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

    Neuronpedia

    INDEX
    Explanations

    references to institutions and their roles in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.04
    4:0.07
    5:0.02
    6:0.06
    7:0.41
    8:0.02
    9:0.03
    10:0.13
    11:0.08
    Negative Logits
     ratios
    -1.67
    oren
    -1.61
    onyms
    -1.59
    estyles
    -1.56
    eny
    -1.54
     phrases
    -1.50
     queries
    -1.47
    oaded
    -1.43
    ients
    -1.43
    76561
    -1.42
    POSITIVE LOGITS
     Starfleet
    1.87
     Instit
    1.79
    Military
    1.62
     governance
    1.60
    negie
    1.60
    GC
    1.57
    Management
    1.56
    ICS
    1.53
     foundation
    1.52
    Universal
    1.51
    Act Density 0.010%

    No Known Activations