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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases signaling anticipation or surprise

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating anticipation or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.84
    icipated
    -0.65
    aturday
    -0.65
    Fall
    -0.63
    "},"
    -0.62
    oulder
    -0.61
    arcity
    -0.61
    antine
    -0.59
    UGC
    -0.58
    20439
    -0.56
    POSITIVE LOGITS
    ...]
    0.73
    âĢ¦)
    0.73
    !:
    0.70
    ...)
    0.70
    !?
    0.69
     minute
    0.68
    âĢ¦
    0.67
    âĢ¦.
    0.67
     kidding
    0.66
    ....
    0.66
    Act Density 0.084%

    No Known Activations