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

    Neuronpedia

    INDEX
    Explanations

    pronouns that refer to individuals, particularly "he" and "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    he she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     povezave
    -0.46
    acana
    -0.43
     Galicia
    -0.42
    jemah
    -0.40
    mely
    -0.40
     intrigu
    -0.40
    ifié
    -0.39
    pousada
    -0.38
     sebelah
    -0.38
    SafeAreaView
    -0.38
    POSITIVE LOGITS
    
    0.45
     husbands
    0.44
     disponibilités
    0.44
     समीक्षक
    0.43
    Contributed
    0.43
     intStringLen
    0.43
    hyrchwyd
    0.42
    stdc
    0.41
     mapStateToProps
    0.41
    pantalones
    0.41
    Act Density 0.003%

    No Known Activations