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

    Neuronpedia

    INDEX
    Explanations

    terms related to the criminalization of actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.05
    4:0.12
    5:0.03
    6:0.03
    7:0.36
    8:0.02
    9:0.03
    10:0.13
    11:0.09
    Negative Logits
     consolation
    -1.55
    vation
    -1.54
    equal
    -1.51
     reassure
    -1.51
    ensional
    -1.49
    igsaw
    -1.45
    erential
    -1.41
    goal
    -1.40
    geon
    -1.40
     cushion
    -1.40
    POSITIVE LOGITS
     violations
    1.65
     tampering
    1.63
     crimes
    1.58
     Crime
    1.58
     felony
    1.58
     criminal
    1.56
     criminally
    1.48
     arrest
    1.47
     manslaughter
    1.46
     exploitation
    1.46
    Act Density 0.003%

    No Known Activations