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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data types and values in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodman
    -0.16
    ht
    -0.16
    readcr
    -0.15
    ello
    -0.15
    ylko
    -0.14
    isch
    -0.14
    885
    -0.14
    InSeconds
    -0.14
    cow
    -0.14
    æ¥
    -0.14
    POSITIVE LOGITS
     precision
    0.34
    precision
    0.31
    .precision
    0.30
     Precision
    0.29
    Precision
    0.28
    _precision
    0.28
     ROUND
    0.28
     precis
    0.25
     prec
    0.25
    _places
    0.25
    Act Density 0.032%

    No Known Activations