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

    Neuronpedia

    INDEX
    Explanations

    references to fictional or fantastical beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lius
    -0.16
    hardt
    -0.16
    cia
    -0.16
    uries
    -0.15
    ripe
    -0.15
    à¥įयव
    -0.15
    Detector
    -0.15
    apk
    -0.15
    lys
    -0.14
    sembling
    -0.14
    POSITIVE LOGITS
    092
    0.15
     Modeling
    0.15
     modeling
    0.15
    ów
    0.14
    yar
    0.14
    elist
    0.13
    rut
    0.13
     Rel
    0.13
     cycle
    0.13
     Ut
    0.13
    Act Density 0.033%

    No Known Activations