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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with questions, challenges, and controversial statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.06
    4:0.09
    5:0.02
    6:0.48
    7:0.06
    8:0.03
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    ALSE
    -1.32
    photo
    -1.29
     waivers
    -1.29
     lineup
    -1.28
     False
    -1.22
    January
    -1.22
    fen
    -1.20
    ****************
    -1.20
    �士
    -1.15
    {"
    -1.12
    POSITIVE LOGITS
    inki
    1.35
     bottleneck
    1.33
     wield
    1.31
    cest
    1.29
    fficient
    1.29
    asso
    1.27
    osate
    1.24
    ockets
    1.23
    ishly
    1.22
     Telescope
    1.21
    Act Density 0.043%

    No Known Activations