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

    Neuronpedia

    INDEX
    Explanations

    uppercase abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to frameworks or specifications, particularly in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.77
    holder
    -0.74
     PsyNet
    -0.73
    gow
    -0.72
     Totem
    -0.66
     Tsu
    -0.66
    ulet
    -0.65
    lace
    -0.65
     Hiroshima
    -0.64
     Dragonbound
    -0.63
    POSITIVE LOGITS
    ONT
    1.26
    ugal
    1.11
    FR
    0.98
    ESH
    0.97
    andom
    0.92
    AME
    0.89
    owship
    0.88
    iggs
    0.86
    ANCE
    0.81
    ACTION
    0.80
    Act Density 0.007%

    No Known Activations