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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions and humor in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emo
    -0.16
    antry
    -0.16
    aders
    -0.15
     Surprise
    -0.15
    issen
    -0.14
     transformed
    -0.14
    /modal
    -0.14
    ichier
    -0.14
    ivo
    -0.14
    ont
    -0.14
    POSITIVE LOGITS
     scatter
    0.16
    UGHT
    0.16
    ENCH
    0.15
     Scatter
    0.15
     Ere
    0.14
    港
    0.14
    itra
    0.14
    oleÄį
    0.14
     Flor
    0.14
    lags
    0.14
    Act Density 0.028%

    No Known Activations