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

    Neuronpedia

    INDEX
    Explanations

    titles, names, and author affiliations in academic articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iage
    -1.08
    =-=-=-=-
    -1.05
    allery
    -1.04
    atform
    -1.04
    ItemTracker
    -1.04
    amental
    -1.02
    staff
    -1.02
    è»
    -1.01
    ancial
    -1.01
    owler
    -0.92
    POSITIVE LOGITS
    ktop
    1.94
    terday
    1.88
    earch
    1.63
    earchers
    1.63
    peed
    1.52
    andro
    1.47
    bians
    1.45
    leep
    1.41
    ury
    1.38
    pec
    1.37
    Act Density 1.624%

    No Known Activations