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

    Neuronpedia

    INDEX
    Explanations

    incidents of violence and crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.02
    3:0.16
    4:0.19
    5:0.07
    6:0.09
    7:0.02
    8:0.17
    9:0.06
    10:0.02
    11:0.01
    Negative Logits
    iture
    -1.97
    merce
    -1.84
    asury
    -1.83
    folio
    -1.79
    ulas
    -1.75
     Centauri
    -1.65
    cca
    -1.58
    hops
    -1.57
     portfolios
    -1.54
    ocry
    -1.53
    POSITIVE LOGITS
     injuring
    2.32
     attackers
    2.07
     gunman
    2.01
     assailants
    1.87
     prompting
    1.79
     killing
    1.78
     gunmen
    1.77
    andals
    1.76
     wounding
    1.75
     unarmed
    1.75
    Act Density 0.142%

    No Known Activations