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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    names of people or entities, particularly in relation to contexts of action or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.71
    folk
    -0.69
    é¾įå¥ij士
    -0.66
    GW
    -0.59
    LINE
    -0.58
    CHQ
    -0.56
    ä¼
    -0.56
    Gaza
    -0.56
    Background
    -0.55
     butterflies
    -0.55
    POSITIVE LOGITS
    arde
    0.95
    iste
    0.80
    esi
    0.78
    onde
    0.77
    oire
    0.75
    asin
    0.75
    ais
    0.74
    ciating
    0.71
    uese
    0.71
    ļéĨĴ
    0.71
    Act Density 0.154%

    No Known Activations