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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' careers and their professional achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewitness
    -0.16
    udson
    -0.16
    ereo
    -0.15
    pii
    -0.14
    ennes
    -0.14
    830
    -0.13
    ernaut
    -0.13
    ä½į
    -0.13
    enden
    -0.13
    bers
    -0.13
    POSITIVE LOGITS
     debut
    0.78
     deb
    0.57
     debuted
    0.55
     début
    0.48
    deb
    0.38
     Deb
    0.36
    .deb
    0.35
     maiden
    0.32
     inaugural
    0.30
     introduction
    0.27
    Act Density 0.089%

    No Known Activations