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

    Neuronpedia

    INDEX
    Explanations

    audience-related terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scot
    -0.69
    imov
    -0.67
     Ski
    -0.67
     Ide
    -0.65
    idy
    -0.62
    uel
    -0.61
    redo
    -0.60
     Plum
    -0.60
    grave
    -0.58
    morrow
    -0.58
    POSITIVE LOGITS
    members
    0.83
    iences
    0.81
     members
    0.80
     member
    0.80
     audience
    0.80
     laughs
    0.78
    IENCE
    0.78
    atics
    0.75
     laughter
    0.73
     gasped
    0.73
    Act Density 0.062%

    No Known Activations