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

    Neuronpedia

    INDEX
    Explanations

    prominent and well-known entities, such as figures, thinkers, authors, artists, performers, and personalities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rontal
    -0.75
    Operation
    -0.70
    ãĤ¦ãĤ¹
    -0.65
    ighter
    -0.63
     Wonderland
    -0.60
    dule
    -0.60
    awar
    -0.59
    Gun
    -0.59
     fork
    -0.58
     Winds
    -0.58
    POSITIVE LOGITS
     whom
    1.10
    hips
    1.09
     who
    1.09
     whose
    1.01
    hip
    1.00
    paces
    0.96
    folk
    0.90
     admired
    0.88
    who
    0.88
     laureate
    0.88
    Act Density 0.337%

    No Known Activations