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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting or mentioning sources and their quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //{{
    -0.18
    @dynamic
    -0.16
    \Id
    -0.15
    TEE
    -0.14
    話
    -0.14
    berry
    -0.14
    оÑģÑĮ
    -0.14
    razier
    -0.14
     grunt
    -0.14
    meli
    -0.14
    POSITIVE LOGITS
    fault
    0.15
     fault
    0.15
    oppins
    0.15
    entic
    0.15
    zzo
    0.15
    ürn
    0.14
    erator
    0.14
    incy
    0.14
    691
    0.14
    629
    0.14
    Act Density 0.288%

    No Known Activations