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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹ĥà¸Ķ
    -0.17
    ften
    -0.17
    adera
    -0.15
     Either
    -0.14
    tring
    -0.14
    Either
    -0.14
    rum
    -0.14
     pháºŃn
    -0.14
    armor
    -0.14
    ÑĥÑĢÑĥ
    -0.14
    POSITIVE LOGITS
     though
    0.29
    Though
    0.24
    though
    0.22
     Though
    0.21
    when
    0.18
     wenn
    0.17
     when
    0.17
     aunque
    0.16
    ough
    0.16
    flo
    0.16
    Act Density 0.037%

    No Known Activations