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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    symbols, dates, and dollar amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SX
    -0.76
    OTA
    -0.76
    arium
    -0.75
     Tak
    -0.75
     TOUR
    -0.74
     Ott
    -0.73
     Ost
    -0.71
    kt
    -0.71
     Ware
    -0.71
     Shroud
    -0.71
    POSITIVE LOGITS
    29
    1.05
    28
    1.00
     29
    0.99
     28
    0.92
     30
    0.90
    30
    0.88
     27
    0.88
    31
    0.88
    27
    0.88
    ina
    0.86
    Act Density 0.283%

    No Known Activations