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

    Neuronpedia

    INDEX
    Explanations

    concepts related to similarity or matching across various contexts

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

    Preceding the word "same"

    np_acts-logits-general · gemini-2.0-flash

    same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.78
     дописавши
    -0.70
    "]);
    -0.67
    -0.66
    setupUi
    -0.66
    })();
    -0.64
    =?";
    -0.61
     án
    -0.60
    Especially
    -0.60
    yntaxException
    -0.59
    POSITIVE LOGITS
    same
    0.95
     same
    0.93
    Same
    0.91
     Same
    0.86
     dezelfde
    0.76
     hetzelfde
    0.72
     mêmes
    0.70
     samma
    0.69
    zelfde
    0.67
     SAME
    0.66
    Act Density 0.234%

    No Known Activations