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

    Neuronpedia

    INDEX
    Explanations

    references to database-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĭį
    -0.17
    NETWORK
    -0.15
     Wheel
    -0.15
    Wheel
    -0.14
     dodge
    -0.14
     unsafe
    -0.14
    erc
    -0.14
     NETWORK
    -0.14
     Florence
    -0.14
     Gut
    -0.14
    POSITIVE LOGITS
     carbon
    0.33
    carbon
    0.30
    Carbon
    0.29
     Carbon
    0.28
    arbon
    0.23
     Axis
    0.19
     tenant
    0.19
     tenants
    0.19
    xac
    0.18
     axis
    0.18
    Act Density 0.003%

    No Known Activations