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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "dozen" and its variations

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

    dozens and hundreds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☸
    -0.68
    بوابة
    -0.55
    Autoritní
    -0.54
     endblock
    -0.54
     MonoBehaviour
    -0.50
    RTLD
    -0.49
    Portale
    -0.49
    afone
    -0.49
     "..\..\
    -0.48
    VIAF
    -0.47
    POSITIVE LOGITS
     dozens
    1.76
     hundreds
    1.43
    hundreds
    1.42
     Hundreds
    1.26
    Hundreds
    1.16
    thousands
    1.13
     thousands
    1.12
     dizaines
    1.12
     decenas
    1.09
    zens
    1.06
    Act Density 0.007%

    No Known Activations