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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly percentages or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychiat
    -0.70
     outl
    -0.66
    Medic
    -0.65
     consecut
    -0.63
    minist
    -0.60
    manship
    -0.60
     misunder
    -0.59
    hetti
    -0.58
    neys
    -0.58
     foreseeable
    -0.58
    POSITIVE LOGITS
     Inquisitor
    0.70
    tro
    0.67
     Hel
    0.65
     largeDownload
    0.65
    ©¶æ¥µ
    0.65
     ILCS
    0.64
    ///
    0.63
     Conclusion
    0.61
    ================================================================
    0.61
    imov
    0.60
    Act Density 0.072%

    No Known Activations