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

    Neuronpedia

    INDEX
    Explanations

    function calls and method definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المناصب
    -0.52
    DeleteBehavior
    -0.50
     nawr
    -0.47
    ########.
    -0.47
     EconPapers
    -0.46
    ẻo
    -0.46
    épendance
    -0.45
    millan
    -0.45
    omenclature
    -0.45
     Ababa
    -0.44
    POSITIVE LOGITS
     value
    3.66
    value
    3.30
     Value
    2.78
    Value
    2.62
     VALUE
    2.53
    VALUE
    2.31
     valeur
    2.28
     waarde
    1.90
     valore
    1.87
    值
    1.87
    Act Density 0.341%

    No Known Activations