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

    Neuronpedia

    INDEX
    Explanations

    references to backdoor vulnerabilities and security-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥ
    -0.15
    atör
    -0.13
    .Export
    -0.13
    oop
    -0.13
     disg
    -0.13
    ToSend
    -0.13
    ritz
    -0.13
    Wunused
    -0.13
    Compiled
    -0.13
    Schedulers
    -0.12
    POSITIVE LOGITS
    ing
    0.22
    -ing
    0.20
    äºĨ
    0.20
    äºĨä¸Ģ
    0.20
    ized
    0.20
    ed
    0.19
    eing
    0.18
    iked
    0.18
    ked
    0.18
    pped
    0.18
    Act Density 0.131%

    No Known Activations