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

    Neuronpedia

    INDEX
    Explanations

    metaphorical expressions describing updates or changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Updated" indicating revisions or updates to information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gravity
    -0.81
    ":[{"
    -0.79
    aden
    -0.77
    natureconservancy
    -0.75
    ften
    -0.74
    belt
    -0.73
    ohm
    -0.73
    zig
    -0.72
    stood
    -0.71
    Js
    -0.70
    POSITIVE LOGITS
     versions
    0.80
     timestamp
    0.74
    irement
    0.70
     version
    0.70
     VERS
    0.69
     Updates
    0.67
     Update
    0.67
     hourly
    0.67
     millenn
    0.66
     editions
    0.65
    Act Density 0.013%

    No Known Activations