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

    Neuronpedia

    INDEX
    Explanations

    negations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hin
    -0.14
     not
    -0.14
    hone
    -0.14
    es
    -0.14
    inski
    -0.14
     no
    -0.14
    csr
    -0.13
    din
    -0.13
    æŦ
    -0.13
     nicht
    -0.13
    POSITIVE LOGITS
     necessarily
    0.21
    ori
    0.18
     yet
    0.17
     anymore
    0.17
    zsche
    0.17
    apos
    0.17
    ches
    0.17
    ibble
    0.16
    ango
    0.15
     quite
    0.15
    Act Density 0.178%

    No Known Activations