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

    Neuronpedia

    INDEX
    Explanations

    terms related to capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WindowConstants
    -0.77
    Σε
    -0.74
    estinal
    -0.72
    assium
    -0.72
     Marlowe
    -0.69
     Aung
    -0.68
    ifrance
    -0.67
    [^
    -0.67
    JMenuItem
    -0.67
     Barlow
    -0.63
    POSITIVE LOGITS
     of
    1.60
    Portail
    0.84
    fillType
    0.83
     của
    0.81
    ]%
    0.80
    katapos
    0.78
    agisse
    0.77
    ēc
    0.76
    dientemente
    0.75
     propOrder
    0.74
    Act Density 0.664%

    No Known Activations