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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and authors in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vette
    -0.15
     Rouge
    -0.15
    ainless
    -0.14
    pora
    -0.14
    quito
    -0.14
    Åį
    -0.14
    ernaut
    -0.14
    Äģn
    -0.13
    ereal
    -0.13
    aksi
    -0.13
    POSITIVE LOGITS
     et
    0.25
    .scalablytyped
    0.17
    ̧
    0.15
     newcom
    0.14
    ãĤ¿ãĥ«
    0.14
    daki
    0.14
    eil
    0.13
    stad
    0.13
    201
    0.13
    ¨
    0.13
    Act Density 0.175%

    No Known Activations