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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to security vulnerabilities and access issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avi
    -0.16
    *)_
    -0.14
    uchs
    -0.14
    glich
    -0.14
    UTE
    -0.14
    andler
    -0.14
    onu
    -0.13
    onium
    -0.13
    ikip
    -0.13
     everything
    -0.13
    POSITIVE LOGITS
    heck
    0.17
    éľ
    0.15
    anas
    0.14
     throughout
    0.14
     earlier
    0.14
    eries
    0.14
    inia
    0.14
    pty
    0.13
    lest
    0.13
    pek
    0.13
    Act Density 0.012%

    No Known Activations