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

    Neuronpedia

    INDEX
    Explanations

    references to security vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sil
    -0.15
    iren
    -0.15
    inker
    -0.15
     Anders
    -0.15
    rac
    -0.15
     Scar
    -0.14
     stav
    -0.14
     Hayes
    -0.14
    anti
    -0.14
    ãĤĥ
    -0.14
    POSITIVE LOGITS
    vero
    0.15
    IDS
    0.14
    KA
    0.14
    ÙĪغ
    0.13
    梨
    0.13
    ób
    0.13
    dek
    0.13
     دÙĨÛĮ
    0.13
     Wilde
    0.13
    obia
    0.13
    Act Density 0.032%

    No Known Activations