Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific types of nested structures or parentheses in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     W
    -0.72
     U
    -0.68
     H
    -0.68
     /
    -0.68
     O
    -0.67
     G
    -0.66
     R
    -0.66
     S
    -0.63
     Se
    -0.61
     and
    -0.61
    POSITIVE LOGITS
     larmes
    1.19
     ainfi
    1.14
     auroit
    1.13
     gouttes
    1.10
     scolaires
    1.10
     inoxydable
    1.09
    Билгалдахарш
    1.07
     $_(
    1.07
    "]=
    1.07
     feroit
    1.05
    Act Density 0.291%

    No Known Activations