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

    Neuronpedia

    INDEX
    Explanations

    Slavic characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols that are not in the standard English alphabet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.75
    olphin
    -0.73
    WARD
    -0.72
    ifference
    -0.70
    ammy
    -0.68
    bed
    -0.65
    ioned
    -0.63
    ibles
    -0.59
    epad
    -0.59
     Passenger
    -0.59
    POSITIVE LOGITS
    ³
    1.14
    ĺ
    1.12
    Ľ
    1.10
    Ļ
    1.09
    Ķ
    1.04
    È
    1.04
    £
    1.00
    ł
    1.00
    Ĵ
    0.99
    ½
    0.99
    Act Density 0.005%

    No Known Activations