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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "sey" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "sey" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.74
     hunger
    -0.73
     supplies
    -0.68
     narcotics
    -0.66
     PKK
    -0.65
     CPC
    -0.65
    Balt
    -0.63
     tense
    -0.62
    ibal
    -0.61
    valued
    -0.61
    POSITIVE LOGITS
    sey
    1.58
    eah
    0.92
    yk
    0.89
    loo
    0.88
    ystem
    0.87
    ertodd
    0.85
    vana
    0.80
    seys
    0.80
     Payton
    0.79
    kee
    0.79
    Act Density 0.011%

    No Known Activations