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

    Neuronpedia

    INDEX
    Explanations

    references to applications, sharing, and emphasis on connectivity in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.30
    2:0.04
    3:0.05
    4:0.04
    5:0.10
    6:0.06
    7:0.03
    8:0.05
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     Antar
    -2.05
     Palest
    -1.92
     Amph
    -1.76
    agnetic
    -1.68
    yan
    -1.68
    unin
    -1.64
    romy
    -1.64
    orah
    -1.64
     humid
    -1.56
     Combat
    -1.52
    POSITIVE LOGITS
     link
    2.61
    link
    2.29
     LINK
    2.29
    Link
    2.17
     links
    2.01
     Link
    1.91
    INK
    1.72
    WARD
    1.68
     linkage
    1.64
    JV
    1.63
    Act Density 0.001%

    No Known Activations