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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "every" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.42
     насељу
    -0.40
    şört
    -0.39
    NameInMap
    -0.37
    recrow
    -0.37
     asla
    -0.37
    eningrad
    -0.37
     Numerade
    -0.36
     justru
    -0.36
     altogether
    -0.35
    POSITIVE LOGITS
     single
    0.88
    every
    0.88
    Every
    0.80
     Every
    0.77
     eneste
    0.77
     conceivable
    0.74
     every
    0.69
     einzelne
    0.68
     egyes
    0.67
     imaginable
    0.67
    Act Density 0.065%

    No Known Activations