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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies and party affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.94
     مرئيه
    -0.77
     ileti
    -0.76
    LookAnd
    -0.72
     utafitiHapana
    -0.70
    êque
    -0.70
     Sinf
    -0.70
     résidence
    -0.68
     Rodrig
    -0.64
    abestanden
    -0.64
    POSITIVE LOGITS
    mopolitan
    0.79
    conservative
    0.72
     conservative
    0.72
     liberal
    0.68
    Clique
    0.60
     mainstream
    0.60
     conservatism
    0.59
    Liberal
    0.58
     gauche
    0.58
     minded
    0.57
    Act Density 0.240%

    No Known Activations