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

    Neuronpedia

    INDEX
    Explanations

    words related to the prefix "prem" or "Prem" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "premier."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.86
    ger
    -0.78
     MacArthur
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    gers
    -0.71
     ãĤµ
    -0.71
     Hedge
    -0.71
     Tid
    -0.70
    meyer
    -0.70
     Scout
    -0.69
    POSITIVE LOGITS
    ises
    1.09
    antle
    1.04
    ortal
    1.01
    iere
    0.99
    iership
    0.95
    ilit
    0.92
     prem
    0.90
    ise
    0.87
    igrate
    0.87
    etheus
    0.86
    Act Density 0.017%

    No Known Activations