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

    Neuronpedia

    INDEX
    Explanations

    references to energy-related concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Revis
    -0.71
    arrête
    -0.69
    MockBean
    -0.68
    cko
    -0.67
     mattino
    -0.67
     déchir
    -0.65
    améli
    -0.65
     Xunit
    -0.65
     Revis
    -0.65
     Joaquim
    -0.63
    POSITIVE LOGITS
     energy
    2.33
     Energy
    2.09
    energy
    2.04
     ENERGY
    2.04
     energies
    1.95
    ENERGY
    1.93
    Energy
    1.92
     Energies
    1.59
     ener
    1.58
     Ener
    1.58
    Act Density 0.035%

    No Known Activations