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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical data in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.00
     propOrder
    -0.92
    AntiForgeryToken
    -0.88
    بوابة
    -0.87
    IsContent
    -0.84
    astéro
    -0.83
    setVerticalGroup
    -0.82
     pleaſure
    -0.79
    AutoScaleMode
    -0.78
    SequentialGroup
    -0.76
    POSITIVE LOGITS
     
    0.62
     but
    0.49
    9
    0.49
     a
    0.48
    1
    0.48
     .
    0.46
    .
    0.44
    ↵
    0.43
     plus
    0.43
     Franklin
    0.42
    Act Density 0.435%

    No Known Activations