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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of a specific individual named "Mas"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Mas"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ames
    -0.69
    ï¸ı
    -0.67
    unes
    -0.64
    orer
    -0.63
     Grimes
    -0.63
    sburgh
    -0.62
    IFIED
    -0.61
     liner
    -0.60
     Saskatchewan
    -0.60
     BMC
    -0.59
    POSITIVE LOGITS
    querade
    1.38
    cul
    1.33
    quer
    1.14
    ques
    1.04
    culus
    1.04
    dar
    1.01
    sey
    0.99
    que
    0.97
    seys
    0.92
    sei
    0.91
    Act Density 0.032%

    No Known Activations