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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.91
     Савезне
    -0.83
    ьаж
    -0.82
     venons
    -0.81
    Jeografia
    -0.79
     Meksiku
    -0.77
    msgTypes
    -0.77
    adpleegd
    -0.75
    rawDesc
    -0.74
     سكانية
    -0.73
    POSITIVE LOGITS
     Piel
    0.52
    Batis
    0.49
    ئات
    0.47
     apl
    0.45
    setopt
    0.44
    バイ
    0.43
    OrBuilder
    0.42
     Hiram
    0.42
     Ciro
    0.42
     към
    0.41
    Act Density 0.012%

    No Known Activations