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

    Neuronpedia

    INDEX
    Explanations

    terms that convey redundancy or excessive repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wijk
    -0.53
    asti
    -0.53
    はじめに
    -0.51
     orice
    -0.49
    स्प
    -0.48
     singola
    -0.47
     single
    -0.46
    atst
    -0.44
     anything
    -0.44
    stin
    -0.43
    POSITIVE LOGITS
    Datuak
    0.88
     тоже
    0.88
    MemoryWarning
    0.83
    これも
    0.83
     nữa
    0.82
     וגם
    0.80
     ebenfalls
    0.79
    同样
    0.79
     turut
    0.75
     equally
    0.75
    Act Density 0.303%

    No Known Activations