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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronoun "she"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.16
    ssf
    -0.15
    ome
    -0.15
    Mate
    -0.15
    ænd
    -0.15
    ayne
    -0.14
    ensis
    -0.14
    æľºåħ³
    -0.14
    ossier
    -0.14
    tti
    -0.14
    POSITIVE LOGITS
    -même
    0.17
    din
    0.16
    ding
    0.15
    æĶ
    0.14
    olean
    0.14
    bett
    0.14
    کارÛĮ
    0.14
    cro
    0.14
     Gro
    0.14
    AMI
    0.14
    Act Density 0.178%

    No Known Activations