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

    Neuronpedia

    INDEX
    Explanations

    references to male or female characters or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Notion
    -0.81
    aarrggbb
    -0.78
     kasarigan
    -0.76
     soot
    -0.71
    things
    -0.71
    شهاد
    -0.71
     Sitten
    -0.69
     YAP
    -0.68
    THINGS
    -0.67
     Machu
    -0.67
    POSITIVE LOGITS
     Male
    1.24
     MALE
    1.18
    MALE
    1.11
     male
    1.11
     FEMALE
    1.05
    Male
    1.02
     males
    1.00
    emale
    0.98
     Females
    0.97
     female
    0.96
    Act Density 0.080%

    No Known Activations