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

    Neuronpedia

    INDEX
    Explanations

    references to violent actions or events, particularly rampages and sprees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.06
    4:0.13
    5:0.03
    6:0.03
    7:0.32
    8:0.03
    9:0.03
    10:0.12
    11:0.08
    Negative Logits
    soDeliveryDate
    -1.64
    addons
    -1.50
    Nit
    -1.49
     certificate
    -1.46
    condition
    -1.46
     referees
    -1.41
    quickShipAvailable
    -1.40
     ORIG
    -1.35
    chance
    -1.33
    qualified
    -1.32
    POSITIVE LOGITS
     spree
    1.68
     looting
    1.54
    ultane
    1.52
     murdering
    1.45
     rampage
    1.42
    LOS
    1.38
     hatred
    1.36
     carnage
    1.35
     THR
    1.34
     spew
    1.34
    Act Density 0.002%

    No Known Activations