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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numeric references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DTV
    -0.15
    à¹ģà¸ľ
    -0.14
    afone
    -0.14
    tica
    -0.14
    bout
    -0.13
     Princip
    -0.13
    yna
    -0.13
    Īĺ
    -0.13
    irtual
    -0.13
    IRTUAL
    -0.13
    POSITIVE LOGITS
    908
    0.16
    he
    0.16
    rek
    0.15
    oot
    0.15
    ste
    0.14
    oki
    0.14
    acements
    0.14
    apro
    0.13
    iele
    0.13
    dek
    0.13
    Act Density 0.099%

    No Known Activations