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

    Neuronpedia

    INDEX
    Explanations

    references to quantity, specifically the term "few" and similar expressions that indicate a small number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -piece
    -0.15
    arth
    -0.14
     piece
    -0.14
     Kendall
    -0.14
    urry
    -0.14
    Ñģли
    -0.14
    piece
    -0.14
    Ñĸж
    -0.14
     peu
    -0.14
    rian
    -0.14
    POSITIVE LOGITS
     months
    0.21
     years
    0.18
     weeks
    0.17
    inos
    0.16
    months
    0.15
     hundred
    0.15
     month
    0.15
    ouce
    0.14
    267
    0.14
     اÙĦتÙĪ
    0.14
    Act Density 0.036%

    No Known Activations