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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences or narratives

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gem
    -0.80
    license
    -0.68
    nesty
    -0.68
    mson
    -0.66
    oen
    -0.64
    tier
    -0.63
    uve
    -0.62
    eers
    -0.62
    emort
    -0.62
    vote
    -0.62
    POSITIVE LOGITS
     firsthand
    1.04
     Rebell
    0.92
     Exper
    0.90
    é¾įåĸļ士
    0.89
     experiences
    0.86
     experien
    0.85
     recounted
    0.84
     upbringing
    0.80
     vividly
    0.79
     endured
    0.77
    Act Density 0.178%

    No Known Activations