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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĻd
    -0.17
    .statusText
    -0.16
     kalan
    -0.15
    ocrat
    -0.14
     Preis
    -0.14
    apro
    -0.14
    plane
    -0.14
    cheid
    -0.14
     FUNC
    -0.14
    ulls
    -0.14
    POSITIVE LOGITS
    kus
    0.16
    iesta
    0.16
    asha
    0.15
    legacy
    0.15
     inclusion
    0.15
    afe
    0.15
    گاÙĩ
    0.14
    aira
    0.14
    Insn
    0.13
     ÐĿаÑģ
    0.13
    Act Density 0.019%

    No Known Activations