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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to females

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific female subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.90
    odder
    -0.71
    church
    -0.69
    ornia
    -0.67
    perties
    -0.67
    atory
    -0.65
     Jindal
    -0.65
    folios
    -0.63
     Vers
    -0.62
    ENSE
    -0.62
    POSITIVE LOGITS
    pher
    1.35
    athed
    1.21
    'd
    1.12
    athing
    1.11
    pherd
    1.07
    ffield
    1.04
    pard
    1.01
    'll
    1.00
    ppard
    0.96
    ldon
    0.85
    Act Density 0.103%

    No Known Activations