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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of mechanical components and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ات
    -0.16
     thermometer
    -0.16
    yz
    -0.14
     stacking
    -0.14
     owning
    -0.14
    -temp
    -0.14
    inst
    -0.14
     spacer
    -0.13
    playing
    -0.13
     Wheeler
    -0.13
    POSITIVE LOGITS
     power
    0.29
    power
    0.26
    Powered
    0.25
    -power
    0.24
    powered
    0.24
     prop
    0.23
     powered
    0.21
     powering
    0.21
     Power
    0.21
     drive
    0.21
    Act Density 0.187%

    No Known Activations