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

    Neuronpedia

    INDEX
    Explanations

    references to energy and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Revis
    -0.71
    MockBean
    -0.69
    cko
    -0.67
     mattino
    -0.65
     déchir
    -0.65
    améli
    -0.65
    ToTop
    -0.65
     Revis
    -0.64
    tifies
    -0.64
    rond
    -0.64
    POSITIVE LOGITS
     energy
    2.17
     Energy
    1.94
     ENERGY
    1.92
    energy
    1.88
     energies
    1.86
    ENERGY
    1.82
    Energy
    1.77
     Ener
    1.53
    Ener
    1.51
     Energies
    1.50
    Act Density 0.046%

    No Known Activations