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

    Neuronpedia

    INDEX
    Explanations

    special characters Ċ and │ combined with numbers indicating a specific sequence or pattern

    oai_token-act-pair · gpt-3.5-turbo

    technical details related to programming and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deng
    -0.70
     Mechdragon
    -0.70
     Raf
    -0.67
     Lazarus
    -0.66
     Rei
    -0.66
     Row
    -0.65
     Shinzo
    -0.65
     Kaz
    -0.62
     Muss
    -0.61
     Daw
    -0.60
    POSITIVE LOGITS
    prototype
    0.85
    ó
    0.78
    given
    0.78
    need
    0.74
    needed
    0.74
    ///
    0.74
    shall
    0.72
    individual
    0.72
    ³³³³³³³³³³³³³³³³
    0.70
    found
    0.70
    Act Density 0.175%

    No Known Activations