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

    Neuronpedia

    INDEX
    Explanations

    instances of dates or years

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.71
    icago
    -0.66
     nap
    -0.65
     fray
    -0.64
     partName
    -0.62
     confinement
    -0.61
     Saying
    -0.61
     chatter
    -0.60
     relativity
    -0.60
    vas
    -0.59
    POSITIVE LOGITS
     replaced
    1.05
     released
    1.04
     implemented
    0.99
    amed
    0.96
     distributed
    0.95
     unveiled
    0.94
     executed
    0.93
     overseen
    0.92
     delivered
    0.92
     administered
    0.92
    Act Density 0.072%

    No Known Activations