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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to government departments and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.01
    2:0.07
    3:0.38
    4:0.03
    5:0.15
    6:0.02
    7:0.05
    8:0.07
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     suff
    -1.93
     iceberg
    -1.93
     bluff
    -1.81
     outper
    -1.78
     selectively
    -1.76
     consciously
    -1.75
     metaphor
    -1.74
     roller
    -1.74
     passively
    -1.72
     inverse
    -1.71
    POSITIVE LOGITS
     Activities
    2.64
     Regulations
    2.56
     Instit
    2.52
     Facilities
    2.50
     Affairs
    2.50
     Tourism
    2.48
     Programs
    2.30
     Accessories
    2.29
     Registration
    2.26
     Devices
    2.25
    Act Density 0.220%

    No Known Activations