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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a quantity of items, particularly focusing on the word "of" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.20
    izik
    -0.16
    ä¸ĢäºĽ
    -0.16
    OfDay
    -0.16
     некоÑĤоÑĢÑĭÑħ
    -0.15
    apt
    -0.14
    ربع
    -0.14
    ory
    -0.14
    nih
    -0.14
    iten
    -0.14
    POSITIVE LOGITS
     dollars
    0.22
     acres
    0.20
     them
    0.19
     pages
    0.18
     copies
    0.17
     miles
    0.17
     us
    0.16
    copies
    0.16
     Dollars
    0.15
     pounds
    0.15
    Act Density 0.032%

    No Known Activations