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

    Neuronpedia

    INDEX
    Explanations

    important people, places, and events mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    variations of the letter "L" used in country names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cog
    -0.76
     JPEG
    -0.72
     invention
    -0.71
     yarn
    -0.70
     readings
    -0.70
     implant
    -0.70
     Doodle
    -0.69
     sten
    -0.69
     pretext
    -0.69
     thrill
    -0.68
    POSITIVE LOGITS
    wealth
    1.00
    where
    0.97
    wide
    0.94
    region
    0.93
    istan
    0.91
    ashtra
    0.91
    capital
    0.89
    iversary
    0.87
    sure
    0.87
    quartered
    0.86
    Act Density 0.173%

    No Known Activations