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

    Neuronpedia

    INDEX
    Explanations

    phrases related to notable individuals and their unique contributions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.07
    2:0.08
    3:0.03
    4:0.03
    5:0.03
    6:0.26
    7:0.09
    8:0.02
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
    acco
    -3.19
    ascus
    -3.02
     ASA
    -3.00
    hazard
    -3.00
    blance
    -2.83
    assad
    -2.75
     agency
    -2.75
     Agency
    -2.75
    apor
    -2.69
    cig
    -2.69
    POSITIVE LOGITS
    Larry
    8.11
     Larry
    7.94
     Sergey
    3.55
    Jerry
    3.25
     Lawrence
    3.16
     IEEE
    3.05
    Oracle
    3.02
     Louie
    3.02
     Laure
    2.99
    NL
    2.99
    Act Density 0.010%

    No Known Activations