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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shmi
    -0.55
     къ
    -0.54
    8
    -0.54
     bas
    -0.51
     che
    -0.50
    ↵
    -0.49
    gcc
    -0.49
    9
    -0.49
     Asymmetric
    -0.48
    7
    -0.47
    POSITIVE LOGITS
     entirety
    1.07
     entire
    0.98
    aarrggbb
    0.93
    entire
    0.84
    robial
    0.84
    __*/
    0.82
     Entire
    0.82
     المعيارى
    0.81
    Entire
    0.81
     totalidad
    0.78
    Act Density 0.055%

    No Known Activations