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

    Neuronpedia

    INDEX
    Explanations

    passive voice verbs

    oai_token-act-pair · gpt-3.5-turbo

    verbs in passive voice constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.78
    ipeg
    -0.74
    guy
    -0.65
     traits
    -0.63
     validity
    -0.63
     wander
    -0.62
     Replacement
    -0.62
     loneliness
    -0.61
     contradiction
    -0.61
     compat
    -0.61
    POSITIVE LOGITS
     alerted
    1.13
     notified
    1.13
     sued
    1.13
     founded
    1.12
     fined
    1.10
     disbanded
    1.10
     aware
    1.03
     negligent
    1.02
     unable
    1.01
     obliged
    1.01
    Act Density 0.324%

    No Known Activations