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

    Neuronpedia

    INDEX
    Explanations

    content related to historical accuracy and real-life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.62
    +#+#
    -0.61
    GOTREF
    -0.60
    ArrowToggle
    -0.58
    IndentedString
    -0.56
    <bos>
    -0.54
    一言
    -0.54
     Roskov
    -0.52
    Compat
    -0.51
    aronder
    -0.51
    POSITIVE LOGITS
     real
    2.99
     actual
    2.63
    real
    2.58
    actual
    2.50
     réel
    2.43
     REAL
    2.36
     vrai
    2.35
    Actual
    2.34
     reales
    2.34
     réelle
    2.33
    Act Density 0.933%

    No Known Activations