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

    Neuronpedia

    INDEX
    Explanations

    contractions that indicate negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aday
    -0.15
    outu
    -0.15
    ÏīÏĤ
    -0.15
     Evel
    -0.14
    -valu
    -0.14
    ableViewController
    -0.14
    rouw
    -0.14
    .Îij
    -0.14
    cip
    -0.14
    ady
    -0.14
    POSITIVE LOGITS
     necessarily
    0.23
     matter
    0.22
    matter
    0.19
     quite
    0.18
     exactly
    0.18
     stop
    0.17
     b
    0.17
     change
    0.17
     aug
    0.17
     mattered
    0.17
    Act Density 0.108%

    No Known Activations