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

    Neuronpedia

    INDEX
    Explanations

    statements and phrases related to political criticism and condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Попис
    -0.60
     linkovi
    -0.59
    :][
    -0.58
     дописавши
    -0.58
     Italijani
    -0.57
    ">//
    -0.57
     هيا
    -0.53
     سكانية
    -0.53
    }';
    -0.53
     continúas
    -0.52
    POSITIVE LOGITS
     condam
    0.60
     abhor
    0.56
    kloped
    0.54
     repugnant
    0.53
    不应该
    0.52
     yrity
    0.51
     vœux
    0.51
     repug
    0.51
     downright
    0.50
     níveis
    0.50
    Act Density 0.425%

    No Known Activations