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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern or questions regarding socioeconomic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indr
    -0.16
    uje
    -0.15
    lama
    -0.14
     Ease
    -0.14
    ownik
    -0.14
    yg
    -0.14
    gend
    -0.14
    ird
    -0.14
    ordan
    -0.14
    ammers
    -0.14
    POSITIVE LOGITS
    immers
    0.15
    .nih
    0.15
    DEV
    0.15
    Äįin
    0.14
    (())↵
    0.14
    voke
    0.14
    ULO
    0.14
    CAF
    0.14
    çĽĬ
    0.14
    <&
    0.14
    Act Density 0.414%

    No Known Activations