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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating states of existence or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sums
    -0.69
     Visitors
    -0.68
     Yaz
    -0.67
     Sons
    -0.67
     summarizes
    -0.66
     Together
    -0.66
     Doe
    -0.65
     Pension
    -0.64
     Janeiro
    -0.62
     Refugee
    -0.62
    POSITIVE LOGITS
     commonplace
    1.23
     prevalent
    1.18
     rampant
    1.14
     predominant
    1.13
     rife
    1.06
     abound
    1.00
     paramount
    0.96
     ubiquitous
    0.95
     substituted
    0.94
     everywhere
    0.93
    Act Density 0.301%

    No Known Activations