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

    Neuronpedia

    INDEX
    Explanations

    words related to gender and gender-neutral concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender inclusivity and related social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.75
    Bus
    -0.73
     Marriott
    -0.70
    shire
    -0.69
    KC
    -0.69
    Js
    -0.67
    dry
    -0.66
     Niet
    -0.64
    akura
    -0.64
    Reviewer
    -0.63
    POSITIVE LOGITS
     ethnicity
    0.83
     pronouns
    0.80
     genders
    0.78
     inheritance
    0.74
     identifiers
    0.73
     influences
    0.73
     minorities
    0.72
     ensl
    0.71
     chromosomes
    0.71
    itives
    0.70
    Act Density 0.217%

    No Known Activations