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

    Neuronpedia

    INDEX
    Explanations

    past actions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I've been."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.73
    ierrez
    -0.72
    izable
    -0.71
    rium
    -0.70
    now
    -0.69
    ellar
    -0.68
    éĹĺ
    -0.67
    ottage
    -0.67
    terday
    -0.66
    Entry
    -0.66
    POSITIVE LOGITS
     itching
    1.02
     wanting
    1.00
     practicing
    0.96
     dreaming
    0.96
     fortunate
    0.95
     waiting
    0.94
     noticing
    0.92
     eyeing
    0.92
     longing
    0.91
     thinking
    0.91
    Act Density 0.081%

    No Known Activations