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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thirds
    -0.72
     lapt
    -0.70
    ciating
    -0.69
     wounding
    -0.69
    teenth
    -0.67
     satell
    -0.64
    etheless
    -0.62
    emouth
    -0.61
     womb
    -0.61
     primates
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.12
    ORTS
    0.99
    rade
    0.98
    ï¸
    0.93
    ACK
    0.87
    acket
    0.82
    acked
    0.82
    encers
    0.81
    ingu
    0.78
    unity
    0.78
    Act Density 0.024%

    No Known Activations