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

    Neuronpedia

    INDEX
    Explanations

    coding terminology and references to stack traces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.11
    2:0.08
    3:0.06
    4:0.05
    5:0.03
    6:0.10
    7:0.10
    8:0.03
    9:0.04
    10:0.15
    11:0.07
    Negative Logits
     Kinn
    -3.74
     Ari
    -3.14
    Ari
    -2.92
     Nev
    -2.88
     Neb
    -2.86
    kk
    -2.80
     Kap
    -2.77
     Kab
    -2.74
     Quadro
    -2.73
     Fallon
    -2.72
    POSITIVE LOGITS
     Trace
    6.66
     trace
    5.97
    trace
    5.86
     tracing
    4.75
     traced
    4.48
    Tr
    4.21
     traces
    4.13
    TR
    3.43
     TR
    3.43
     Trout
    3.09
    Act Density 0.001%

    No Known Activations