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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal actions and criminal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.11
    3:0.04
    4:0.05
    5:0.11
    6:0.07
    7:0.07
    8:0.07
    9:0.07
    10:0.14
    11:0.06
    Negative Logits
     evolves
    -1.64
    ankind
    -1.62
    ◼
    -1.39
    angular
    -1.39
     coales
    -1.33
     fades
    -1.31
    Sense
    -1.29
    Tokens
    -1.29
     evolve
    -1.27
    DragonMagazine
    -1.25
    POSITIVE LOGITS
     unlawfully
    1.69
     illegally
    1.67
     convicted
    1.61
     criminally
    1.58
     accused
    1.52
     felon
    1.49
     suspected
    1.49
     unsuccessfully
    1.47
     felony
    1.47
     misdemeanor
    1.44
    Act Density 0.038%

    No Known Activations