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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and adjectives related to entities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oid
    -0.17
    eon
    -0.15
    erc
    -0.15
    meden
    -0.15
    orage
    -0.14
    sha
    -0.14
    gons
    -0.14
    ãĤ¤ãĥĪ
    -0.14
    ond
    -0.14
    902
    -0.13
    POSITIVE LOGITS
    ãģıãĤĮ
    0.16
    owi
    0.15
    obo
    0.15
    airo
    0.15
    isseur
    0.14
    icie
    0.14
    zilla
    0.14
    NotFoundException
    0.14
    působ
    0.14
    isse
    0.13
    Act Density 0.088%

    No Known Activations