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

    Neuronpedia

    INDEX
    Explanations

    differences or distinctions between various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    roll
    -0.94
    Bern
    -0.93
    azz
    -0.92
    tti
    -0.92
    iverse
    -0.92
    inet
    -0.90
    anced
    -0.90
    icago
    -0.90
    whe
    -0.87
    Bah
    -0.87
    POSITIVE LOGITS
     ours
    1.23
    lihood
    1.07
     what
    0.97
    otin
    0.89
     those
    0.88
     hers
    0.83
     anything
    0.83
     [+
    0.81
     usual
    0.80
     our
    0.80
    Act Density 1.048%

    No Known Activations