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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with special characters followed by letters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dupl
    -0.73
    creen
    -0.72
    wagen
    -0.71
     Bris
    -0.70
     Jeanne
    -0.69
     conduc
    -0.68
     destro
    -0.68
     Farn
    -0.66
    WithNo
    -0.66
    sters
    -0.65
    POSITIVE LOGITS
    ª
    1.20
    Ĵ
    1.09
    IJ
    1.08
    ł
    1.04
    ı
    1.01
    ¤
    1.00
    ¹
    0.98
    Ĥ
    0.95
    ħ
    0.93
    ij
    0.93
    Act Density 0.106%

    No Known Activations