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

    Neuronpedia

    INDEX
    Explanations

    words with the suffix "-ised."

    oai_token-act-pair · gpt-3.5-turbo

    words that convey the concept of being made or transformed into a particular state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enson
    -0.59
     harbor
    -0.59
     totaling
    -0.58
     longtime
    -0.58
     attorneys
    -0.58
     rumors
    -0.57
     Attorney
    -0.57
     cove
    -0.55
     Eternal
    -0.55
     felon
    -0.53
    POSITIVE LOGITS
    ised
    4.38
    ising
    2.89
    ized
    2.87
    isation
    2.86
    ises
    2.70
    isations
    2.55
    ise
    2.35
    isers
    2.15
    isable
    2.06
    izes
    2.05
    Act Density 0.007%

    No Known Activations