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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Durant
    -0.16
    ilden
    -0.15
     Thornton
    -0.15
    anning
    -0.14
    anford
    -0.14
    enburg
    -0.14
    úc
    -0.14
     Commerce
    -0.13
     Chapman
    -0.13
    ario
    -0.13
    POSITIVE LOGITS
    rame
    0.16
    izr
    0.15
    abal
    0.15
     доÑģÑĤ
    0.15
    алеж
    0.15
    acker
    0.14
    æĤ
    0.14
    747
    0.14
    ksam
    0.14
    linky
    0.14
    Act Density 0.003%

    No Known Activations