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

    Neuronpedia

    INDEX
    Explanations

    pronouns and collective terms that indicate inclusivity or group identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULSE
    -0.16
    .mapping
    -0.15
    ños
    -0.14
    agh
    -0.14
    inka
    -0.13
    ÅĽmy
    -0.13
    اÙĦÙĩ
    -0.13
    ogui
    -0.13
    strup
    -0.13
     Erf
    -0.13
    POSITIVE LOGITS
     Jaune
    0.18
    ies
    0.15
    ÙĬØ©
    0.15
    ity
    0.15
     ConfigureServices
    0.15
    gies
    0.14
     finely
    0.14
    IES
    0.14
    rien
    0.14
     dec
    0.14
    Act Density 0.049%

    No Known Activations