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

    Neuronpedia

    INDEX
    Explanations

    concepts related to theoretical physics and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithType
    -0.15
     hashtag
    -0.15
    spot
    -0.15
     Dynamo
    -0.15
     Gust
    -0.15
    æĹ
    -0.14
     biome
    -0.14
     Gallagher
    -0.14
    roller
    -0.14
    опаÑģ
    -0.14
    POSITIVE LOGITS
     Lore
    0.22
     Schwar
    0.17
     accel
    0.17
     observer
    0.17
     Mach
    0.17
     Dil
    0.17
     acceleration
    0.17
     dil
    0.16
     Twins
    0.16
    accel
    0.16
    Act Density 0.047%

    No Known Activations