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

    Neuronpedia

    INDEX
    Explanations

    references to organizational roles and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.39
    3:0.03
    4:0.02
    5:0.03
    6:0.06
    7:0.08
    8:0.04
    9:0.02
    10:0.11
    11:0.08
    Negative Logits
    hof
    -3.17
     gobl
    -3.12
     brace
    -2.95
    hiba
    -2.79
     skelet
    -2.75
    alde
    -2.74
    kefeller
    -2.74
     confir
    -2.70
     scen
    -2.69
    anwhile
    -2.68
    POSITIVE LOGITS
     Publication
    4.01
     Message
    3.90
     Topic
    3.82
     Drop
    3.72
     Filter
    3.70
     Painting
    3.69
     Site
    3.65
     Tracks
    3.64
     Primary
    3.64
     Resource
    3.63
    Act Density 0.065%

    No Known Activations