INDEX
Explanations
mentions of individuals named Thomas
New Auto-Interp
Negative Logits
imate
-0.17
ough
-0.16
à¸ĩาà¸Ļ
-0.15
ushman
-0.15
Pros
-0.15
sı
-0.14
verted
-0.14
pros
-0.14
ollapsed
-0.14
s
-0.14
POSITIVE LOGITS
otel
0.15
sonian
0.15
глÑı
0.14
itto
0.14
ston
0.14
strcasecmp
0.14
ẫn
0.14
eton
0.13
Payne
0.13
że
0.13
Activations Density 0.025%