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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to energy and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MockBean
    -0.86
     IBOutlet
    -0.77
    __*/
    -0.76
    améli
    -0.75
    ttemberg
    -0.74
     faulting
    -0.74
    ofollow
    -0.73
     bint
    -0.73
     nahilalakip
    -0.73
    Revis
    -0.73
    POSITIVE LOGITS
     energy
    1.54
     Energy
    1.47
     energies
    1.47
     ENERGY
    1.45
    ENERGY
    1.44
    energy
    1.31
    Energy
    1.25
     Ener
    1.20
    energies
    1.18
     Energies
    1.15
    Act Density 0.037%

    No Known Activations