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

    Neuronpedia

    INDEX
    Explanations

    references to military or governmental activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.33
    1:0.02
    2:0.09
    3:0.14
    4:0.03
    5:0.04
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.11
    11:0.03
    Negative Logits
    icrobial
    -2.15
    hp
    -2.11
     headlights
    -2.11
     nano
    -1.93
     crest
    -1.90
     steak
    -1.88
     Chevrolet
    -1.87
     Generation
    -1.86
     Leopard
    -1.85
    texture
    -1.83
    POSITIVE LOGITS
     cancell
    2.79
     proced
    2.76
     originate
    2.67
    geries
    2.57
     preceded
    2.43
     cancelled
    2.35
     commissions
    2.33
     involve
    2.32
     occur
    2.31
     duration
    2.30
    Act Density 0.410%

    No Known Activations