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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and verbs that indicate significant concepts or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     of
    -0.76
     thereof
    -0.75
     Of
    -0.73
    of
    -0.70
     OF
    -0.68
    Of
    -0.62
     thats
    -0.62
    OF
    -0.58
     alot
    -0.58
    needed
    -0.55
    POSITIVE LOGITS
    —"
    0.55
    ,—
    0.51
    —
    0.50
    icides
    0.49
    ;
    0.47
     —
    0.47
    razen
    0.46
    adoes
    0.46
    geries
    0.44
    ,
    0.44
    Act Density 1.245%

    No Known Activations