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

    Neuronpedia

    INDEX
    Explanations

    terms and actions related to cleaning and organizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbo
    -0.16
    Tu
    -0.14
    leaflet
    -0.14
     Ark
    -0.14
    aks
    -0.14
    amd
    -0.14
    rella
    -0.13
    ÑĪов
    -0.13
    iale
    -0.13
    OrElse
    -0.13
    POSITIVE LOGITS
     away
    0.28
     slate
    0.24
     debris
    0.23
     Away
    0.23
     decks
    0.20
    æİī
    0.19
     mess
    0.19
    /reset
    0.19
     thoroughly
    0.19
     caches
    0.18
    Act Density 0.094%

    No Known Activations