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

    Neuronpedia

    INDEX
    Explanations

    references to power generation measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to megawatt measurements related to energy generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.77
     Desire
    -0.74
     Paradox
    -0.66
     Sense
    -0.66
    ÙIJ
    -0.66
    Ô
    -0.63
     Costume
    -0.63
     synopsis
    -0.63
    cember
    -0.63
     Mesa
    -0.62
    POSITIVE LOGITS
    abytes
    1.20
    abyte
    1.07
    apixel
    0.98
    awatts
    0.90
    acity
    0.86
    imet
    0.85
    atis
    0.81
    aunts
    0.80
    apolis
    0.80
     meg
    0.80
    Act Density 0.009%

    No Known Activations