INDEX
Explanations
194 (1940s)
The neuron fires on temporal indicators—especially years or decade markers (and related terms like “wartime”).
New Auto-Interp
Negative Logits
від
-0.07
postal
-0.07
SignUp
-0.06
گذاری
-0.06
anus
-0.06
XIII
-0.06
Concat
-0.06
MBA
-0.06
ipment
-0.06
<Block
-0.06
POSITIVE LOGITS
815
0.07
边
0.07
окра
0.07
بالرياض
0.06
邊
0.06
disobed
0.06
.centerX
0.06
práv
0.06
讲
0.06
.selectAll
0.06
Activations Density 0.030%