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

    Neuronpedia

    INDEX
    Explanations

    references to generalizations and collective descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exels
    -0.43
    >):
    -0.39
    ⭐⭐⭐⭐
    -0.39
    BuildContext
    -0.35
    (_,
    -0.34
    ()")
    -0.34
    intios
    -0.34
    {`
    -0.34
    ")->
    -0.33
    FieldNumber
    -0.33
    POSITIVE LOGITS
     zelve
    0.61
    EDEFAULT
    0.52
    zelf
    0.50
     quelconque
    0.46
     autorytatywna
    0.46
    مشخص
    0.45
     paard
    0.45
     tatuagem
    0.45
     tertentu
    0.45
    anjutnya
    0.45
    Act Density 0.842%

    No Known Activations