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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and their corresponding data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.57
    &#
    -0.49
     
    -0.48
     "
    -0.48
    .
    -0.47
     -
    -0.47
     mệnh
    -0.47
    丙
    -0.45
    jshint
    -0.44
    ňte
    -0.44
    POSITIVE LOGITS
    verwijspagina
    1.00
     myſelf
    1.00
    :✨
    0.96
     виправивши
    0.93
     Efq
    0.93
     becauſe
    0.91
     Monfieur
    0.90
     itſelf
    0.90
     Theſe
    0.88
     whoſe
    0.87
    Act Density 0.038%

    No Known Activations