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

    Neuronpedia

    INDEX
    Explanations

    references to physical structures such as pits, coals, and barbecues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monticello
    -0.57
    SceneManagement
    -0.50
    MERCE
    -0.48
    NESOTA
    -0.48
     كومونز
    -0.48
    ceptives
    -0.48
    kaido
    -0.46
    IANCE
    -0.46
    ENSUS
    -0.46
    atchewan
    -0.45
    POSITIVE LOGITS
     pit
    1.48
     Pit
    1.47
    Pit
    1.46
     PIT
    1.40
    pit
    1.32
     pits
    1.25
    PIT
    1.25
     Pits
    1.17
     Pitts
    1.09
    pits
    1.05
    Act Density 0.104%

    No Known Activations