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

    Neuronpedia

    INDEX
    Explanations

    words and terms related to environmental issues and the authority of governing organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.03
    3:0.04
    4:0.07
    5:0.14
    6:0.10
    7:0.28
    8:0.04
    9:0.03
    10:0.03
    11:0.06
    Negative Logits
    ctrl
    -2.13
    �
    -2.03
    govtrack
    -1.98
    uple
    -1.95
    grave
    -1.90
     Kaf
    -1.89
    lich
    -1.88
     blurred
    -1.86
     Reese
    -1.84
     ape
    -1.79
    POSITIVE LOGITS
    ocry
    2.26
    soType
    2.17
     References
    2.09
    sites
    2.07
    ⓘ
    2.04
     distribution
    1.99
    urations
    1.98
    SpaceEngineers
    1.95
     adaptation
    1.95
     winters
    1.94
    Act Density 0.005%

    No Known Activations