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

    Neuronpedia

    INDEX
    Explanations

    numerical data and citations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    kids
    -0.75
    Kids
    -0.70
    bucks
    -0.67
    RELATED
    -0.66
    MORE
    -0.65
    Shop
    -0.65
    pping
    -0.65
    doors
    -0.64
     snapped
    -0.64
    Luckily
    -0.63
    POSITIVE LOGITS
     methodological
    1.10
     empirical
    1.08
     theorem
    1.02
     philosophers
    1.02
     manuscript
    1.01
     literature
    0.99
     manuscripts
    0.98
     textual
    0.98
     epist
    0.96
     authors
    0.94
    Act Density 1.030%

    No Known Activations