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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals identified by the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.67
    NRS
    -0.67
    farious
    -0.66
     Destination
    -0.63
    seless
    -0.62
    problem
    -0.61
    Something
    -0.60
     Checking
    -0.59
    foundation
    -0.59
    evaluate
    -0.59
    POSITIVE LOGITS
     owns
    1.13
     grew
    1.05
     suffers
    1.05
     earns
    1.04
     died
    0.97
     lives
    0.97
     prefers
    0.94
     specializes
    0.94
     wears
    0.92
     resides
    0.91
    Act Density 0.089%

    No Known Activations