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

    Neuronpedia

    INDEX
    Explanations

    direct quotations or statements attributed to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.28
    3:0.07
    4:0.03
    5:0.04
    6:0.04
    7:0.07
    8:0.07
    9:0.06
    10:0.12
    11:0.10
    Negative Logits
    guyen
    -1.74
     Rookie
    -1.40
     Kik
    -1.34
     Luxem
    -1.31
    版
    -1.30
     Jungle
    -1.29
    ヘ
    -1.29
    displayText
    -1.29
     Pv
    -1.28
     millenn
    -1.27
    POSITIVE LOGITS
     …"
    1.63
    sic
    1.63
    ..."
    1.61
    idges
    1.57
     [...]
    1.57
    ."
    1.50
    selves
    1.50
     […]
    1.48
    ignty
    1.46
    …]
    1.46
    Act Density 0.049%

    No Known Activations