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

    Neuronpedia

    INDEX
    Explanations

    contractions such as "it's" and "isn't"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is subjectively perceived or defined

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.64
     [-
    -0.64
     BB
    -0.62
    ume
    -0.61
     Daly
    -0.61
     Clear
    -0.60
     Harlem
    -0.59
     allegedly
    -0.57
     Gil
    -0.56
    -[
    -0.56
    POSITIVE LOGITS
    rosso
    1.03
     wiser
    0.90
     someday
    0.86
     somew
    0.85
    cheat
    0.80
     misunder
    0.72
    legged
    0.72
     underest
    0.70
     typo
    0.70
    vana
    0.69
    Act Density 0.341%

    No Known Activations