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

    Neuronpedia

    INDEX
    Explanations

    Information related to technical specifications and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.82
    public
    -0.82
    //
    -0.81
    -0.75
    -0.75
    for
    -0.75
    0
    -0.73
    <h1>
    -0.73
    -0.72
    -0.72
    POSITIVE LOGITS
     stockholm
    1.80
     maneu
    1.66
     lidl
    1.65
     milf
    1.58
     wikihow
    1.55
     impra
    1.55
     quoique
    1.55
     véhic
    1.50
     affor
    1.49
     peppa
    1.49
    Act Density 0.284%

    No Known Activations