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

    Neuronpedia

    INDEX
    Explanations

    various statistical analysis and results formatting elements in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     I
    -0.66
     T
    -0.65
     [
    -0.64
     E
    -0.63
     L
    -0.62
     A
    -0.61
     it
    -0.61
     F
    -0.58
     #
    -0.58
     D
    -0.57
    POSITIVE LOGITS
    -----------
    2.50
    -------------
    2.48
    ------------
    2.45
    --------------
    2.43
    ----------
    2.33
    ---------------
    2.32
    --------
    2.31
    ---------
    2.20
     ------------
    1.97
     ---------------
    1.97
    Act Density 0.302%

    No Known Activations