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

    Neuronpedia

    INDEX
    Explanations

    legislation related terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to legislation and companions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.20
    3:0.05
    4:0.15
    5:0.09
    6:0.03
    7:0.04
    8:0.07
    9:0.16
    10:0.06
    11:0.03
    Negative Logits
    龍契士
    -1.23
    ricted
    -1.20
     betting
    -1.13
    assetsadobe
    -1.12
    oday
    -1.12
    uthor
    -1.10
     submer
    -1.09
    hett
    -1.08
    assets
    -1.06
     Bucket
    -1.06
    POSITIVE LOGITS
    gio
    1.44
     Travels
    1.35
    gui
    1.33
    signed
    1.19
    utor
    1.17
    ioch
    1.15
    mons
    1.15
     Weasley
    1.12
    alone
    1.10
     Nero
    1.10
    Act Density 0.005%

    No Known Activations