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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "you" or "I" is followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the first time" or references to past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meantime
    -0.70
    now
    -0.64
     retaining
    -0.61
    utical
    -0.58
     provisional
    -0.58
    urity
    -0.58
     nowhere
    -0.58
     Prepar
    -0.57
    redients
    -0.57
     Dhabi
    -0.57
    POSITIVE LOGITS
     ever
    1.08
     EVER
    1.05
     interacted
    1.04
     ventured
    1.00
     encountered
    1.00
     bothered
    0.99
     touched
    0.98
     interfered
    0.97
     encount
    0.97
     visited
    0.97
    Act Density 0.155%

    No Known Activations