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

    Neuronpedia

    INDEX
    Explanations

    terms related to representation and accuracy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ity
    -0.17
    iteit
    -0.17
    heid
    -0.17
    keit
    -0.16
    anie
    -0.16
    uvre
    -0.16
    ität
    -0.16
    azione
    -0.16
    ung
    -0.16
    ión
    -0.15
    POSITIVE LOGITS
    ations
    0.34
    itions
    0.32
    isations
    0.32
    uations
    0.30
    izations
    0.30
    ences
    0.30
    ulations
    0.30
    iances
    0.30
    aciones
    0.29
    iations
    0.29
    Act Density 0.229%

    No Known Activations