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

    Neuronpedia

    INDEX
    Explanations

    proper names, likely names of people or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Decre
    -0.73
    planes
    -0.68
    process
    -0.63
     heights
    -0.60
     trunc
    -0.59
    Results
    -0.57
     ital
    -0.57
    FIX
    -0.57
     misunder
    -0.57
     feast
    -0.56
    POSITIVE LOGITS
     Jr
    1.02
     Sr
    0.97
     chairman
    0.92
     director
    0.90
     dean
    0.89
     spokesman
    0.89
     founder
    0.88
     aka
    0.87
     QC
    0.86
     PhD
    0.85
    Act Density 0.113%

    No Known Activations