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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and stability-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eren
    -0.17
    elson
    -0.17
    anut
    -0.17
    DonaldTrump
    -0.16
    enary
    -0.15
    еÑģа
    -0.15
    Gratis
    -0.15
    RootElement
    -0.15
    \\/
    -0.15
    ÅĻeb
    -0.15
    POSITIVE LOGITS
     stability
    0.16
    urdy
    0.16
    kker
    0.16
    Ñīи
    0.16
    weg
    0.15
     Stability
    0.15
     stable
    0.14
    DT
    0.14
     vững
    0.14
    -as
    0.14
    Act Density 0.028%

    No Known Activations