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

    Neuronpedia

    INDEX
    Explanations

    the word "That" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.83
    참고
    -0.63
    Portale
    -0.61
     دریافت‌شده
    -0.56
    ly
    -0.55
    getColumnIndex
    -0.52
    UnitTesting
    -0.52
    mente
    -0.52
    いる
    -0.50
    saraba
    -0.50
    POSITIVE LOGITS
    zelfde
    0.80
     pesky
    0.80
    cher
    0.79
     same
    0.77
     fateful
    0.72
    cham
    0.69
    ch
    0.69
    chers
    0.66
     said
    0.64
    ValueStyle
    0.63
    Act Density 0.154%

    No Known Activations