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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to gender identity and transgender experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     dispatch
    -0.85
     Waste
    -0.79
     alarms
    -0.77
     forecasting
    -0.77
    sers
    -0.75
     Lans
    -0.74
     reimburse
    -0.73
     Emergency
    -0.72
    Emergency
    -0.72
     cleanup
    -0.72
    POSITIVE LOGITS
     genders
    1.35
     biologically
    1.25
     heterosexual
    1.22
    gender
    1.21
    isexual
    1.19
    sexual
    1.17
     ethnicity
    1.15
     sexuality
    1.15
     bisexual
    1.14
     sexes
    1.13
    Act Density 0.636%

    No Known Activations