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

    Neuronpedia

    INDEX
    Explanations

    phrases at the end of segments in a consistent format, potentially related to authorship or usage rights

    oai_token-act-pair · gpt-3.5-turbo

    the attribution of works, specifically focusing on the "BY" licensing or copyright information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pend
    -0.61
     triangle
    -0.60
     rad
    -0.57
     grid
    -0.57
     Strait
    -0.57
    teness
    -0.57
    isting
    -0.57
     oscill
    -0.56
     implanted
    -0.56
     embedded
    -0.56
    POSITIVE LOGITS
    BY
    4.71
    by
    1.76
     BY
    1.54
    bys
    1.44
    BU
    1.27
    BIT
    1.23
    BUS
    1.22
    bye
    1.14
    BE
    1.14
    By
    1.12
    Act Density 0.013%

    No Known Activations