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

    Neuronpedia

    INDEX
    Explanations

    words related to reasons, factors, purposes, forms, occupations, outfits, sources, ways, projects, topics, diseases, subjects, issues, and groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reasons, factors, and purposes for actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enne
    -0.77
    ILA
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    ebook
    -0.66
    eka
    -0.63
    IELD
    -0.63
    arde
    -0.62
     Enough
    -0.61
     Redemption
    -0.61
    apest
    -0.59
    POSITIVE LOGITS
     including
    1.60
     ranging
    1.43
     Including
    1.21
     imaginable
    1.20
     besides
    1.19
    including
    1.17
     includ
    1.10
     simultaneously
    1.07
     throughout
    1.01
     viz
    0.97
    Act Density 0.377%

    No Known Activations