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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideology, particularly conservative and liberal viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     privées
    -0.78
     виправивши
    -0.70
    quelize
    -0.64
     المعيارى
    -0.59
    (!__
    -0.59
    AccessorTable
    -0.58
     Commander
    -0.58
     Commanders
    -0.58
     étrangères
    -0.57
    ambique
    -0.57
    POSITIVE LOGITS
     conservative
    0.88
     liberal
    0.79
    conservative
    0.73
     conservatives
    0.72
     konserv
    0.69
    Liberal
    0.69
    liberal
    0.69
     conservatism
    0.68
    Conservative
    0.67
     liberals
    0.64
    Act Density 0.367%

    No Known Activations