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

    Neuronpedia

    INDEX
    Explanations

    names or references related to prestigious titles such as "Pri" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "pri" or its variations, indicating a focus on awards or recognition related to "prizes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.12
    schild
    -0.83
    icago
    -0.79
     bracelet
    -0.71
    lihood
    -0.70
    ded
    -0.68
     dred
    -0.66
     Wink
    -0.66
    ding
    -0.66
    INESS
    -0.65
    POSITIVE LOGITS
    ests
    1.13
    zes
    1.05
    esses
    1.01
    ety
    0.98
    eties
    0.94
    etary
    0.92
    quet
    0.91
    archs
    0.89
    vy
    0.88
    heed
    0.87
    Act Density 0.012%

    No Known Activations