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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "de" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    人
    -0.16
    ildren
    -0.15
    ieber
    -0.14
    kaar
    -0.14
    igers
    -0.14
    rrha
    -0.14
    iaux
    -0.14
    nyder
    -0.14
    elm
    -0.14
    plementation
    -0.14
    POSITIVE LOGITS
     way
    0.20
     manera
    0.17
    way
    0.17
     acuerdo
    0.17
     forma
    0.17
    str
    0.16
    WAY
    0.16
     note
    0.16
    961
    0.16
     manière
    0.15
    Act Density 0.024%

    No Known Activations