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

    Neuronpedia

    INDEX
    Explanations

    significant political figures and their positions within the party structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     progressive
    -0.17
    Democratic
    -0.17
     Democratic
    -0.17
     Progressive
    -0.16
     queer
    -0.16
    æ°ij主
    -0.16
    Æ¡
    -0.16
    æĥij
    -0.15
    wort
    -0.15
    uten
    -0.15
    POSITIVE LOGITS
     liberty
    0.29
     conservative
    0.27
     conservatism
    0.25
     Conserv
    0.24
     conservatives
    0.24
     Jude
    0.23
     Conservative
    0.22
     Liberty
    0.22
     freedom
    0.22
     libert
    0.21
    Act Density 0.042%

    No Known Activations