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

    Neuronpedia

    INDEX
    Explanations

    conversational transitions and filler phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.04
    3:0.14
    4:0.22
    5:0.01
    6:0.16
    7:0.17
    8:0.03
    9:0.02
    10:0.05
    11:0.08
    Negative Logits
     synonymous
    -1.45
     Ambro
    -1.42
     Osc
    -1.34
     appl
    -1.29
     denote
    -1.29
     Pwr
    -1.28
     stret
    -1.27
     amounted
    -1.26
     centerpiece
    -1.24
     spree
    -1.24
    POSITIVE LOGITS
    osaurs
    1.59
    vantage
    1.50
    ggies
    1.48
     comrade
    1.42
    \",
    1.39
     comrades
    1.38
    DragonMagazine
    1.38
    anners
    1.34
    wat
    1.34
    ileged
    1.31
    Act Density 0.008%

    No Known Activations