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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases associated with processes and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meiden
    -0.15
    anje
    -0.15
    762
    -0.15
    anean
    -0.15
     tracer
    -0.15
     Shib
    -0.15
     Proxy
    -0.14
     Sev
    -0.14
    _VERBOSE
    -0.13
     Covent
    -0.13
    POSITIVE LOGITS
    ocket
    0.15
    oux
    0.15
    ops
    0.15
    riel
    0.14
    NCY
    0.14
     Sadd
    0.14
    templ
    0.14
    .inflate
    0.14
    à¸İ
    0.14
    bserv
    0.13
    Act Density 0.001%

    No Known Activations