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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks to shareable stories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of stories or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.69
     reluct
    -0.65
     mosqu
    -0.63
     spons
    -0.62
     practition
    -0.59
    quartered
    -0.57
    ò
    -0.57
    chwitz
    -0.55
     nomine
    -0.55
     confir
    -0.55
    POSITIVE LOGITS
    :
    0.64
     Related
    0.61
    illian
    0.60
     Loading
    0.59
     Flavoring
    0.58
    !:
    0.56
     Gutenberg
    0.55
    Subscribe
    0.55
    iden
    0.55
     âĨĴ
    0.54
    Act Density 0.023%

    No Known Activations