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

    Neuronpedia

    INDEX
    Explanations

    references to Pulitzer Prizes and their winners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.39
    1:0.01
    2:0.06
    3:0.11
    4:0.03
    5:0.13
    6:0.02
    7:0.04
    8:0.06
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     Lego
    -2.62
     Iw
    -2.59
     Ridley
    -2.58
     Sega
    -2.43
     Whedon
    -2.32
     Tant
    -2.29
     Constantin
    -2.27
     Hera
    -2.23
     Atari
    -2.23
     Konami
    -2.19
    POSITIVE LOGITS
    ribune
    2.80
     Pulitzer
    2.76
     Reporting
    2.73
     dataset
    2.37
    opol
    2.36
    veyard
    2.35
    journal
    2.34
    icter
    2.33
    owler
    2.32
     reader
    2.29
    Act Density 0.001%

    No Known Activations