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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to abstract or metaphorical concepts and places

    oai_token-act-pair · gpt-3.5-turbo

    references to different domains or areas of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bor
    -0.63
    ãģį
    -0.63
     Clover
    -0.63
    HOME
    -0.62
    inated
    -0.61
    ãģĦ
    -0.61
    TER
    -0.61
    aquin
    -0.61
     Fas
    -0.59
     Rate
    -0.58
    POSITIVE LOGITS
    naire
    0.87
     realms
    0.83
    osaurs
    0.80
    uin
    0.77
    icular
    0.75
     collide
    0.75
    wide
    0.75
    mares
    0.74
    ality
    0.73
     realm
    0.73
    Act Density 0.043%

    No Known Activations