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

    Neuronpedia

    INDEX
    Explanations

    concepts related to product design and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inheritance
    -0.17
     dust
    -0.17
     Dust
    -0.15
     refriger
    -0.15
     respir
    -0.14
     Dustin
    -0.14
     grass
    -0.14
     asset
    -0.14
     Refriger
    -0.14
     metro
    -0.14
    POSITIVE LOGITS
     heaters
    0.28
     heater
    0.26
     tank
    0.26
    tank
    0.24
     Tank
    0.23
    -tank
    0.23
    Tank
    0.22
    -he
    0.22
     radiant
    0.21
    heat
    0.21
    Act Density 0.032%

    No Known Activations