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

    Neuronpedia

    INDEX
    Explanations

    references to criminal activities and legal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     massac
    -0.17
    kills
    -0.16
     massacre
    -0.16
     executions
    -0.16
     shooters
    -0.16
    æĿĢ
    -0.16
     killers
    -0.15
     killings
    -0.15
     killed
    -0.15
     slaughtered
    -0.15
    POSITIVE LOGITS
     punches
    0.34
     physical
    0.31
     punched
    0.30
     punching
    0.29
     punch
    0.29
     Physical
    0.28
    Physical
    0.28
     physically
    0.28
     Punch
    0.28
    physical
    0.27
    Act Density 0.218%

    No Known Activations