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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terms related to substances and chemicals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ership
    -0.85
    kus
    -0.80
    Books
    -0.75
    irc
    -0.70
    udeb
    -0.70
    Plex
    -0.69
    Fal
    -0.68
    ENG
    -0.66
    Cent
    -0.66
    esan
    -0.66
    POSITIVE LOGITS
     ions
    0.97
     additives
    0.95
     chemically
    0.95
     substances
    0.93
     soluble
    0.88
     compounds
    0.88
     molecules
    0.86
    icity
    0.84
     glutamate
    0.84
     secondly
    0.83
    Act Density 13.187%

    No Known Activations