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

    Neuronpedia

    INDEX
    Explanations

    words related to medical procedures or tools

    oai_token-act-pair · gpt-3.5-turbo

    words related to various suffixes and endings in the context of nouns and adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ī
    -0.67
    YL
    -0.67
     Birch
    -0.65
     Tsukuyomi
    -0.63
    PDATE
    -0.62
    ashtra
    -0.62
    senal
    -0.60
    SIGN
    -0.58
    assic
    -0.58
    frey
    -0.57
    POSITIVE LOGITS
    gered
    0.70
    arag
    0.69
    rily
    0.68
    ionage
    0.66
    uch
    0.64
    pires
    0.63
    lect
    0.61
    azines
    0.60
    ctions
    0.60
    imus
    0.58
    Act Density 0.228%

    No Known Activations