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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question marks in the dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mans
    -0.17
    kid
    -0.16
    adb
    -0.15
     ÙĤدر
    -0.14
    sock
    -0.14
     Lorem
    -0.13
    íĻį
    -0.13
    lah
    -0.13
    legend
    -0.13
    mah
    -0.13
    POSITIVE LOGITS
     voice
    0.17
    oice
    0.16
     Narr
    0.15
     frost
    0.15
    Narr
    0.15
    Voice
    0.15
    ouncer
    0.14
    ItemClick
    0.14
    EMALE
    0.14
     Hast
    0.13
    Act Density 0.054%

    No Known Activations