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

    Neuronpedia

    INDEX
    Explanations

    the presence of common nouns or specific subjects related to a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.06
    3:0.09
    4:0.07
    5:0.09
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    ��
    -2.20
    icter
    -2.16
    aughs
    -2.12
    �
    -2.01
    �
    -2.00
     architect
    -2.00
     Symphony
    -1.97
     architects
    -1.96
    ™
    -1.92
     Champion
    -1.90
    POSITIVE LOGITS
    "}
    2.71
    \-
    2.23
     seiz
    2.22
    Reviewed
    2.10
    umen
    2.06
    hold
    2.06
    "}],"
    2.03
     recharge
    1.99
    "},"
    1.98
    ources
    1.98
    Act Density 0.000%

    No Known Activations