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

    Neuronpedia

    INDEX
    Explanations

    code-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addtogroup
    -0.16
    èµı
    -0.16
    渡
    -0.15
    illac
    -0.15
    è³ŀ
    -0.15
    ledo
    -0.14
    ekl
    -0.14
     Hacker
    -0.14
    ÃŁe
    -0.14
    _KEEP
    -0.14
    POSITIVE LOGITS
     determination
    0.14
     bridal
    0.14
     tray
    0.14
    uki
    0.13
    akra
    0.13
    abox
    0.13
     environment
    0.13
     íĻĺê²½
    0.13
     preference
    0.13
    vasive
    0.13
    Act Density 0.173%

    No Known Activations