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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mojom
    -0.16
    879
    -0.16
     Lange
    -0.16
    ry
    -0.15
     greed
    -0.15
    ksen
    -0.15
    odore
    -0.14
    317
    -0.14
    TRL
    -0.14
     kır
    -0.14
    POSITIVE LOGITS
    iterr
    0.17
    yre
    0.15
    azen
    0.15
    oÄŁ
    0.15
    untas
    0.15
    les
    0.14
    iew
    0.14
    lesia
    0.14
    si
    0.14
    avenport
    0.14
    Act Density 0.088%

    No Known Activations