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

    Neuronpedia

    INDEX
    Explanations

    verbs in the imperative form

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rab
    -0.69
     Bars
    -0.66
     Awakens
    -0.66
    terday
    -0.63
     Nights
    -0.62
     TED
    -0.62
     Prairie
    -0.62
     Hitch
    -0.62
    might
    -0.61
     emergence
    -0.61
    POSITIVE LOGITS
     subjected
    1.10
     judged
    1.10
     considered
    1.10
     able
    1.08
     treated
    1.05
     taken
    1.03
     regarded
    1.02
     evaluated
    1.02
     deemed
    1.02
    acons
    1.01
    Act Density 0.314%

    No Known Activations