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

    Neuronpedia

    INDEX
    Explanations

    negations or phrases indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essen
    -0.15
    PURE
    -0.15
    atural
    -0.15
    leton
    -0.15
    861
    -0.14
    ResponseBody
    -0.14
    267
    -0.14
    Leap
    -0.14
    ERY
    -0.13
    ancia
    -0.13
    POSITIVE LOGITS
     necessarily
    0.21
    withstanding
    0.17
     ones
    0.16
     merely
    0.16
    ecut
    0.15
    just
    0.15
    ivor
    0.15
    ori
    0.15
     اÛĮÙĨÚ©Ùĩ
    0.14
    achi
    0.14
    Act Density 0.029%

    No Known Activations