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

    Neuronpedia

    INDEX
    Explanations

    references to scientific equations and concepts related to physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éŨ
    -0.15
     volcano
    -0.15
    éĸĢ
    -0.14
    etting
    -0.14
     Dynamo
    -0.14
    astos
    -0.14
    717
    -0.14
    Skeleton
    -0.14
    243
    -0.13
    UInteger
    -0.13
    POSITIVE LOGITS
     Lore
    0.29
     observer
    0.27
     observers
    0.26
    observer
    0.22
     Observer
    0.21
     contracting
    0.21
     lore
    0.21
    -frame
    0.20
     boost
    0.20
     frames
    0.20
    Act Density 0.045%

    No Known Activations