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

    Neuronpedia

    INDEX
    Explanations

    references to influential figures and works in philosophy and literature

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ipment
    -0.90
    BILITIES
    -0.79
    Deploy
    -0.78
    wcs
    -0.78
    localhost
    -0.77
    twitch
    -0.76
    ticket
    -0.76
    AMI
    -0.74
     servicing
    -0.73
    ometown
    -0.72
    POSITIVE LOGITS
     philosophers
    1.47
     Hegel
    1.47
     philosopher
    1.44
     Nietzsche
    1.43
     literary
    1.39
     novelist
    1.35
     Aristotle
    1.35
     poets
    1.33
    olkien
    1.32
     Tolkien
    1.31
    Act Density 1.318%

    No Known Activations