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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating definitions or explanations of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    478
    -0.16
    ano
    -0.16
    à¸ķà¸Ļ
    -0.15
    tout
    -0.14
    271
    -0.14
    acionales
    -0.14
    uyo
    -0.14
    lem
    -0.14
    ica
    -0.14
    ETERS
    -0.14
    POSITIVE LOGITS
    Ĺi
    0.15
    yre
    0.15
    quence
    0.14
    .words
    0.14
    ucher
    0.14
    eru
    0.14
     facts
    0.14
    ecut
    0.14
    ento
    0.14
     Giles
    0.13
    Act Density 0.018%

    No Known Activations