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

    Neuronpedia

    INDEX
    Explanations

    instances of quantity and measurement in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.62
     aught
    -0.59
    principalTable
    -0.59
    sizeCache
    -0.58
    Might
    -0.57
    Any
    -0.55
    ticularly
    -0.55
    Anything
    -0.52
    TestBed
    -0.50
    moveToFirst
    -0.49
    POSITIVE LOGITS
     plenty
    1.47
     lots
    1.45
     tons
    1.19
    Lots
    1.10
     LOTS
    1.10
    plenty
    1.08
    lots
    1.08
     Lots
    1.06
     great
    1.03
     ample
    1.01
    Act Density 0.296%

    No Known Activations