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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions and instances of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regor
    -0.16
    á»Ļ
    -0.15
    .DataType
    -0.15
    lernen
    -0.14
    rement
    -0.14
    kö
    -0.14
    ÙħاÙħ
    -0.13
    ilogy
    -0.13
    ovable
    -0.13
    regon
    -0.13
    POSITIVE LOGITS
    Sm
    0.15
     Slee
    0.15
     ÎĶεν
    0.15
    ango
    0.14
     bid
    0.14
     Kaf
    0.14
    bare
    0.14
     bou
    0.13
    /wp
    0.13
    oui
    0.13
    Act Density 0.287%

    No Known Activations