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

    Neuronpedia

    INDEX
    Explanations

    queries about understanding and knowledge related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ple
    -0.16
    ller
    -0.16
    uzzi
    -0.15
    qli
    -0.15
    oreach
    -0.14
    款
    -0.14
    hread
    -0.14
    igi
    -0.13
    phans
    -0.13
    ÙĬÙĨØ©
    -0.13
    POSITIVE LOGITS
    agraph
    0.15
    ewan
    0.15
     Wrong
    0.14
    มาà¸ģ
    0.14
    cheme
    0.14
     quan
    0.14
     Harm
    0.14
    itches
    0.14
    hire
    0.14
    icago
    0.14
    Act Density 0.101%

    No Known Activations