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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies and affiliations, particularly conservative and liberal perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.22
    1:0.03
    2:0.07
    3:0.02
    4:0.07
    5:0.04
    6:0.17
    7:0.05
    8:0.04
    9:0.03
    10:0.14
    11:0.08
    Negative Logits
     Gou
    -1.13
     Minotaur
    -1.09
     Ambro
    -1.06
     Kik
    -1.04
     Tsu
    -1.03
     simulator
    -1.02
     Array
    -1.02
     Finder
    -1.01
     auction
    -1.01
     Tunnel
    -1.00
    POSITIVE LOGITS
    ervative
    1.34
    galitarian
    1.29
    meric
    1.26
     partisans
    1.25
    gressive
    1.23
    ervatives
    1.21
    idy
    1.20
    riors
    1.19
     creed
    1.18
    hemy
    1.17
    Act Density 0.061%

    No Known Activations