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

    Neuronpedia

    INDEX
    Explanations

    references to personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.09
    5:0.03
    6:0.06
    7:0.32
    8:0.04
    9:0.03
    10:0.15
    11:0.09
    Negative Logits
    dates
    -1.87
     patents
    -1.67
    birth
    -1.54
     leases
    -1.47
     vouchers
    -1.42
    ebook
    -1.39
     licences
    -1.38
     certificates
    -1.37
     discoveries
    -1.37
     supplies
    -1.36
    POSITIVE LOGITS
     persona
    1.58
     Grizz
    1.54
     demeanor
    1.48
     Lieutenant
    1.43
     Tact
    1.43
     fearless
    1.42
    Lt
    1.41
    aggressive
    1.37
     Courage
    1.36
     intimidating
    1.35
    Act Density 0.001%

    No Known Activations