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

    Neuronpedia

    INDEX
    Explanations

    text separators and formatting elements, like equal signs and dashes

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lling
    -0.78
    assic
    -0.75
    ornia
    -0.74
    rican
    -0.72
    rael
    -0.71
    matically
    -0.69
    iller
    -0.69
    icion
    -0.67
    inav
    -0.67
     dared
    -0.66
    POSITIVE LOGITS
    */
    1.10
    ===
    0.96
     =================================================================
    0.94
    END
    0.92
    =-=-
    0.90
    ==
    0.86
     SECTION
    0.86
    =>
    0.85
    Chapter
    0.84
     ********************************
    0.84
    Act Density 0.059%

    No Known Activations