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

    Neuronpedia

    INDEX
    Explanations

    terms related to political topics and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ような
    -0.68
    ные
    -0.66
    ulatory
    -0.65
    чные
    -0.64
    готови
    -0.64
    illary
    -0.64
    chial
    -0.64
    amerikanischer
    -0.63
    ptian
    -0.62
    itake
    -0.62
    POSITIVE LOGITS
     Protestantism
    1.23
     Judaism
    1.19
    Semitism
    1.18
     Buddhism
    1.17
     Communism
    1.12
     Catholicism
    1.10
     Feminism
    1.09
     dentistry
    1.09
     liberalism
    1.09
     communism
    1.08
    Act Density 1.389%

    No Known Activations