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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'a' in various contexts, with a focus on words and phrases that stand out due to their importance or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesz
    -0.16
     Cres
    -0.15
    elerinden
    -0.15
     kabil
    -0.15
    ycastle
    -0.14
    èĨľ
    -0.14
    ooke
    -0.14
    fortune
    -0.14
    olvers
    -0.14
    adro
    -0.14
    POSITIVE LOGITS
    _ACT
    0.19
    isi
    0.15
     Strap
    0.15
    abay
    0.14
    ãĥ¬ãĥ¼
    0.14
     unary
    0.14
    ACT
    0.14
    sequential
    0.14
    nown
    0.14
    à¥ģब
    0.14
    Act Density 0.021%

    No Known Activations