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

    Neuronpedia

    INDEX
    Explanations

    references to firearms

    oai_token-act-pair · gpt-3.5-turbo

    references to guns and gun-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hort
    -0.68
     Ethiop
    -0.68
     Strawberry
    -0.67
     Dragons
    -0.66
     Humph
    -0.66
     Dull
    -0.66
     Debor
    -0.66
     Schiff
    -0.64
     newsp
    -0.64
    algia
    -0.62
    POSITIVE LOGITS
    powder
    1.71
    nery
    1.50
    ner
    1.44
    ners
    1.42
    smith
    1.32
    metal
    1.31
    nar
    1.31
    fight
    1.27
    fighter
    1.25
    ning
    1.23
    Act Density 0.043%

    No Known Activations