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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric characters or specific character sequences within text

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to programming and character data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rak
    -0.83
    uci
    -0.76
    cler
    -0.72
    Monitor
    -0.70
    igun
    -0.70
    DEM
    -0.69
    ciplinary
    -0.69
    Watch
    -0.67
    odynam
    -0.67
    aimon
    -0.66
    POSITIVE LOGITS
    acters
    1.06
     comma
    1.00
     phrases
    0.96
     ASCII
    0.95
     text
    0.93
     strings
    0.93
     "%
    0.92
     UTF
    0.89
     spelling
    0.88
     gib
    0.88
    Act Density 0.183%

    No Known Activations