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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and terms

    oai_token-act-pair · gpt-3.5-turbo

    programming-related terms and technical jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.73
     Hew
    -0.66
    accompan
    -0.63
    sett
    -0.62
     UCHIJ
    -0.62
    idis
    -0.61
     INCLUD
    -0.61
     cumbers
    -0.61
    ©¶æ¥µ
    -0.61
    hement
    -0.60
    POSITIVE LOGITS
    _
    1.79
    _{
    1.33
    _.
    1.23
    _>
    1.17
    _-
    1.10
    ___
    1.06
    _(
    1.06
     _
    1.03
    __
    0.90
    _-_
    0.84
    Act Density 0.058%

    No Known Activations