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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     writ
    -0.17
    ÏĦά
    -0.14
    ourn
    -0.14
    ekil
    -0.13
    agar
    -0.13
    zej
    -0.13
    angered
    -0.13
    oger
    -0.13
    estar
    -0.13
    moil
    -0.13
    POSITIVE LOGITS
    μεν
    0.17
     Hatch
    0.17
    _bundle
    0.15
    Unc
    0.15
    imator
    0.14
     vulner
    0.14
    âĺħâĺħ
    0.14
     Unc
    0.14
     Neville
    0.14
     Hak
    0.14
    Act Density 0.014%

    No Known Activations