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

    Neuronpedia

    INDEX
    Explanations

    variables and parameters often associated with mathematical expressions or scientific models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.04
     للاسماء
    -1.02
     تضيفلها
    -0.96
     linkovi
    -0.94
     Theſe
    -0.93
     ***!
    -0.91
     himſelf
    -0.91
     myſelf
    -0.91
     leaſt
    -0.89
     resourceCulture
    -0.86
    POSITIVE LOGITS
     final
    0.44
     ‘
    0.43
     Pro
    0.43
     interesar
    0.41
     a
    0.40
    kunta
    0.39
    ttemberg
    0.39
     del
    0.38
     —
    0.38
     pro
    0.37
    Act Density 0.911%

    No Known Activations