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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with popular websites and social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.07
    3:0.05
    4:0.06
    5:0.02
    6:0.37
    7:0.06
    8:0.03
    9:0.04
    10:0.11
    11:0.09
    Negative Logits
    iously
    -1.13
     Poe
    -1.12
     Chick
    -1.09
     Alv
    -1.08
     Zimmer
    -1.06
    combe
    -1.05
    quist
    -1.04
     whales
    -1.03
     scoff
    -1.02
    tein
    -1.02
    POSITIVE LOGITS
    ortium
    1.46
    support
    1.39
    ーク
    1.38
    itiz
    1.32
    readable
    1.25
    funding
    1.24
     newsp
    1.17
    rals
    1.17
    orthy
    1.15
    Done
    1.15
    Act Density 0.013%

    No Known Activations