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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy consumption and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MockBean
    -0.80
    __*/
    -0.73
     bint
    -0.72
     IBOutlet
    -0.70
    Revis
    -0.69
     mattino
    -0.69
     déchir
    -0.67
    ofollow
    -0.67
    améli
    -0.67
    lauben
    -0.67
    POSITIVE LOGITS
     energy
    1.77
     energies
    1.66
     Energy
    1.64
     ENERGY
    1.61
    ENERGY
    1.57
    energy
    1.54
    Energy
    1.46
     Ener
    1.30
    energies
    1.30
     Energies
    1.30
    Act Density 0.058%

    No Known Activations