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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.13
    2:0.06
    3:0.07
    4:0.05
    5:0.03
    6:0.17
    7:0.09
    8:0.04
    9:0.04
    10:0.10
    11:0.11
    Negative Logits
     scout
    -2.56
     electors
    -2.52
    isconsin
    -2.51
     spine
    -2.46
     corridors
    -2.42
     revenge
    -2.39
     drafted
    -2.38
     drafting
    -2.36
     arcs
    -2.36
     heating
    -2.36
    POSITIVE LOGITS
     Show
    4.35
    Show
    3.85
     SHOW
    3.66
     Admission
    3.17
     Demand
    3.02
     Showdown
    2.96
     Perform
    2.94
     Markets
    2.89
    Display
    2.87
     Lect
    2.86
    Act Density 0.001%

    No Known Activations