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

    Neuronpedia

    INDEX
    Explanations

    repetitions of the word "same."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    same context or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.57
     '\\;'
    -0.56
    RectangleBorder
    -0.52
    Бахар
    -0.47
    GenerationType
    -0.46
    RegressionTest
    -0.46
    rrggbb
    -0.46
    PerformLayout
    -0.46
     mourut
    -0.45
    stylers
    -0.44
    POSITIVE LOGITS
     same
    0.87
    Same
    0.69
     desselben
    0.67
    同一
    0.67
     Same
    0.67
     mesmas
    0.66
    same
    0.66
     samme
    0.63
     dezelfde
    0.62
     denselben
    0.61
    Act Density 0.033%

    No Known Activations