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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing quantities or numbers associated with groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.08
    owitz
    -0.07
    ioned
    -0.07
    selling
    -0.06
    isma
    -0.06
     seins
    -0.06
    ÑģÑĤÑĢо
    -0.06
    zÃŃ
    -0.06
    shan
    -0.06
    thes
    -0.06
    POSITIVE LOGITS
     thousands
    0.10
     hundreds
    0.08
    inue
    0.07
    ousands
    0.07
     millions
    0.07
     billions
    0.07
     dozens
    0.07
    Thousands
    0.07
    fold
    0.07
     Thousands
    0.07
    Act Density 0.003%

    No Known Activations