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

    Neuronpedia

    INDEX
    Explanations

    references to energy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of energy-related concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -1.07
    glers
    -0.86
    ãĥĥãĥĪ
    -0.77
    iple
    -0.75
    umbnail
    -0.72
    gery
    -0.71
    ãĥīãĥ©
    -0.70
    azeera
    -0.69
    iak
    -0.69
    enance
    -0.68
    POSITIVE LOGITS
     superpower
    0.92
     efficiency
    0.88
     consumption
    0.86
     powering
    0.80
     absorption
    0.80
     metabolism
    0.78
     installations
    0.78
     advisor
    0.76
    minist
    0.76
     propulsion
    0.76
    Act Density 0.023%

    No Known Activations