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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating the absence or limitation of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ľi
    -0.15
    inci
    -0.14
    apol
    -0.14
    vÄĽt
    -0.14
    achuset
    -0.14
    ereco
    -0.14
    fusc
    -0.14
    .foreach
    -0.14
     eldre
    -0.13
    elay
    -0.13
    POSITIVE LOGITS
     necessarily
    0.38
     sure
    0.27
    withstanding
    0.25
    sure
    0.23
     least
    0.23
    least
    0.21
     Sure
    0.20
     because
    0.20
     counting
    0.20
     anymore
    0.20
    Act Density 0.064%

    No Known Activations