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

    Neuronpedia

    INDEX
    Explanations

    references to political events and statements involving countries and leaders

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whedon
    -1.02
     Slate
    -0.92
     Briggs
    -0.91
     Simmons
    -0.90
     Watkins
    -0.84
     NYC
    -0.82
     Rollins
    -0.81
     Craigslist
    -0.81
    Ohio
    -0.80
     Larson
    -0.80
    POSITIVE LOGITS
     Daesh
    1.08
    )",
    1.06
    ),"
    1.02
     fulfil
    1.01
     manoeuv
    0.96
    .""
    0.96
     martyr
    0.96
     honour
    0.94
     envis
    0.92
    ',"
    0.92
    Act Density 1.500%

    No Known Activations