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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific groups or events, specifically women's-related terms

    oai_token-act-pair · gpt-3.5-turbo

    the possessive form related to women in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.90
    mr
    -0.80
    leased
    -0.79
    uncle
    -0.79
    cedented
    -0.77
    assian
    -0.75
    hiba
    -0.70
    ulhu
    -0.70
    regor
    -0.70
    Reviewer
    -0.69
    POSITIVE LOGITS
     Mutual
    0.80
     Clubs
    0.77
     Liberation
    0.74
     Cooper
    0.74
     Basketball
    0.73
    istance
    0.73
     Caucus
    0.72
     Crusade
    0.70
     clubs
    0.67
     basketball
    0.67
    Act Density 0.053%

    No Known Activations