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

    Neuronpedia

    INDEX
    Explanations

    concepts related to energy and its physical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulan
    -0.17
    .Override
    -0.15
    ÙĤØ·
    -0.15
     unprotected
    -0.15
    keit
    -0.15
     instantaneous
    -0.15
     habitual
    -0.14
    onia
    -0.14
    edar
    -0.13
     lengths
    -0.13
    POSITIVE LOGITS
     energy
    0.48
    energy
    0.43
     Energy
    0.40
    -energy
    0.39
    Energy
    0.37
     ENERGY
    0.36
    .energy
    0.35
     energies
    0.34
    _energy
    0.33
    nergy
    0.33
    Act Density 0.129%

    No Known Activations