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

    Neuronpedia

    INDEX
    Explanations

    references to violence and crime, particularly involving severe offenses against individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.09
    3:0.34
    4:0.04
    5:0.09
    6:0.03
    7:0.06
    8:0.07
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
     qualitative
    -2.11
     specialization
    -2.10
     successors
    -2.07
     modes
    -2.03
     foundational
    -2.02
     innovations
    -2.02
     Econom
    -1.96
     Principles
    -1.95
     formulations
    -1.95
     prestige
    -1.94
    POSITIVE LOGITS
     stabbed
    2.69
    police
    2.54
     gunman
    2.52
     kidnap
    2.51
     murdered
    2.46
     vandal
    2.45
     hanged
    2.41
     rapist
    2.38
     kidn
    2.37
     kidnapped
    2.37
    Act Density 1.756%

    No Known Activations