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

    Neuronpedia

    INDEX
    Explanations

    technical terms and codes containing special characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters represented as "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.72
     Springer
    -0.70
     Mirage
    -0.69
    creen
    -0.68
     interfering
    -0.67
     mosqu
    -0.66
     Ukrain
    -0.66
     kindergarten
    -0.66
    ammed
    -0.66
     shroud
    -0.65
    POSITIVE LOGITS
    ł
    1.13
    ij
    1.03
    IJ
    1.02
    ª
    0.98
    ¹
    0.96
    ı
    0.95
    £
    0.94
    Ĵ
    0.93
    âĸº
    0.92
    į
    0.86
    Act Density 0.221%

    No Known Activations