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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols often used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cranes
    -0.60
     île
    -0.52
     religieuses
    -0.51
     herbicides
    -0.50
    花板
    -0.50
     bodas
    -0.49
     zelve
    -0.49
     richied
    -0.49
     hâte
    -0.48
     voudrais
    -0.48
    POSITIVE LOGITS
    IContainer
    0.93
    Хьажоргаш
    0.91
     autorytatywna
    0.85
    '))
    0.85
    Manbalar
    0.84
    TypedDataSet
    0.81
     المعيارى
    0.80
    ')):
    0.78
    '])
    0.78
    '){
    0.76
    Act Density 0.523%

    No Known Activations