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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to letters or written correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.06
    makeConstraints
    -0.96
    Lähteet
    -0.92
     Roskov
    -0.87
    hehehe
    -0.80
    uesday
    -0.80
    mylist
    -0.79
    paravant
    -0.78
    TestingModule
    -0.78
    Alike
    -0.78
    POSITIVE LOGITS
     letters
    1.85
     Letters
    1.71
     letter
    1.64
     LETTER
    1.61
     Letter
    1.59
    Letters
    1.57
    letter
    1.54
     LETTERS
    1.50
    letters
    1.50
    Letter
    1.49
    Act Density 0.075%

    No Known Activations