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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations related to organizations and regulatory bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.10
    2:0.09
    3:0.08
    4:0.06
    5:0.03
    6:0.16
    7:0.10
    8:0.04
    9:0.05
    10:0.08
    11:0.12
    Negative Logits
     USC
    -2.97
     Fellowship
    -2.60
     sor
    -2.52
     Organ
    -2.48
     sponsoring
    -2.48
     Program
    -2.39
     DOT
    -2.38
     Committee
    -2.38
     fraternity
    -2.37
     Priority
    -2.37
    POSITIVE LOGITS
    alogue
    2.73
    gae
    2.71
     Seym
    2.70
    я
    2.57
    ソ
    2.41
    cale
    2.39
    ナ
    2.33
    Moore
    2.33
    morrow
    2.31
    perature
    2.29
    Act Density 0.002%

    No Known Activations