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

    Neuronpedia

    INDEX
    Explanations

    names of different individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eer
    -0.63
    e
    -0.61
     compensated
    -0.60
     shattered
    -0.59
    eva
    -0.59
     patiently
    -0.59
    eers
    -0.58
     Dollars
    -0.58
     spirited
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.58
    POSITIVE LOGITS
    eston
    1.10
    opez
    1.09
    iffe
    1.09
    oyd
    1.05
    uminati
    1.04
    ateral
    1.04
    ayers
    1.02
    ibraries
    1.01
    ution
    1.00
    yrics
    1.00
    Act Density 0.041%

    No Known Activations