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

    Neuronpedia

    INDEX
    Explanations

    references to violent crime and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.20
    4:0.03
    5:0.03
    6:0.12
    7:0.18
    8:0.04
    9:0.06
    10:0.07
    11:0.09
    Negative Logits
    版
    -1.40
     pse
    -1.25
     Goose
    -1.22
     Horizons
    -1.16
    vre
    -1.15
     Seed
    -1.15
    ritz
    -1.14
     floated
    -1.13
     Wonders
    -1.11
    kefeller
    -1.10
    POSITIVE LOGITS
     abusive
    1.24
    ansk
    1.18
     DUI
    1.08
     heroin
    1.06
     insurgent
    1.04
     extortion
    1.03
    ��
    1.03
     morphine
    1.02
     methamphetamine
    1.01
     inj
    0.99
    Act Density 0.029%

    No Known Activations