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

    Neuronpedia

    INDEX
    Explanations

    dates, months, and numbers

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amus
    -0.76
    achi
    -0.71
     XIV
    -0.70
    987
    -0.68
     Oswald
    -0.67
    ettings
    -0.66
    olean
    -0.64
     Jem
    -0.62
    ouver
    -0.61
    \\\\\\\\
    -0.59
    POSITIVE LOGITS
    25
    0.85
    23
    0.85
    22
    0.85
    24
    0.85
    28
    0.77
    21
    0.74
     2024
    0.72
    30
    0.71
    29
    0.71
    222
    0.70
    Act Density 0.096%

    No Known Activations