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

    Neuronpedia

    INDEX
    Explanations

    references to organizations or online platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Deal
    -0.79
     Roads
    -0.75
    PLIED
    -0.71
    western
    -0.68
    DonaldTrump
    -0.66
     Glover
    -0.66
     Guards
    -0.64
    BOOK
    -0.64
    Disclaimer
    -0.63
    Mini
    -0.62
    POSITIVE LOGITS
     org
    1.27
    asms
    1.07
    inal
    1.05
    ersen
    0.88
    urable
    0.87
    ittal
    0.87
    inators
    0.85
     skelet
    0.84
    ination
    0.83
    inates
    0.79
    Act Density 0.009%

    No Known Activations