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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the ability or capacity to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    airo
    -0.16
    lag
    -0.15
    oders
    -0.15
     secure
    -0.14
    erner
    -0.14
    rob
    -0.14
     Patch
    -0.14
    ero
    -0.14
    at
    -0.14
     Y
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥ«
    0.15
     sona
    0.15
    peÄį
    0.15
    ãĥ¼ãĥª
    0.15
     ============================================================================↵
    0.14
    adian
    0.14
    ÑģÑĮого
    0.14
    δÏħ
    0.14
    DataMember
    0.14
    ’t
    0.14
    Act Density 0.047%

    No Known Activations