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

    Neuronpedia

    INDEX
    Explanations

    words related to a wide range or variety

    oai_token-act-pair · gpt-3.5-turbo

    references to various kinds of "spectrum."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiro
    -0.69
    lisher
    -0.67
    BY
    -0.66
    ishable
    -0.65
    ished
    -0.65
    lished
    -0.62
    lishes
    -0.61
    than
    -0.61
    bear
    -0.61
    ivia
    -0.60
    POSITIVE LOGITS
     spectrum
    1.07
    geist
    0.82
     Spectrum
    0.77
    ittal
    0.76
    ically
    0.72
    anches
    0.71
    naire
    0.68
     ranging
    0.68
    aire
    0.68
    aze
    0.67
    Act Density 0.015%

    No Known Activations