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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics related to rates and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    concaten
    -0.53
    UIImageView
    -0.52
    shuff
    -0.48
     Oli
    -0.48
    München
    -0.47
     Thom
    -0.46
     Dubois
    -0.46
     Columbus
    -0.46
    Horiz
    -0.46
    invention
    -0.46
    POSITIVE LOGITS
     rate
    0.88
    RATE
    0.79
     RATE
    0.79
    rate
    0.77
     Rate
    0.77
    Rate
    0.72
     rates
    0.71
    TagMode
    0.69
     degree
    0.67
    merate
    0.67
    Act Density 0.289%

    No Known Activations