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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.15
    UMAN
    -0.14
    enstein
    -0.14
    arakter
    -0.14
    oppins
    -0.14
    emetery
    -0.14
     Penal
    -0.14
    deniz
    -0.14
    าศ
    -0.13
     enough
    -0.13
    POSITIVE LOGITS
     sure
    0.18
    gets
    0.15
    asts
    0.15
     mı
    0.15
    arded
    0.15
    @ResponseBody
    0.14
    ignet
    0.14
    _sta
    0.14
    uard
    0.13
    Sure
    0.13
    Act Density 0.059%

    No Known Activations