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

    Neuronpedia

    INDEX
    Explanations

    references to the term "fugitive"

    oai_token-act-pair · gpt-3.5-turbo

    references to fugitives and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.72
    erity
    -0.72
    hetically
    -0.69
    wn
    -0.66
    jriwal
    -0.66
    anguage
    -0.66
    ONES
    -0.65
    yton
    -0.65
    place
    -0.64
    eer
    -0.64
    POSITIVE LOGITS
     Fug
    1.22
     fug
    1.05
    querque
    0.82
     Drugs
    0.78
    laws
    0.78
     Flag
    0.69
     Shelter
    0.69
     Unlimited
    0.69
    SourceFile
    0.67
    iesta
    0.67
    Act Density 0.017%

    No Known Activations