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

    Neuronpedia

    INDEX
    Explanations

    instances of serious injuries and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wounded
    -0.16
     une
    -0.15
    inea
    -0.15
     tired
    -0.15
    ä¹±
    -0.15
    æĥij
    -0.15
     hurting
    -0.15
    gid
    -0.14
     murdered
    -0.14
     illness
    -0.14
    POSITIVE LOGITS
     permanently
    0.24
     nearly
    0.23
     require
    0.22
     staples
    0.21
     requiring
    0.21
     requires
    0.21
     almost
    0.21
    almost
    0.20
     Requires
    0.20
    requ
    0.20
    Act Density 0.078%

    No Known Activations