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

    Neuronpedia

    INDEX
    Explanations

    numbers related to bits and memory storage sizes

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical specifications and technical details related to computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.92
    ĸļ
    -0.82
    orical
    -0.79
    ority
    -0.77
    atti
    -0.77
    allery
    -0.75
    owsky
    -0.75
    azine
    -0.72
    olicy
    -0.71
    orie
    -0.71
    POSITIVE LOGITS
    384
    0.83
    PDATE
    0.72
     integers
    0.72
     currencies
    0.71
    --------------------------------------------------------
    0.70
    ãĥ¢
    0.70
    bit
    0.70
    ference
    0.69
    batch
    0.69
    GB
    0.68
    Act Density 0.054%

    No Known Activations