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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical specifications and engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soap
    -0.15
    ckpt
    -0.15
     Bolt
    -0.15
    rides
    -0.14
     ÑĢам
    -0.14
    /ion
    -0.14
     tide
    -0.14
    à¸ĩà¸ķ
    -0.14
     incapac
    -0.14
     Bearings
    -0.14
    POSITIVE LOGITS
     cable
    0.41
     cables
    0.35
     Cable
    0.34
     conductor
    0.28
     stranded
    0.26
     conduct
    0.26
     bra
    0.23
     Jacket
    0.22
    termination
    0.21
     copper
    0.21
    Act Density 0.033%

    No Known Activations