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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and political events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting, specifically periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Egypt
    -0.90
     Bib
    -0.80
    lement
    -0.80
     Jordanian
    -0.79
     Soy
    -0.79
    Iv
    -0.79
    thodox
    -0.78
     rom
    -0.78
     Ethiop
    -0.78
     phyl
    -0.77
    POSITIVE LOGITS
     Murphy
    2.53
    Mur
    2.40
     Mur
    1.80
    mur
    1.60
     mur
    1.20
     Nolan
    1.10
     Lieberman
    1.05
     Quinn
    1.01
     Sweeney
    0.99
     Guth
    0.98
    Act Density 0.278%

    No Known Activations