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

    Neuronpedia

    INDEX
    Explanations

    proposals related to political or cultural critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vanden
    -0.69
     Adkins
    -0.64
     Pom
    -0.64
    |}{$
    -0.63
     Zah
    -0.62
     HATE
    -0.61
     Hodges
    -0.61
     Luk
    -0.60
    เลข
    -0.60
     lotta
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.97
     متعلقه
    0.88
    出版年
    0.88
     resourceCulture
    0.85
    </h3>
    0.84
     Audiodateien
    0.82
    }))
    0.81
    featureID
    0.80
    ']")
    0.79
    </em>
    0.78
    Act Density 0.047%

    No Known Activations