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

    Neuronpedia

    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    %.
    -0.70
    %).
    -0.61
    onga
    -0.58
    $.
    -0.58
    }.
    -0.56
    };
    -0.54
     attRot
    -0.53
    .).
    -0.51
    +.
    -0.49
    >.
    -0.49
    POSITIVE LOGITS
     yesterday
    1.17
     earlier
    0.92
     Wednesday
    0.92
     Tuesday
    0.91
     Thursday
    0.91
     shortly
    0.90
     Monday
    0.83
     tonight
    0.82
     recently
    0.82
     Friday
    0.82
    Act Density 1.574%

    No Known Activations