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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey controversy or hypocrisy in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    at odds, hypocritical, growing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Komunikasi
    -0.52
    ⓧ
    -0.50
     disambiguazione
    -0.48
    ніципалі
    -0.47
    OGND
    -0.46
     дописавши
    -0.46
     desmotivaciones
    -0.45
    CppMethod
    -0.45
     NACIONAL
    -0.44
     surla
    -0.43
    POSITIVE LOGITS
     fig
    0.36
    CreateInfo
    0.35
    CreateMap
    0.35
    Alike
    0.35
    Diweddarwch
    0.34
     Eigen
    0.34
     destabili
    0.34
     Amb
    0.33
     rot
    0.33
    mbh
    0.33
    Act Density 0.078%

    No Known Activations