INDEX
Explanations
elements related to films or movies
New Auto-Interp
Negative Logits
―――――
-0.80
ſche
-0.80
Hochspringen
-0.79
Anſ
-0.79
itſelf
-0.77
juſ
-0.76
للاسماء
-0.75
auffi
-0.75
preſent
-0.74
ſind
-0.73
POSITIVE LOGITS
The
1.05
A
0.71
The
0.69
La
0.67
Un
0.62
THE
0.60
Love
0.60
Mr
0.60
0.60
Die
0.59
Activations Density 0.313%