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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies, specifically liberalism and socialism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.81
     mystérie
    -0.66
    клопе
    -0.65
    adple
    -0.61
     Signalez
    -0.61
    ();)
    -0.59
     flyknit
    -0.59
    Economía
    -0.59
     pério
    -0.59
     dignidad
    -0.59
    POSITIVE LOGITS
    mopolitan
    0.75
    leaning
    0.63
     conservative
    0.60
    inist
    0.60
    biased
    0.60
     tendencies
    0.59
    conservative
    0.57
     bias
    0.56
    лизм
    0.54
     grammes
    0.53
    Act Density 0.266%

    No Known Activations