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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing characteristics or actions of people

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their actions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.95
    enegger
    -0.79
    =~
    -0.73
     TAMADRA
    -0.72
    atever
    -0.69
     ................
    -0.64
    externalActionCode
    -0.63
    -+
    -0.61
     Printing
    -0.60
    =-=-=-=-=-=-=-=-
    -0.60
    POSITIVE LOGITS
    rosso
    0.77
    hops
    0.71
    ilo
    0.70
    trop
    0.67
    perm
    0.66
    uce
    0.65
    inelli
    0.63
    enos
    0.63
    hop
    0.61
    assium
    0.60
    Act Density 0.488%

    No Known Activations