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

    Neuronpedia

    INDEX
    Explanations

    questions and the use of transitional or linking words within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Invent
    -0.17
     Ton
    -0.17
    Ton
    -0.16
    yntax
    -0.14
    alo
    -0.14
    udit
    -0.14
    γά
    -0.14
     Alexandre
    -0.14
    hn
    -0.14
    aze
    -0.14
    POSITIVE LOGITS
    .Networking
    0.17
    ioso
    0.16
    isku
    0.16
    ounge
    0.15
     DISCLAIM
    0.15
    дап
    0.15
    endid
    0.14
    jad
    0.14
    astreet
    0.14
    otion
    0.14
    Act Density 0.004%

    No Known Activations