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

    Neuronpedia

    INDEX
    Explanations

    terms related to data accumulation and aggregation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Wod
    -0.82
    SOUNDBITE
    -0.81
     Brito
    -0.79
    cine
    -0.79
     Boch
    -0.78
    topic
    -0.77
     Tig
    -0.76
     Biel
    -0.76
     Snyder
    -0.75
    geral
    -0.75
    POSITIVE LOGITS
    acc
    1.20
    Acc
    1.19
     Acc
    1.13
     acc
    1.09
     ACC
    1.03
    ACC
    0.97
     NSCoder
    0.78
    AuthContext
    0.73
     accordion
    0.72
     Akk
    0.71
    Act Density 0.009%

    No Known Activations