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

    Neuronpedia

    INDEX
    Explanations

    references to individuals named "Booker"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SV
    -0.79
     Appl
    -0.70
    mpeg
    -0.70
    RH
    -0.69
    mast
    -0.69
     rad
    -0.69
    stan
    -0.66
     IRC
    -0.65
    snap
    -0.65
     Exercise
    -0.64
    POSITIVE LOGITS
     Booker
    4.25
     Gardner
    2.10
    Book
    1.16
     Cory
    1.14
     Newark
    1.10
     Lowry
    1.09
     Grayson
    1.06
     Berger
    1.05
     Torres
    1.05
    imore
    1.03
    Act Density 0.031%

    No Known Activations