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

    Neuronpedia

    INDEX
    Explanations

    references to work-related concepts and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lust
    -0.17
    949
    -0.15
     Bain
    -0.15
    arend
    -0.15
    721
    -0.14
    BJ
    -0.14
    978
    -0.14
    pect
    -0.14
    Lux
    -0.14
    ë£Į
    -0.14
    POSITIVE LOGITS
    æĸ
    0.19
    ánu
    0.15
    ascus
    0.14
    itty
    0.14
    ngo
    0.14
    ạnh
    0.14
    /animate
    0.14
    REA
    0.14
    ละ
    0.14
    _dbg
    0.14
    Act Density 0.000%

    No Known Activations