INDEX
Explanations
estimated
The neuron fires on mentions of scheduled timing details—words like “Estimated,” “time,” and “between” used in conveying when something will occur.
New Auto-Interp
Negative Logits
.foundation
-0.07
Tape
-0.07
amente
-0.06
ideshow
-0.06
prü
-0.06
ord
-0.06
catalogue
-0.06
ậm
-0.06
Counter
-0.06
emás
-0.06
POSITIVE LOGITS
expected
0.08
estimate
0.07
estimated
0.07
oppose
0.07
Wh
0.06
قدرت
0.06
gov
0.06
predictions
0.06
illusions
0.06
()
0.06
Activations Density 0.018%