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

    Neuronpedia

    INDEX
    Explanations

    first person singular statements about various topics

    oai_token-act-pair · gpt-3.5-turbo

    statements of self-perception or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Farming
    -0.74
    enge
    -0.62
    owship
    -0.61
     Gale
    -0.58
     Hazard
    -0.57
    ception
    -0.57
     Bucks
    -0.56
    earch
    -0.54
    tions
    -0.54
     Us
    -0.53
    POSITIVE LOGITS
    'm
    1.03
    'll
    1.03
    've
    1.01
     dodged
    0.86
    'd
    0.86
     can
    0.76
    owa
    0.75
    athered
    0.74
    asel
    0.74
    zzo
    0.74
    Act Density 0.110%

    No Known Activations