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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     est
    -0.55
     plus
    -0.55
    '])
    -0.55
    více
    -0.55
    '][]
    -0.55
     But
    -0.55
     que
    -0.54
    "])
    -0.54
     Far
    -0.53
     dans
    -0.52
    POSITIVE LOGITS
     Shakspeare
    0.97
     Negroes
    0.94
     uſ
    0.87
     Shaksp
    0.85
     juſt
    0.84
     diſt
    0.82
     leſs
    0.82
     fevere
    0.81
     greateſt
    0.81
     poffible
    0.81
    Act Density 0.035%

    No Known Activations