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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Democratic
    -0.21
    Democratic
    -0.21
     Democrat
    -0.19
     DNC
    -0.19
     Clinton
    -0.17
     Democrats
    -0.17
     Biden
    -0.16
    hlen
    -0.16
     Bernie
    -0.16
     leftist
    -0.15
    POSITIVE LOGITS
     conservatism
    0.22
     Conserv
    0.18
     conservative
    0.17
     conserv
    0.16
     Conservative
    0.16
     conservatives
    0.15
     princip
    0.15
     discipl
    0.15
     Leather
    0.15
    éĽª
    0.15
    Act Density 0.120%

    No Known Activations