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

    Neuronpedia

    INDEX
    Explanations

    references to medical or health-related topics, particularly around misinformation and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĪĴ
    -0.31
    -↵↵
    -0.20
    ãĢľ
    -0.19
    —↵↵
    -0.19
     âĪĴ
    -0.18
    Ù¬
    -0.18
    ï¼į
    -0.18
     ðŁĻĤ↵↵
    -0.17
     ”↵↵
    -0.17
    ————
    -0.17
    POSITIVE LOGITS
     --
    0.95
     --↵
    0.67
     --↵↵
    0.55
    --
    0.52
     "--
    0.50
     '--
    0.50
     [--
    0.50
    .--
    0.47
    /--
    0.46
     (--
    0.46
    Act Density 0.086%

    No Known Activations