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

    Neuronpedia

    INDEX
    Explanations

    words related to groupings or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seau
    -0.17
    \core
    -0.15
     Demp
    -0.15
    zano
    -0.15
    ARGER
    -0.15
    loub
    -0.15
    BJECT
    -0.15
    undler
    -0.14
    jing
    -0.14
    BuilderInterface
    -0.14
    POSITIVE LOGITS
    son
    0.15
    ing
    0.15
    ost
    0.14
    DDL
    0.14
    ÑĪин
    0.14
    ings
    0.13
    orama
    0.13
    avity
    0.13
     Ster
    0.13
    erson
    0.13
    Act Density 0.024%

    No Known Activations