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

    Neuronpedia

    INDEX
    Explanations

    references to software updates and fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rieve
    -0.15
    anten
    -0.15
    iders
    -0.14
    ÙĪاÙĨ
    -0.14
    etri
    -0.13
     stakes
    -0.13
     challenges
    -0.13
    è¢ĭ
    -0.13
     then
    -0.13
    undler
    -0.13
    POSITIVE LOGITS
     bug
    0.18
     Proper
    0.17
     breaking
    0.17
    proper
    0.17
     minor
    0.17
     Breaking
    0.16
    Breaking
    0.16
    breaking
    0.15
     properly
    0.15
    bug
    0.15
    Act Density 0.049%

    No Known Activations