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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals, with a focus on names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.33
    3:0.03
    4:0.03
    5:0.03
    6:0.06
    7:0.07
    8:0.04
    9:0.03
    10:0.11
    11:0.08
    Negative Logits
    atell
    -2.24
    yrinth
    -2.17
    enth
    -2.09
    venth
    -2.05
    irtual
    -2.05
    ocy
    -2.05
     Alright
    -2.02
    plets
    -2.02
    ItemTracker
    -2.02
    alys
    -1.98
    POSITIVE LOGITS
     Confederate
    2.19
    ►
    2.17
     condol
    2.17
     Caldwell
    2.12
     passage
    2.08
     condemnation
    2.02
     Gillespie
    2.00
    Davis
    1.99
     recommends
    1.98
    DonaldTrump
    1.97
    Act Density 0.005%

    No Known Activations