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
    er
    -0.14
    these
    -0.14
     ByVal
    -0.14
     CY
    -0.14
    anco
    -0.14
     hearing
    -0.14
    enko
    -0.13
    umbo
    -0.13
    QA
    -0.13
    itet
    -0.13
    POSITIVE LOGITS
    ames
    0.17
    ecut
    0.17
    ek
    0.15
     advice
    0.15
    ÃŃrk
    0.14
     mÃŃ
    0.14
    eki
    0.14
    rado
    0.14
    .mx
    0.14
    undry
    0.14
    Act Density 0.018%

    No Known Activations