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

    Neuronpedia

    INDEX
    Explanations

    references to feminine pronouns and possessive forms related to a specific individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.90
    providedIn
    -0.86
     تضيفلها
    -0.78
    NewUrlParser
    -0.75
    تقاوى
    -0.75
    BufferException
    -0.75
     pleaſure
    -0.75
    __(/*!
    -0.74
    IntoConstraints
    -0.73
     nahilalakip
    -0.72
    POSITIVE LOGITS
     her
    1.92
     she
    1.66
    she
    1.27
     herself
    1.27
    She
    1.22
    她
    1.18
    เธอ
    1.08
     그녀
    1.07
    Она
    1.06
    her
    1.05
    Act Density 0.144%

    No Known Activations