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

    Neuronpedia

    INDEX
    Explanations

    legal or policy-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    statements concerning the legitimacy of executive orders and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.92
     experien
    -0.84
    ukong
    -0.84
    enne
    -0.82
    sburg
    -0.79
     RTX
    -0.78
    odiac
    -0.78
     Remastered
    -0.71
    ibel
    -0.68
     Saud
    -0.67
    POSITIVE LOGITS
     counterproductive
    1.60
     unconstitutional
    1.54
     ineffective
    1.53
     unsustainable
    1.40
     wasteful
    1.39
     impractical
    1.39
     discriminatory
    1.39
     inefficient
    1.33
     unethical
    1.32
     unnecessary
    1.32
    Act Density 0.357%

    No Known Activations