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

    Neuronpedia

    INDEX
    Explanations

    information related to aviation incidents and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.03
    2:0.13
    3:0.09
    4:0.05
    5:0.09
    6:0.05
    7:0.10
    8:0.11
    9:0.04
    10:0.07
    11:0.03
    Negative Logits
     Rape
    -2.98
     raped
    -2.83
     rape
    -2.76
    Lib
    -2.75
    Marginal
    -2.56
     raping
    -2.54
    <?
    -2.52
    Labour
    -2.50
    ilib
    -2.49
     Ug
    -2.48
    POSITIVE LOGITS
     NTS
    4.37
     FAA
    3.46
     Elliott
    3.00
     Siber
    2.88
     Carroll
    2.87
     derail
    2.83
     Everett
    2.79
     Tracks
    2.76
     Boeing
    2.70
     cockpit
    2.69
    Act Density 0.001%

    No Known Activations