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

    Neuronpedia

    INDEX
    Explanations

    various types of nouns and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fior
    -0.15
    ancellor
    -0.14
    usting
    -0.14
    GT
    -0.14
    actus
    -0.14
    à¥įà¤ķर
    -0.14
    UBY
    -0.14
    inho
    -0.13
    azaar
    -0.13
    ych
    -0.13
    POSITIVE LOGITS
    _prot
    0.16
    \Bundle
    0.16
    ropa
    0.16
     Sporting
    0.16
     Minor
    0.15
    าà¸Ļ
    0.15
    ä¼´
    0.14
    mods
    0.14
     Dillon
    0.14
    addir
    0.14
    Act Density 0.002%

    No Known Activations