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

    Neuronpedia

    INDEX
    Explanations

    incidents involving injuries and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krom
    -0.15
    Sink
    -0.15
    993
    -0.15
    exter
    -0.14
    uet
    -0.14
    atta
    -0.14
    entine
    -0.14
     murderer
    -0.14
    ascus
    -0.14
    ÅĻes
    -0.14
    POSITIVE LOGITS
     injured
    0.56
     wounded
    0.52
     injury
    0.52
     injuries
    0.50
     Injury
    0.46
     seriously
    0.41
     injuring
    0.37
     inj
    0.37
    伤
    0.36
     wounds
    0.36
    Act Density 0.161%

    No Known Activations