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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in a question mark

    oai_token-act-pair · gpt-3.5-turbo

    question marks and rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Supplemental
    -0.48
     âĢ¢
    -0.48
     import
    -0.47
     periphery
    -0.42
     minor
    -0.41
    jong
    -0.41
     embed
    -0.41
     seasonal
    -0.41
     ·
    -0.40
     imported
    -0.40
    POSITIVE LOGITS
    ?"
    3.43
    ?!"
    3.12
    ?".
    3.05
    ?",
    3.05
    !?"
    2.94
    ?'"
    2.88
    "?
    2.78
    ?'
    2.52
    ?ãĢį
    2.45
    ?).
    2.06
    Act Density 0.009%

    No Known Activations