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

    Neuronpedia

    INDEX
    Explanations

    the word "women."

    oai_token-act-pair · gpt-3.5-turbo

    references to women or feminine themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspended
    -0.74
     jails
    -0.68
     jail
    -0.65
     decline
    -0.64
     halves
    -0.64
     Bots
    -0.63
     script
    -0.63
     chill
    -0.62
     exile
    -0.62
     refund
    -0.60
    POSITIVE LOGITS
    omen
    5.09
    oman
    1.86
    omes
    1.34
    ome
    1.32
    omers
    1.21
    omon
    1.18
    oming
    1.14
    osen
    1.10
    oms
    1.09
    omal
    1.06
    Act Density 0.016%

    No Known Activations