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

    Neuronpedia

    INDEX
    Explanations

    copyright information, particularly the use of Creative Commons licensing

    oai_token-act-pair · gpt-3.5-turbo

    references to copyright licenses, particularly Creative Commons licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nor
    -0.89
    rano
    -0.88
    jet
    -0.86
    atom
    -0.83
    ka
    -0.76
    lon
    -0.76
    ogene
    -0.76
    opol
    -0.75
    man
    -0.72
    ichi
    -0.72
    POSITIVE LOGITS
    IST
    1.28
    ER
    1.22
    TY
    1.18
    BOOK
    1.15
    NESS
    1.14
    TERN
    1.12
    IZ
    1.12
    ISM
    1.07
    BY
    1.06
    LE
    1.05
    Act Density 0.038%

    No Known Activations