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

    Neuronpedia

    INDEX
    Explanations

    words associated with community, demographics, and socioeconomic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.25
    ies
    -0.17
    /es
    -0.16
    -ing
    -0.16
    etail
    -0.16
    ãĢħ
    -0.15
    ä¹ĭä¸Ģ
    -0.15
    duit
    -0.15
     Karn
    -0.15
    ESH
    -0.15
    POSITIVE LOGITS
    S
    0.28
    à¥įस
    0.19
    ÂłS
    0.16
    ส
    0.16
    s
    0.15
    Ñģ
    0.15
    ns
    0.15
    se
    0.15
    ws
    0.14
    å¢
    0.14
    Act Density 0.087%

    No Known Activations