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

    Neuronpedia

    INDEX
    Explanations

    references to positions of power or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.04
    4:0.08
    5:0.04
    6:0.35
    7:0.14
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
     mummy
    -1.40
     hurry
    -1.38
    usercontent
    -1.25
     Cruel
    -1.22
     Cavern
    -1.22
     Wax
    -1.21
     Hallow
    -1.19
     assurances
    -1.17
     Archdemon
    -1.16
    phrine
    -1.15
    POSITIVE LOGITS
    eele
    1.55
    CLASSIFIED
    1.38
    channelAvailability
    1.35
    pole
    1.30
    Interstitial
    1.29
    Nob
    1.28
    Offset
    1.28
    ��
    1.27
    PLA
    1.26
    agonists
    1.23
    Act Density 0.002%

    No Known Activations