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

    Neuronpedia

    INDEX
    Explanations

    references to minutes or short time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "min" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.69
    eering
    -0.68
     Dreams
    -0.64
     Crusade
    -0.64
     Directorate
    -0.63
     Balk
    -0.63
    ÙIJ
    -0.62
     Samurai
    -0.61
     Piercing
    -0.60
    ãĤ©
    -0.59
    POSITIVE LOGITS
    nesota
    1.28
    otaur
    1.18
    iatures
    1.17
    neapolis
    1.13
    utes
    1.11
    usc
    1.03
    istered
    0.97
    isters
    0.96
    erva
    0.95
    oths
    0.94
    Act Density 0.010%

    No Known Activations