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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters, particularly the question mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.89
    xus
    -0.88
    chnology
    -0.87
     handshake
    -0.79
    aughs
    -0.79
    peria
    -0.77
     gestation
    -0.75
    cephal
    -0.75
     tremend
    -0.75
    emate
    -0.74
    POSITIVE LOGITS
    ¿
    1.16
    į
    1.11
    оÐ
    1.10
    ĭ
    1.08
    ÑĢ
    1.05
    е
    1.03
    о
    1.01
    Ĩ
    1.00
    ĩ
    0.98
    »
    0.97
    Act Density 0.004%

    No Known Activations