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

    Neuronpedia

    INDEX
    Explanations

    decisions or judgments made by an authority figure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ruled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.78
    akra
    -0.76
    ription
    -0.75
    rity
    -0.71
    ionage
    -0.69
    ickr
    -0.67
    ipal
    -0.66
    Newsletter
    -0.64
    ãĥ¤
    -0.64
     Pilgrim
    -0.64
    POSITIVE LOGITS
    phas
    0.83
    maker
    0.76
    inker
    0.75
     unfit
    0.70
    tto
    0.68
    rooms
    0.67
    ULE
    0.66
    book
    0.66
    witz
    0.65
    sets
    0.63
    Act Density 0.023%

    No Known Activations