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

    Neuronpedia

    INDEX
    Explanations

    references to synthetic data in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èį
    -0.18
    .metro
    -0.17
    Editors
    -0.14
     vibr
    -0.14
    reate
    -0.14
    OLUM
    -0.14
    appen
    -0.13
     Emp
    -0.13
    ãĤ«ãĥ«
    -0.13
    olum
    -0.13
    POSITIVE LOGITS
     ciphertext
    0.27
     secure
    0.27
     secret
    0.26
     security
    0.25
     Secure
    0.24
     cryptographic
    0.24
     leakage
    0.23
    secure
    0.23
     Yao
    0.23
     crypt
    0.22
    Act Density 0.008%

    No Known Activations