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

    Neuronpedia

    INDEX
    Explanations

    terms related to crime and illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ово
    -0.16
     赤
    -0.16
    orz
    -0.15
    .onViewCreated
    -0.15
    .useState
    -0.15
    kuk
    -0.14
    è¯Ŀ
    -0.14
    mán
    -0.13
    âĸ¡âĸ¡
    -0.13
    ienes
    -0.13
    POSITIVE LOGITS
     alike
    0.23
    SSERT
    0.16
     etc
    0.15
    .Îł
    0.14
    ationToken
    0.14
    ãĥ£
    0.14
    obuf
    0.14
     respectively
    0.14
     Abb
    0.14
     bent
    0.14
    Act Density 1.915%

    No Known Activations