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

    Neuronpedia

    INDEX
    Explanations

    important nouns or phrases indicating significance in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uger
    -0.17
    orton
    -0.16
    anner
    -0.15
    pts
    -0.15
    idden
    -0.14
    facts
    -0.14
    PMC
    -0.13
    ByteBuffer
    -0.13
    çĥ
    -0.13
    unn
    -0.13
    POSITIVE LOGITS
     problem
    0.18
     key
    0.17
     thing
    0.17
     reason
    0.17
    orem
    0.17
    oret
    0.17
    -gnu
    0.17
    à§į
    0.16
     purpose
    0.15
    etz
    0.15
    Act Density 0.168%

    No Known Activations