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

    Neuronpedia

    INDEX
    Explanations

    references to investigations or criminal activities related to LGBTQ+ events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     leftist
    -0.24
     progressive
    -0.23
     progressives
    -0.23
     Democratic
    -0.23
     Progressive
    -0.23
    Democratic
    -0.22
     DNC
    -0.19
    æ°ij主
    -0.19
     Democrat
    -0.19
     democratic
    -0.18
    POSITIVE LOGITS
     conservative
    0.34
     conservatism
    0.32
     conservatives
    0.30
     Tea
    0.30
     Conserv
    0.27
     Conservative
    0.26
     conserv
    0.26
     Conservatives
    0.23
     tea
    0.22
     GOP
    0.22
    Act Density 0.413%

    No Known Activations