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

    Neuronpedia

    INDEX
    Explanations

    topics related to government policies and laws affecting society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.01
    2:0.13
    3:0.08
    4:0.07
    5:0.04
    6:0.04
    7:0.02
    8:0.09
    9:0.07
    10:0.11
    11:0.11
    Negative Logits
    mediately
    -1.52
    ogle
    -1.47
     approx
    -1.43
    ipeg
    -1.37
    requently
    -1.34
    undred
    -1.30
    roximately
    -1.28
     trough
    -1.28
    itely
    -1.28
    ociated
    -1.27
    POSITIVE LOGITS
     etc
    2.21
    etc
    1.69
    politics
    1.49
    iferation
    1.47
     blah
    1.46
    olitics
    1.44
     Achievement
    1.43
    anship
    1.39
    opathy
    1.37
    �
    1.36
    Act Density 0.165%

    No Known Activations