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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to regulatory or legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.39
    2:0.03
    3:0.02
    4:0.03
    5:0.20
    6:0.02
    7:0.01
    8:0.05
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
    �
    -1.70
     salsa
    -1.57
    Marvel
    -1.56
    imation
    -1.55
    ms
    -1.52
    ¯¯
    -1.51
    ym
    -1.50
    MAP
    -1.50
    aucuses
    -1.49
    Jeremy
    -1.48
    POSITIVE LOGITS
    Or
    1.93
     or
    1.87
     lawy
    1.80
     Or
    1.78
     unlaw
    1.77
     occas
    1.70
     embr
    1.69
     agre
    1.69
    ebin
    1.68
    or
    1.66
    Act Density 0.037%

    No Known Activations