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

    Neuronpedia

    INDEX
    Explanations

    different forms and contexts of the word "letter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.99
     propOrder
    -0.88
    Lähteet
    -0.87
     Roskov
    -0.81
    hehehe
    -0.78
    uesday
    -0.75
    Alike
    -0.75
    mylist
    -0.73
    Verweise
    -0.72
    tablissement
    -0.71
    POSITIVE LOGITS
     letters
    1.74
     Letters
    1.61
    Letters
    1.49
     LETTER
    1.48
     letter
    1.47
     Letter
    1.45
    letter
    1.41
    letters
    1.38
     LETTERS
    1.37
    Letter
    1.35
    Act Density 0.078%

    No Known Activations