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

    Neuronpedia

    INDEX
    Explanations

    names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names, throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minecraft
    -0.92
    kefeller
    -0.72
    zsche
    -0.70
    ftime
    -0.70
    atform
    -0.69
    ĸļ
    -0.68
    isphere
    -0.66
    ibaba
    -0.64
    inki
    -0.63
    itionally
    -0.63
    POSITIVE LOGITS
    vez
    0.84
    abbage
    0.71
     Sins
    0.69
    neau
    0.69
     Gaul
    0.69
    ij士
    0.66
    Administ
    0.64
     Maced
    0.64
     Detail
    0.63
    Esc
    0.61
    Act Density 0.517%

    No Known Activations