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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pone
    -0.16
    Ñĭп
    -0.15
     Lorem
    -0.15
    adr
    -0.14
    ukan
    -0.14
    uke
    -0.14
    undan
    -0.14
    riz
    -0.14
    anche
    -0.14
     zar
    -0.14
    POSITIVE LOGITS
    tica
    0.18
    nech
    0.15
    ysi
    0.15
    achs
    0.14
    lotte
    0.14
    psilon
    0.13
     Barber
    0.13
    thers
    0.13
    ayah
    0.13
    quis
    0.13
    Act Density 0.313%

    No Known Activations