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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references to individuals, particularly notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pod
    -0.79
     Pod
    -0.75
     Ear
    -0.72
     Pon
    -0.70
     Flight
    -0.68
     Nar
    -0.67
     Esper
    -0.67
     ear
    -0.65
     Strat
    -0.64
     Cran
    -0.63
    POSITIVE LOGITS
    illard
    5.02
    udeau
    1.41
    illet
    1.15
    unks
    1.08
    rouse
    1.05
    ierre
    1.03
    arden
    0.91
    oyd
    0.90
    arding
    0.89
    ettel
    0.89
    Act Density 0.008%

    No Known Activations