INDEX
Explanations
nuts and seeds
The neuron responds to words for nuts and seeds (e.g. “nuts,” “seeds,” “nozes,” “sementes”).
New Auto-Interp
Negative Logits
.Question
-0.07
structions
-0.06
_learning
-0.06
_Report
-0.06
บอก
-0.06
د
-0.06
measurement
-0.06
기술
-0.06
_bt
-0.06
bour
-0.06
POSITIVE LOGITS
dad
0.07
亜
0.07
helicopters
0.06
Accepted
0.06
Haram
0.06
berries
0.06
tf
0.06
.ant
0.06
mats
0.06
Budapest
0.06
Activations Density 0.020%