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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate detailed scientific or mathematical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.56
    ’
    -0.54
    -
    -0.53
     &
    -0.53
     ‘
    -0.52
     mit
    -0.52
     
    -0.51
    ‘
    -0.49
    _
    -0.49
    ⁦
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.88
    awtextra
    0.85
     pleaſure
    0.83
     deſt
    0.82
    CppCodeGen
    0.81
    MLLoader
    0.80
     Réponses
    0.80
     تضيفلها
    0.79
    </table>
    0.77
     CreateTagHelper
    0.75
    Act Density 0.293%

    No Known Activations