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

    Neuronpedia

    INDEX
    Explanations

    characteristics and traits associated with favorable roles or qualities in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asin
    -0.17
    stile
    -0.15
    ilib
    -0.14
    âh
    -0.14
    ÑģÑĤвоÑĢ
    -0.14
    اش
    -0.13
    -metadata
    -0.13
    æ²
    -0.13
     INCIDENT
    -0.13
    asco
    -0.13
    POSITIVE LOGITS
    itz
    0.20
    arden
    0.15
     loud
    0.15
     neither
    0.14
    bard
    0.14
    飯
    0.14
     clean
    0.14
     ÐĴики
    0.14
     geil
    0.13
    arel
    0.13
    Act Density 0.366%

    No Known Activations