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

    Neuronpedia

    INDEX
    Explanations

    function definitions and identifiers in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stanton
    -0.15
    borough
    -0.15
    phere
    -0.15
     Extreme
    -0.14
    boro
    -0.14
     Conce
    -0.14
    ìĨ
    -0.14
    aland
    -0.14
    bench
    -0.14
    orderby
    -0.13
    POSITIVE LOGITS
    aggable
    0.16
    ustos
    0.15
     Quint
    0.15
    olini
    0.14
    lacak
    0.14
    Ñĩие
    0.14
     Ars
    0.14
    گاÙĩÛĮ
    0.14
    BOTTOM
    0.14
    dech
    0.14
    Act Density 1.290%

    No Known Activations