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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thus" and its variations, indicating conclusions or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bernadette
    -0.93
     Coton
    -0.87
     Eureka
    -0.84
     Frankie
    -0.83
     Apre
    -0.82
     LON
    -0.82
     Colette
    -0.82
    bek
    -0.81
    eable
    -0.81
     Whal
    -0.80
    POSITIVE LOGITS
     thus
    1.42
     Thus
    1.31
    thus
    1.28
    Thus
    1.25
     Ainsi
    1.05
    Ainsi
    1.03
    ly
    0.95
     demikian
    0.84
     către
    0.84
     ويكيميديا
    0.83
    Act Density 0.103%

    No Known Activations