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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    dates and specific times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.66
     behavi
    -0.66
     careless
    -0.64
     basket
    -0.63
     Mellon
    -0.59
    ļéĨĴ
    -0.59
     shocks
    -0.57
     suitcase
    -0.56
     prolifer
    -0.53
     multiplying
    -0.53
    POSITIVE LOGITS
     03
    1.00
     29
    0.99
     04
    0.99
     06
    0.98
     08
    0.98
     07
    0.98
     09
    0.96
     02
    0.95
     05
    0.95
     28
    0.94
    Act Density 0.044%

    No Known Activations