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

    Neuronpedia

    INDEX
    Explanations

    statements or declarations made within an official report

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Occup
    -0.66
    pron
    -0.65
    grain
    -0.64
     Maker
    -0.64
    Pont
    -0.63
    ben
    -0.63
    brook
    -0.62
    acqu
    -0.62
     spectator
    -0.61
    patch
    -0.61
    POSITIVE LOGITS
     titled
    0.74
     furthermore
    0.70
     summar
    0.70
     scathing
    0.70
     quoting
    0.69
     omin
    0.69
     comprises
    0.68
     seq
    0.66
     authors
    0.66
     convinc
    0.65
    Act Density 10.210%

    No Known Activations