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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical events and political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    opian
    -0.97
     level
    -0.94
     redress
    -0.91
    eks
    -0.91
    erest
    -0.89
     drain
    -0.85
    angible
    -0.84
    obe
    -0.84
    irds
    -0.82
     wildlife
    -0.82
    POSITIVE LOGITS
    whose
    1.59
    which
    1.46
    formerly
    1.45
    particularly
    1.33
    who
    1.33
    along
    1.29
    currently
    1.29
    perhaps
    1.24
    ––
    1.24
     aka
    1.24
    Act Density 1.574%

    No Known Activations