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

    Neuronpedia

    INDEX
    Explanations

    terms related to methods and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.71
    cursion
    -0.71
    IsMutable
    -0.69
    flink
    -0.67
    ///</
    -0.64
     demurrer
    -0.63
     cowardice
    -0.63
    UnsafeEnabled
    -0.62
     Proust
    -0.61
    criture
    -0.60
    POSITIVE LOGITS
     became
    0.85
     becomes
    0.80
     become
    0.75
     Became
    0.71
     Becomes
    0.65
    become
    0.63
    became
    0.63
     Become
    0.62
     lenker
    0.61
    Become
    0.61
    Act Density 0.270%

    No Known Activations