INDEX
Explanations
mentions of specific individuals, particularly those named Manny or Manus
New Auto-Interp
Negative Logits
arton
-0.15
emm
-0.15
bson
-0.15
zig
-0.14
068
-0.14
й
-0.14
FromArray
-0.14
walker
-0.14
ritz
-0.14
ãĤĵãģł
-0.14
POSITIVE LOGITS
uales
0.21
resa
0.20
tras
0.19
fred
0.19
ouri
0.18
hattan
0.18
ificent
0.18
ousel
0.17
depressive
0.17
ifest
0.17
Activations Density 0.029%