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

    Neuronpedia

    INDEX
    Explanations

    references to official documents and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.04
    4:0.03
    5:0.04
    6:0.02
    7:0.06
    8:0.03
    9:0.05
    10:0.44
    11:0.12
    Negative Logits
     Galile
    -1.50
     vigilante
    -1.48
     tragedy
    -1.44
     tragedies
    -1.41
     vigilant
    -1.40
    mare
    -1.39
     pity
    -1.38
     lyn
    -1.34
    "]=>
    -1.33
     vengeance
    -1.33
    POSITIVE LOGITS
    ��
    2.13
     outlining
    2.11
     detailing
    2.09
    itled
    2.00
     titled
    1.92
     outlines
    1.89
    enum
    1.81
     dated
    1.78
     revised
    1.72
     handwritten
    1.68
    Act Density 0.363%

    No Known Activations