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

    Neuronpedia

    INDEX
    Explanations

    documents or sections of text that contain formally written letters or responses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    negie
    -0.69
     STATS
    -0.68
    rolet
    -0.68
     Scion
    -0.65
     Tune
    -0.65
     Occupations
    -0.64
    tics
    -0.62
    rises
    -0.61
     Nex
    -0.59
    alon
    -0.58
    POSITIVE LOGITS
    Letter
    1.11
     letter
    1.06
    letter
    1.01
     addressed
    1.00
     letters
    0.99
     mailed
    0.96
     correspondence
    0.94
     sent
    0.94
     inbox
    0.92
    velop
    0.87
    Act Density 0.526%

    No Known Activations