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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions with the form "has been"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "has been."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.74
    rones
    -0.74
    odder
    -0.70
    ives
    -0.69
     Relief
    -0.68
     Awakens
    -0.66
     Wid
    -0.66
     Wish
    -0.64
    lies
    -0.63
    would
    -0.62
    POSITIVE LOGITS
     subjected
    0.95
     replaced
    0.94
     deemed
    0.93
     likened
    0.92
     seen
    0.91
     shown
    0.90
     able
    0.90
     taken
    0.89
    avering
    0.88
     forgiven
    0.86
    Act Density 0.155%

    No Known Activations