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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to physical attributes or locations, such as heights, buildings, or items found in specific places

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    7601
    -0.51
    ãĤ§
    -0.48
    minist
    -0.47
     USPS
    -0.46
    terness
    -0.46
    ewitness
    -0.44
     Copyright
    -0.44
     guiActiveUn
    -0.44
    htaking
    -0.44
     BALL
    -0.44
    POSITIVE LOGITS
     respectively
    0.74
    iliary
    0.55
     TAMADRA
    0.54
    .''.
    0.53
     mosqu
    0.52
     supplemented
    0.50
    ).[
    0.50
    +.
    0.48
    *.
    0.48
    .
    0.48
    Act Density 1.395%

    No Known Activations