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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures, specifically "bosses."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.76
     itſelf
    -0.70
     ſch
    -0.63
     ſta
    -0.63
     ainfi
    -0.63
     purpoſe
    -0.60
     quæ
    -0.60
     étoit
    -0.59
    ſelf
    -0.59
     ſche
    -0.58
    POSITIVE LOGITS
     boss
    0.75
     Boss
    0.71
     bosses
    0.63
     competent
    0.61
    competent
    0.58
    boss
    0.57
    Boss
    0.55
    compet
    0.54
     competency
    0.54
     BOSS
    0.50
    Act Density 0.196%

    No Known Activations