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

    Neuronpedia

    INDEX
    Explanations

    terms related to debates and discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    s
    -0.89
     asmen
    -0.71
    cheng
    -0.67
     Fisher
    -0.66
    ph
    -0.66
    sns
    -0.63
    I
    -0.63
    Abp
    -0.62
    sq
    -0.61
    ません
    -0.61
    POSITIVE LOGITS
    debate
    1.41
     Debate
    1.34
    Debate
    1.34
     debate
    1.20
     Debates
    1.13
     debates
    1.11
     DEB
    1.11
     itſelf
    1.02
     myſelf
    1.02
     debated
    1.00
    Act Density 0.002%

    No Known Activations