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

    Neuronpedia

    INDEX
    Explanations

    words related to energy and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    mentions of energy and its various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.98
     Sections
    -0.70
     Grave
    -0.69
     Flesh
    -0.67
    izon
    -0.66
    nee
    -0.66
    ettings
    -0.66
    glers
    -0.65
     Mock
    -0.65
    sonian
    -0.65
    POSITIVE LOGITS
     energy
    0.92
    energy
    0.88
     efficiency
    0.86
    jriwal
    0.86
     superpower
    0.82
     powering
    0.80
     fueling
    0.77
     absorption
    0.76
     outage
    0.75
     equival
    0.75
    Act Density 0.027%

    No Known Activations