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

    Neuronpedia

    INDEX
    Explanations

    words related to data storage and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to "gigabytes" or "gigawatts."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.97
    tenance
    -0.80
    velt
    -0.76
     CONTROL
    -0.73
    Ô
    -0.68
    66666666
    -0.68
    ÙIJ
    -0.65
     Quincy
    -0.62
     Dise
    -0.62
    090
    -0.61
    POSITIVE LOGITS
    abyte
    1.49
    abytes
    1.46
    apixel
    1.17
    abit
    1.03
     gig
    0.88
    awatts
    0.88
    natureconservancy
    0.86
    rett
    0.84
    antically
    0.82
    lio
    0.80
    Act Density 0.009%

    No Known Activations