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
    ossier
    -0.20
     Pepper
    -0.15
    глÑıд
    -0.14
    Ton
    -0.14
     acomp
    -0.13
     addCriterion
    -0.13
    icÃŃ
    -0.13
     biç
    -0.13
     dedi
    -0.13
    олов
    -0.13
    POSITIVE LOGITS
    vest
    0.15
    EATURE
    0.15
    vas
    0.15
    ument
    0.15
    667
    0.14
    lez
    0.14
    ean
    0.14
    agram
    0.14
    owie
    0.14
    otope
    0.14
    Act Density 0.368%

    No Known Activations