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

    Neuronpedia

    INDEX
    Explanations

    references to political affiliations and voter behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moo
    -0.16
    Americans
    -0.15
     Americans
    -0.15
    ronics
    -0.15
    ÑĨа
    -0.15
    inois
    -0.14
    å±ĭ
    -0.14
    paque
    -0.14
    à¸Ĭ
    -0.13
    nodoc
    -0.13
    POSITIVE LOGITS
     Labour
    0.29
     seats
    0.26
     Labor
    0.26
     LAB
    0.25
     Leave
    0.25
     Lab
    0.23
     Lib
    0.23
     Conservative
    0.22
     leaf
    0.22
     Tory
    0.22
    Act Density 0.090%

    No Known Activations