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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.78
    ĸļ
    -0.73
    terday
    -0.70
     ..........
    -0.70
    inez
    -0.63
    ļéĨĴ
    -0.62
    aeda
    -0.60
    cffff
    -0.59
     Beir
    -0.59
     Faust
    -0.58
    POSITIVE LOGITS
     wat
    0.69
     observers
    0.66
     enrol
    0.60
     scholars
    0.60
     implementations
    0.59
     reviewers
    0.58
    irms
    0.58
     experiences
    0.57
     classes
    0.57
     clears
    0.56
    Act Density 0.584%

    No Known Activations