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

    Neuronpedia

    INDEX
    Explanations

    architectural features and decorative elements in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESIS
    -0.15
    eder
    -0.15
     Fold
    -0.14
    Directed
    -0.14
    rupa
    -0.14
    rale
    -0.14
    ungs
    -0.14
     Added
    -0.13
     Confidential
    -0.13
    æĶ¾åľ¨
    -0.13
    POSITIVE LOGITS
     deck
    0.40
    deck
    0.35
     Deck
    0.35
    Deck
    0.30
     covered
    0.28
     fest
    0.27
     bed
    0.27
     decks
    0.26
     done
    0.24
    -bed
    0.23
    Act Density 0.225%

    No Known Activations