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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols in the text

    oai_token-act-pair · gpt-4-turbo

    symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or list items in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushi
    -0.77
    omorphic
    -0.75
    brance
    -0.75
     wagon
    -0.74
    rolet
    -0.73
     grain
    -0.72
     shaping
    -0.71
    laus
    -0.71
    alsa
    -0.71
    icum
    -0.71
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.24
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.13
    ï¸ı
    0.97
    ï¸
    0.92
    tal
    0.84
    âĸł
    0.78
     Includes
    0.77
    âĢ¢
    0.77
    Publisher
    0.73
    ---------
    0.71
    Act Density 0.011%

    No Known Activations