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

    Neuronpedia

    INDEX
    Explanations

    evidence of societal roles and expectations in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     пÑĢидеÑĤÑģÑı
    -0.16
    tility
    -0.15
    CRET
    -0.14
    otal
    -0.14
    avra
    -0.14
    presso
    -0.14
    likelihood
    -0.14
    olla
    -0.14
    á»ĵi
    -0.14
    _EXISTS
    -0.13
    POSITIVE LOGITS
     supposed
    1.05
     suppose
    0.79
     meant
    0.60
     supposedly
    0.60
     purported
    0.54
     alleged
    0.54
     allegedly
    0.49
     intended
    0.43
     Suppose
    0.42
     SUP
    0.40
    Act Density 0.389%

    No Known Activations