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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of certainty or emphasis in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAPE
    -0.59
    éroport
    -0.55
    estinations
    -0.53
    abetes
    -0.52
    chmal
    -0.51
     ſeveral
    -0.51
    –¿
    -0.51
    scription
    -0.50
    Скачать
    -0.50
     setLoading
    -0.50
    POSITIVE LOGITS
    verständlich
    0.83
     obviously
    0.80
     natürlich
    0.79
     ovviamente
    0.79
     obviamente
    0.79
     évidemment
    0.76
     natuurlijk
    0.73
    følgelig
    0.72
    obviously
    0.70
     Natürlich
    0.70
    Act Density 0.231%

    No Known Activations