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

    Neuronpedia

    INDEX
    Explanations

    references to deception or falsified information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naments
    -0.17
    ÑģÑİ
    -0.14
    .gs
    -0.14
    èo
    -0.14
    окÑģи
    -0.13
    jug
    -0.13
    rex
    -0.13
    й
    -0.13
    ally
    -0.13
    ioni
    -0.13
    POSITIVE LOGITS
    kus
    0.18
    484
    0.16
    erap
    0.15
    uchar
    0.15
    folio
    0.15
    olor
    0.15
    ulence
    0.14
     Synthetic
    0.14
    /false
    0.14
    elry
    0.14
    Act Density 0.011%

    No Known Activations