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

    Neuronpedia

    INDEX
    Explanations

    numbers represented in digit format

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, particularly digits and their counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.90
    ModLoader
    -0.79
    roxy
    -0.78
    nd
    -0.77
    ouf
    -0.74
    ritz
    -0.72
    dep
    -0.71
    lain
    -0.71
    Study
    -0.70
    rael
    -0.68
    POSITIVE LOGITS
    eteen
    0.87
    omial
    0.86
    ized
    0.86
    igr
    0.85
    itial
    0.84
    oded
    0.83
     digits
    0.83
    ised
    0.83
     digit
    0.82
    umeric
    0.79
    Act Density 0.022%

    No Known Activations