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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating hypothetical situations and emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     converge
    -0.68
     procedure
    -0.67
     originate
    -0.64
    aceutical
    -0.64
     residue
    -0.63
     scrimmage
    -0.63
     spectrum
    -0.61
    osate
    -0.60
     disperse
    -0.60
     arise
    -0.59
    POSITIVE LOGITS
     able
    1.15
    friends
    1.07
     thankful
    0.93
    getting
    0.93
     glad
    0.87
    acons
    0.87
     happiest
    0.87
    heading
    0.87
    league
    0.85
    orc
    0.85
    Act Density 0.235%

    No Known Activations