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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions with the verb "be" followed by a gerund ("-ing" form of a verb)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Relief
    -0.74
     VIDEOS
    -0.73
     Mobility
    -0.72
     srfAttach
    -0.71
     Taxes
    -0.69
     Lag
    -0.64
     Wid
    -0.63
     Sop
    -0.62
     Elements
    -0.61
     Newspaper
    -0.60
    POSITIVE LOGITS
     evaluated
    1.01
     able
    1.00
     treated
    0.97
     replaced
    0.96
     judged
    0.95
     tested
    0.95
     assessed
    0.93
     investigated
    0.92
     subjected
    0.89
    amed
    0.88
    Act Density 0.062%

    No Known Activations