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

    Neuronpedia

    INDEX
    Explanations

    terms related to transgender issues

    oai_token-act-pair · gpt-3.5-turbo

    references to transgender topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARRANT
    -0.74
     Slug
    -0.74
    FIELD
    -0.70
     Sunder
    -0.67
    dylib
    -0.66
    RANT
    -0.65
     Bard
    -0.65
    eers
    -0.65
    MENTS
    -0.65
    eer
    -0.62
    POSITIVE LOGITS
    mitt
    1.11
    gression
    1.06
    missible
    1.02
    racial
    1.01
    continental
    0.99
    istors
    0.97
    gender
    0.93
    figured
    0.93
    posed
    0.92
    gressive
    0.90
    Act Density 0.007%

    No Known Activations