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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to energy consumption and physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UZ
    -0.15
     unprotected
    -0.15
    .Override
    -0.15
    blick
    -0.14
     exposures
    -0.14
    ÙĤØ·
    -0.13
    urat
    -0.13
    onia
    -0.13
    killer
    -0.13
    MUX
    -0.13
    POSITIVE LOGITS
     heat
    0.23
     Carn
    0.22
     energy
    0.21
    .scalablytyped
    0.20
     transfer
    0.20
     transferred
    0.20
     Transfer
    0.20
    heat
    0.20
     transfers
    0.20
     conversion
    0.19
    Act Density 0.050%

    No Known Activations