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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating contrasts or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decently
    -0.53
     himself
    -0.52
    ftagPool
    -0.50
    himself
    -0.50
    Anyways
    -0.49
    Итак
    -0.49
     же
    -0.49
     cherchés
    -0.49
    Пока
    -0.48
     shall
    -0.48
    POSITIVE LOGITS
     Majefty
    1.07
     purpoſe
    1.06
     ſtate
    1.06
     Jefus
    1.00
     itſelf
    0.99
     uſed
    0.97
     uſe
    0.96
     pleaſure
    0.96
     reaſon
    0.95
     Efq
    0.95
    Act Density 2.888%

    No Known Activations