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

    Neuronpedia

    INDEX
    Explanations

    references to firearms and gun-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imore
    -0.15
    ajs
    -0.15
    ermen
    -0.14
     Canter
    -0.14
    cloak
    -0.14
    asto
    -0.14
     mend
    -0.14
    ocate
    -0.14
    ersist
    -0.13
     cages
    -0.13
    POSITIVE LOGITS
     Rug
    0.26
     rifles
    0.25
     rifle
    0.25
     scoped
    0.24
     Winchester
    0.23
     Brow
    0.23
     Colts
    0.22
     caliber
    0.22
     Gat
    0.21
    Scoped
    0.21
    Act Density 0.167%

    No Known Activations