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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating speech or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.03
    5:0.12
    6:0.02
    7:0.02
    8:0.04
    9:0.13
    10:0.39
    11:0.07
    Negative Logits
    miss
    -1.66
     indisc
    -1.52
     pageant
    -1.48
    fell
    -1.42
    incarn
    -1.41
    sburg
    -1.40
     indec
    -1.40
     tomb
    -1.39
    Appearances
    -1.39
     takeoff
    -1.38
    POSITIVE LOGITS
    resso
    1.57
     Insight
    1.57
     dx
    1.55
    ournals
    1.54
     algae
    1.51
     Analytics
    1.51
     analys
    1.51
    alyst
    1.49
     analyse
    1.49
     CLIENT
    1.48
    Act Density 0.943%

    No Known Activations