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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy efficiency and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MockBean
    -0.85
     IBOutlet
    -0.78
    améli
    -0.76
    __*/
    -0.74
     faulting
    -0.73
    ttemberg
    -0.71
     bint
    -0.71
    ofollow
    -0.71
    arrête
    -0.71
     Gothenburg
    -0.69
    POSITIVE LOGITS
     energy
    1.60
     Energy
    1.49
     energies
    1.48
     ENERGY
    1.48
    ENERGY
    1.46
    energy
    1.37
    Energy
    1.29
     Ener
    1.21
     Energies
    1.21
    energies
    1.20
    Act Density 0.053%

    No Known Activations