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

    Neuronpedia

    INDEX
    Explanations

    references to political donors and their influence on campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Democratic
    -0.28
    Democratic
    -0.23
     Progressive
    -0.23
     progressives
    -0.23
     progressive
    -0.22
     DNC
    -0.22
     Biden
    -0.21
     Democrats
    -0.21
     Labor
    -0.20
     Democrat
    -0.20
    POSITIVE LOGITS
     Conserv
    0.31
     conserv
    0.31
     conservatism
    0.30
     conservative
    0.25
     tea
    0.25
     Tea
    0.25
     conservatives
    0.24
     GOP
    0.23
     conserve
    0.23
     Jeb
    0.22
    Act Density 0.116%

    No Known Activations