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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal, political, and social issues or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    matically
    -0.94
    elled
    -0.85
     toget
    -0.84
    LET
    -0.82
     crushing
    -0.78
     tremend
    -0.78
     daunting
    -0.77
    ighty
    -0.76
     disg
    -0.76
    ucci
    -0.75
    POSITIVE LOGITS
     Ones
    1.29
     Guys
    1.16
     Skies
    1.15
     Realms
    1.14
     Objects
    1.14
     Opportun
    1.13
     Characters
    1.12
     Conduct
    1.12
     Items
    1.11
     Moments
    1.10
    Act Density 14.696%

    No Known Activations