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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns related to a female subject

    oai_token-act-pair · gpt-3.5-turbo

    references to a female subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.69
    undo
    -0.63
    escription
    -0.63
    hovah
    -0.63
    anamo
    -0.60
     homosexuals
    -0.59
    Reply
    -0.59
    ornia
    -0.59
    govtrack
    -0.58
    emetery
    -0.58
    POSITIVE LOGITS
    pher
    1.41
    athed
    1.18
    ding
    1.02
    lled
    1.02
    athing
    1.01
    pard
    0.99
    ikh
    0.96
    cule
    0.96
    pherd
    0.88
    ldon
    0.88
    Act Density 0.180%

    No Known Activations