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

    Neuronpedia

    INDEX
    Explanations

    references to news articles and sources related to reporting or ongoing stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.10
    2:0.03
    3:0.02
    4:0.06
    5:0.14
    6:0.05
    7:0.03
    8:0.04
    9:0.34
    10:0.04
    11:0.04
    Negative Logits
    olls
    -1.53
    atever
    -1.50
    ¯¯
    -1.48
    axis
    -1.47
    arters
    -1.46
    ilts
    -1.45
    cially
    -1.44
    bably
    -1.44
    adra
    -1.44
    erella
    -1.42
    POSITIVE LOGITS
     Replay
    1.60
     Updated
    1.45
     Telegram
    1.42
    Quotes
    1.42
     emoji
    1.42
     Deng
    1.38
     DVDs
    1.36
     OECD
    1.36
     newsletters
    1.36
    anu
    1.34
    Act Density 0.036%

    No Known Activations