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

    Neuronpedia

    INDEX
    Explanations

    dialogue-related phrases and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to conversation or discussion in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cot
    -0.76
    rule
    -0.74
    addons
    -0.74
    isher
    -0.73
    ulz
    -0.72
    arah
    -0.71
    cheat
    -0.70
    rug
    -0.69
    old
    -0.69
    innon
    -0.69
    POSITIVE LOGITS
     dialogue
    1.04
    naire
    0.99
    ogue
    0.87
     Franç
    0.84
    ues
    0.84
     Dialogue
    0.83
     conversation
    0.77
     dialog
    0.77
     reperto
    0.77
    dayName
    0.75
    Act Density 0.018%

    No Known Activations