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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    by
    -0.16
    a
    -0.14
    idor
    -0.14
    whole
    -0.13
     whole
    -0.13
    eg
    -0.13
     perfectly
    -0.13
     lip
    -0.13
     Ping
    -0.13
    isma
    -0.13
    POSITIVE LOGITS
    .Syntax
    0.15
    иÑĤом
    0.14
    ayet
    0.14
    fdc
    0.14
    anche
    0.14
    /Dk
    0.14
    deÅŁ
    0.13
    IFEST
    0.13
    abyrin
    0.13
    axy
    0.13
    Act Density 0.059%

    No Known Activations