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

    Neuronpedia

    INDEX
    Explanations

    words related to different areas such as sports contracts, marine conservation, love, and celestial bodies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.78
     causation
    -0.77
     confines
    -0.74
    OPLE
    -0.72
     CPC
    -0.72
     goats
    -0.71
     spat
    -0.71
     responsibility
    -0.70
     sanity
    -0.67
     wrath
    -0.67
    POSITIVE LOGITS
    leck
    1.04
    ratulations
    1.02
    Wan
    1.02
    wald
    0.96
    uary
    0.94
    aqu
    0.93
    worldly
    0.90
    orio
    0.88
    lette
    0.86
    thal
    0.85
    Act Density 8.404%

    No Known Activations