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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrass
    -0.16
    illet
    -0.16
    iscard
    -0.16
    ÏģÏī
    -0.15
    _MSK
    -0.15
     баг
    -0.15
    .SizeType
    -0.15
    StateChanged
    -0.14
    ãģ¹
    -0.14
    çļĦè¯Ŀ
    -0.14
    POSITIVE LOGITS
    ↵
    0.16
    starter
    0.15
    pf
    0.15
    2
    0.15
    /Foundation
    0.14
    ch
    0.14
     having
    0.14
     Voll
    0.14
    ep
    0.13
    523
    0.13
    Act Density 0.924%

    No Known Activations