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

    Neuronpedia

    INDEX
    Explanations

    medical terms and names related to political power and world affairs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Marie
    -0.79
    ources
    -0.71
     unanim
    -0.71
     Jury
    -0.71
    know
    -0.70
     unanimous
    -0.70
    ngth
    -0.68
    Dispatch
    -0.68
    MW
    -0.67
     drib
    -0.66
    POSITIVE LOGITS
    ĪĴ
    0.85
    dit
    0.85
    edia
    0.84
    istan
    0.81
    ylon
    0.80
     Beaut
    0.79
    nia
    0.78
    aneers
    0.77
     Laboratories
    0.76
    levard
    0.75
    Act Density 15.914%

    No Known Activations