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

    Neuronpedia

    INDEX
    Explanations

    names of people or specific individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    prus
    -0.62
     captcha
    -0.57
    cients
    -0.53
    anwhile
    -0.53
     unrestricted
    -0.51
     buzzing
    -0.51
     redistributed
    -0.51
     deficits
    -0.50
     collisions
    -0.50
    ancies
    -0.50
    POSITIVE LOGITS
    *,
    1.11
    ,
    0.93
     QC
    0.91
     Jr
    0.90
    !,
    0.88
    ?,
    0.88
     Sr
    0.86
     ,
    0.85
    ,,
    0.85
    ,[
    0.83
    Act Density 0.253%

    No Known Activations