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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or references to ranks in a list or hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utzer
    -0.16
     Burl
    -0.15
    âĶĶ
    -0.15
    jured
    -0.15
    idual
    -0.15
    éĴŁ
    -0.14
    uten
    -0.14
    βάλ
    -0.14
     EVP
    -0.13
     Way
    -0.13
    POSITIVE LOGITS
     bunch
    0.63
     lot
    0.60
    lot
    0.43
     Lot
    0.40
    Lot
    0.38
     LOT
    0.37
     batch
    0.32
    _lot
    0.30
    LOT
    0.29
    batch
    0.28
    Act Density 0.025%

    No Known Activations