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

    Neuronpedia

    INDEX
    Explanations

    phrases that express varying degrees of effort or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ths
    -0.15
    cie
    -0.14
    íĮ
    -0.14
    hev
    -0.14
    orc
    -0.14
    reff
    -0.13
    landa
    -0.13
    pps
    -0.13
    ensa
    -0.13
    arget
    -0.13
    POSITIVE LOGITS
    ouri
    0.17
     cop
    0.17
     Cop
    0.15
    ish
    0.15
    oca
    0.14
    _TRIGGER
    0.14
    bish
    0.13
    ASP
    0.13
    _RUNTIME
    0.13
    ChangedEventArgs
    0.13
    Act Density 0.020%

    No Known Activations