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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "be" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    557
    -0.17
     optarg
    -0.15
    unsch
    -0.15
    533
    -0.14
    ijn
    -0.14
    ibt
    -0.14
    rij
    -0.14
    ä¸ĸç´Ģ
    -0.14
    سÛĮÙĨ
    -0.13
    road
    -0.13
    POSITIVE LOGITS
     used
    0.21
     applied
    0.18
    used
    0.16
    amat
    0.16
    Applied
    0.16
    amm
    0.16
     kullanarak
    0.16
     use
    0.15
     íĨµíķ´
    0.15
    _used
    0.15
    Act Density 0.221%

    No Known Activations