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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.08
    2:0.02
    3:0.30
    4:0.03
    5:0.14
    6:0.06
    7:0.02
    8:0.06
    9:0.10
    10:0.02
    11:0.01
    Negative Logits
    PATH
    -2.02
    Article
    -1.95
    lists
    -1.85
    tier
    -1.80
    LIST
    -1.79
    ��
    -1.74
    �
    -1.73
    Statistics
    -1.71
    APD
    -1.71
    �
    -1.70
    POSITIVE LOGITS
     Roose
    1.95
     Proud
    1.77
     museums
    1.77
     Ambro
    1.75
     Alb
    1.74
     Peru
    1.71
     pard
    1.71
     Rept
    1.70
     Ft
    1.70
     Pow
    1.68
    Act Density 0.093%

    No Known Activations