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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the word "that" to highlight actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endphp
    -0.64
    WireFormat
    -0.63
    trise
    -0.62
     akong
    -0.62
     ویکی‌پدیا
    -0.59
     wikipagina
    -0.54
    webElementXpaths
    -0.54
    TabbedPane
    -0.53
     PHA
    -0.52
     Royce
    -0.52
    POSITIVE LOGITS
    THAT
    1.27
    That
    1.21
     That
    1.20
     THAT
    1.14
    that
    1.01
     jenem
    0.93
     ese
    0.92
     esa
    0.85
    脚注の使い方
    0.84
    Ese
    0.84
    Act Density 0.221%

    No Known Activations