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

    Neuronpedia

    INDEX
    Explanations

    topics or subjects under discussion or consideration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "debating" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eared
    -0.86
    of
    -0.76
    uras
    -0.74
    hetical
    -0.74
    TPS
    -0.73
    istics
    -0.73
    eled
    -0.72
    uci
    -0.71
    istence
    -0.70
    isting
    -0.70
    POSITIVE LOGITS
     debating
    1.05
     debated
    0.95
     debates
    0.90
     debate
    0.80
     unanimously
    0.79
     Debate
    0.76
     discounted
    0.67
     whether
    0.63
    ij士
    0.63
    puff
    0.63
    Act Density 0.017%

    No Known Activations