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

    Neuronpedia

    INDEX
    Explanations

    phrases with special characters used as formatting or separators

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istar
    -0.71
     condem
    -0.70
    iev
    -0.69
    onds
    -0.68
    ascular
    -0.68
    nesday
    -0.67
     ejected
    -0.67
     marching
    -0.67
     Cycling
    -0.67
    ulner
    -0.66
    POSITIVE LOGITS
    âĸ
    1.27
    ï¸ı
    1.12
    âĹ
    1.10
    âĸº
    1.08
    ł
    1.07
    ï¸
    1.06
    ¼
    1.04
    ¡
    1.03
    âĢ¢âĢ¢
    1.03
    âĸł
    1.03
    Act Density 0.008%

    No Known Activations