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

    Neuronpedia

    INDEX
    Explanations

    words related to structural or functional components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Advertisements
    -0.16
    gend
    -0.15
    AttributeValue
    -0.14
    -urlencoded
    -0.14
    .undefined
    -0.13
    èĪĮ
    -0.13
    inden
    -0.13
     administr
    -0.13
    ALSE
    -0.12
    thon
    -0.12
    POSITIVE LOGITS
    ãĥŃãĥ³
    0.15
    iah
    0.15
    anon
    0.15
    ayet
    0.15
    óg
    0.14
     among
    0.14
    opoulos
    0.14
    urch
    0.14
    ĵåIJį
    0.14
    anie
    0.14
    Act Density 0.009%

    No Known Activations