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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to females or femininity

    oai_token-act-pair · gpt-3.5-turbo

    references to female entities or characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rieg
    -0.86
    lov
    -0.85
    vous
    -0.81
    ypes
    -0.80
    akespe
    -0.80
    hemy
    -0.78
    krit
    -0.78
    lay
    -0.78
    heet
    -0.77
    xtap
    -0.76
    POSITIVE LOGITS
    volent
    1.28
     genital
    1.14
     empowerment
    1.03
     reproductive
    0.98
     genitals
    0.92
     contraceptive
    0.83
     menstrual
    0.82
     infertility
    0.81
     sexuality
    0.80
     emancipation
    0.78
    Act Density 0.025%

    No Known Activations