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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments expressed towards society and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ansvar
    -0.51
     épais
    -0.50
     embarazadas
    -0.49
     juger
    -0.48
     råd
    -0.48
     concorso
    -0.47
     tecnici
    -0.46
     espírito
    -0.46
     manhã
    -0.45
     jovens
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.90
     дописавши
    0.89
    StructEnd
    0.87
    الحياه
    0.86
    Przypisy
    0.85
    tagHelperRunner
    0.85
    GOTREF
    0.82
     Taktlose
    0.80
    RegressionTest
    0.80
    تقاوى
    0.78
    Act Density 0.131%

    No Known Activations