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

    Neuronpedia

    INDEX
    Explanations

    words related to formal statements or discussions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to decision-making and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shrouded
    -0.67
     inconvenient
    -0.65
    ulously
    -0.64
     swiftly
    -0.64
    ãĥŁ
    -0.63
     stylish
    -0.63
    ");
    -0.63
     antic
    -0.62
     uncommon
    -0.62
     controvers
    -0.62
    POSITIVE LOGITS
    laughs
    0.92
    plet
    0.82
     Dialogue
    0.79
     Everybody
    0.79
    cause
    0.78
    Yeah
    0.75
    Laughs
    0.74
    laughter
    0.74
    ertodd
    0.70
     Alright
    0.70
    Act Density 0.893%

    No Known Activations