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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating obligation, separation, or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤµãĤ¤
    -0.15
    erk
    -0.14
    ÑĦоÑĢми
    -0.14
     Buccane
    -0.14
    iosa
    -0.14
    ục
    -0.14
     bdsm
    -0.13
    Ñĥнк
    -0.13
     ED
    -0.13
    vil
    -0.13
    POSITIVE LOGITS
    лÑİÑĩа
    0.16
    abar
    0.15
    enta
    0.15
    gend
    0.15
    grim
    0.14
    RootElement
    0.14
     Bloomberg
    0.14
    èĩªèº«
    0.14
     himself
    0.14
     grant
    0.13
    Act Density 0.228%

    No Known Activations