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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.07
    2:0.10
    3:0.06
    4:0.11
    5:0.09
    6:0.09
    7:0.07
    8:0.06
    9:0.05
    10:0.12
    11:0.07
    Negative Logits
    ◼
    -1.65
    �
    -1.57
    etheless
    -1.52
    NetMessage
    -1.51
    EStream
    -1.39
    ��
    -1.35
    SPONSORED
    -1.31
    mpeg
    -1.27
    ecycle
    -1.26
     largeDownload
    -1.24
    POSITIVE LOGITS
     Lies
    1.10
     Variant
    1.01
     Ny
    0.99
    Reading
    0.98
     Starts
    0.98
    ギ
    0.95
    ........
    0.94
     Reading
    0.93
     boots
    0.92
     goodbye
    0.91
    Act Density 0.137%

    No Known Activations