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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consacré
    -0.34
    someone
    -0.34
     tazas
    -0.34
     kautta
    -0.34
    ...).
    -0.33
     financière
    -0.32
    GETHER
    -0.32
     kemarin
    -0.32
     hiasan
    -0.31
     seragam
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.57
     oprot
    0.55
    +#+#
    0.55
    دانشنامهٔ
    0.54
    jamientos
    0.53
    DMETHOD
    0.53
    BeginContext
    0.53
    tonode
    0.52
    hyrchwyd
    0.52
     snippetHide
    0.50
    Act Density 1.032%

    No Known Activations