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

    Neuronpedia

    INDEX
    Explanations

    keywords and references to citations in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äs
    -0.15
    ayed
    -0.15
    liga
    -0.14
    udio
    -0.14
    ownik
    -0.14
    tre
    -0.14
    arias
    -0.14
    emmel
    -0.14
    INES
    -0.14
    rvé
    -0.13
    POSITIVE LOGITS
    ÑĢеÑħ
    0.16
     Starr
    0.16
    elli
    0.15
    richt
    0.14
    cky
    0.14
    æĢ§
    0.14
    èħ
    0.14
    icari
    0.14
    estro
    0.13
    tero
    0.13
    Act Density 0.001%

    No Known Activations