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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions or confrontations involving objects or people

    oai_token-act-pair · gpt-3.5-turbo

    connective words or phrases that indicate relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAM
    -0.65
    HI
    -0.63
    rison
    -0.63
    raq
    -0.58
    mma
    -0.58
    hips
    -0.57
     Gamble
    -0.56
    camp
    -0.54
    ppa
    -0.54
    lain
    -0.54
    POSITIVE LOGITS
     the
    0.94
    the
    0.90
    rontal
    0.72
     Corpus
    0.71
     tha
    0.66
     largeDownload
    0.62
     The
    0.62
    The
    0.60
    illary
    0.60
    Õ
    0.60
    Act Density 0.382%

    No Known Activations