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

    Neuronpedia

    INDEX
    Explanations

    words related to themes of community integration and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æ¿
    -0.16
    iever
    -0.15
    gle
    -0.15
    aida
    -0.15
    åĢĴ
    -0.15
    DV
    -0.15
    udeau
    -0.14
    aly
    -0.13
     Fulton
    -0.13
    uida
    -0.13
    POSITIVE LOGITS
    ØŃداث
    0.17
    ektor
    0.15
    aneous
    0.15
    taire
    0.15
    UCKET
    0.15
    vertime
    0.15
    eka
    0.15
    ean
    0.15
     Lana
    0.14
    ynet
    0.14
    Act Density 0.016%

    No Known Activations