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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to product design and mechanical components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŀ¶
    -0.18
    avana
    -0.16
     poles
    -0.16
    ë°ĺ기
    -0.16
    anka
    -0.15
    isel
    -0.15
    é¡Į
    -0.15
     tilt
    -0.14
     privile
    -0.14
    .Pod
    -0.14
    POSITIVE LOGITS
     captive
    0.17
     cured
    0.16
     bosses
    0.16
     Witness
    0.16
    stdafx
    0.16
     mating
    0.15
     cham
    0.15
     mate
    0.15
     Datum
    0.15
    ulumi
    0.15
    Act Density 0.432%

    No Known Activations