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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.16
    841
    -0.15
    elijk
    -0.15
    (es
    -0.15
    roperties
    -0.15
    asse
    -0.14
    bourg
    -0.14
    ạch
    -0.14
    .Emit
    -0.13
    isher
    -0.13
    POSITIVE LOGITS
    íģ¼
    0.17
     лиÑĪÑĮ
    0.16
    Fans
    0.15
    дÑĸл
    0.14
    s
    0.14
    icia
    0.14
    naments
    0.14
    vet
    0.14
    ('__
    0.14
    idian
    0.13
    Act Density 0.099%

    No Known Activations