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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    》.
    -0.86
    oa̍t
    -0.86
    */}
    -0.80
     Pind
    -0.75
    prüche
    -0.74
     поводу
    -0.71
     '\\;'
    -0.71
    '}>
    -0.69
     OB
    -0.68
     DOS
    -0.67
    POSITIVE LOGITS
    â
    1.88
     â
    1.73
    Câ
    1.19
    lâ
    1.18
     Bâ
    1.13
     Mâ
    1.13
     Â
    1.12
    Â
    1.07
     lâ
    1.06
     vâ
    1.04
    Act Density 0.167%

    No Known Activations