Token ID24253
Feature activation-8.88e+00

Pos logit contributions
 ED+5.691
 twe+5.216
aned+4.929
ascar+4.927
 ►+4.892
Neg logit contributions
bis-14.419
uay-14.229
mbuds-13.086
ozy-12.745
MIT-12.744
Token He
Token ID679
Feature activation-3.21e-01

Pos logit contributions
mph+3.337
hem+3.235
aned+3.212
ascar+3.123
ropolitan+3.106
Neg logit contributions
bis-9.050
uay-8.881
�醒-7.995
-7.901
MIT-7.885
Tokenyer
Token ID9860
Feature activation-1.11e+00

Pos logit contributions
ropolitan+0.258
ascar+0.256
mph+0.252
aned+0.248
mith+0.247
Neg logit contributions
bis-0.193
uay-0.188
 Maher-0.157
MIT-0.155
isine-0.153
Token.)
Token ID2014
Feature activation-3.69e+00

Pos logit contributions
ropolitan+0.659
ascar+0.654
mph+0.643
mith+0.631
aned+0.626
Neg logit contributions
bis-0.893
uay-0.877
MIT-0.764
isine-0.760
 Maher-0.758
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
ropolitan+2.296
ascar+2.237
mph+2.207
mith+2.177
 ED+2.161
Neg logit contributions
bis-2.845
uay-2.780
isine-2.473
icter-2.393
prints-2.388
Token::
Token ID3712
Feature activation-8.84e-01

Pos logit contributions
ropolitan+0.934
ascar+0.916
mph+0.899
mith+0.867
aned+0.860
Neg logit contributions
bis-1.902
uay-1.868
 Maher-1.671
MIT-1.659
isine-1.651
TokenCenter
Token ID23656
Feature activation+1.58e+00

Pos logit contributions
ropolitan+0.484
ascar+0.479
mph+0.476
aned+0.459
Lex+0.459
Neg logit contributions
bis-0.751
uay-0.740
 Maher-0.651
MIT-0.643
isine-0.643
Token $
Token ID720
Feature activation+3.20e+00

Pos logit contributions
bis+1.188
uay+1.160
 Maher+1.007
MIT+1.000
isine+0.989
Neg logit contributions
ropolitan-1.034
ascar-1.020
mph-1.003
aned-0.982
mith-0.976
Tokens
Token ID82
Feature activation+1.85e+00

Pos logit contributions
bis+1.678
uay+1.592
 Maher+1.272
timer+1.272
prints+1.259
Neg logit contributions
ropolitan-2.859
ascar-2.808
rolet-2.738
mph-2.733
aned-2.721
TokenFormat
Token ID26227
Feature activation-1.34e+00

Pos logit contributions
bis+1.579
uay+1.541
MIT+1.376
 Maher+1.360
prints+1.350
Neg logit contributions
ropolitan-1.029
ascar-1.005
mph-0.972
aned-0.964
rolet-0.955
Token.
Token ID13
Feature activation-1.36e+01

Pos logit contributions
ropolitan+0.799
ascar+0.790
mph+0.782
mith+0.760
aned+0.756
Neg logit contributions
bis-1.077
uay-1.053
 Maher-0.922
isine-0.918
MIT-0.916
TokenLine
Token ID13949
Feature activation+1.53e+00

Pos logit contributions
Lex+7.776
mph+7.284
ascar+7.098
hem+7.008
Leader+6.982
Neg logit contributions
uay-9.822
bis-9.418
icter-8.949
 Maher-8.818
isine-8.752
TokenAl
Token ID2348
Feature activation+1.18e+00

Pos logit contributions
bis+1.437
uay+1.409
 Maher+1.261
MIT+1.254
isine+1.243
Neg logit contributions
ropolitan-0.717
ascar-0.703
mph-0.686
aned-0.667
mith-0.660
Tokenignment
Token ID16747
Feature activation-1.39e+00

Pos logit contributions
bis+0.793
uay+0.770
 Maher+0.653
isine+0.648
MIT+0.644
Neg logit contributions
ropolitan-0.876
ascar-0.858
mph-0.851
aned-0.834
rolet-0.829
Token =
Token ID796
Feature activation+6.07e-01

Pos logit contributions
ropolitan+0.759
ascar+0.750
mph+0.736
mith+0.713
aned+0.712
Neg logit contributions
bis-1.196
uay-1.173
 Maher-1.037
MIT-1.032
isine-1.027
Token [
Token ID685
Feature activation+2.84e+00

Pos logit contributions
bis+0.527
uay+0.516
 Maher+0.457
MIT+0.455
isine+0.451
Neg logit contributions
ropolitan-0.327
ascar-0.322
mph-0.315
aned-0.307
mith-0.305