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

    Neuronpedia

    INDEX
    Explanations

    versions of software or products

    oai_token-act-pair · gpt-3.5-turbo

    version numbers of software or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.71
     ancest
    -0.66
     crucifix
    -0.65
    inguished
    -0.65
     aisle
    -0.63
    rero
    -0.62
     Souls
    -0.61
     Berm
    -0.61
     Bronx
    -0.61
    ierrez
    -0.60
    POSITIVE LOGITS
    ĨĴ
    0.92
     onwards
    0.86
    beta
    0.86
     Version
    0.84
    Version
    0.81
    çīĪ
    0.80
     version
    0.77
    ogue
    0.77
    ARCH
    0.74
    upt
    0.73
    Act Density 0.061%

    No Known Activations