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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Indented
    -0.56
    philo
    -0.53
     المعيارى
    -0.50
    Slap
    -0.46
    medaille
    -0.43
     gordo
    -0.43
     mainline
    -0.42
    arraycopy
    -0.41
    nowrap
    -0.41
    orElse
    -0.41
    POSITIVE LOGITS
     surely
    1.08
    oubtedly
    1.00
     seguramente
    0.85
     inevitably
    0.85
     undoubtedly
    0.83
     Surely
    0.82
     doubtless
    0.82
    Surely
    0.81
     inevitable
    0.80
    Autoritní
    0.78
    Act Density 0.325%

    No Known Activations