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

    Neuronpedia

    INDEX
    Explanations

    mentions of suspensions or disciplinary actions against individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.02
    6:0.36
    7:0.04
    8:0.04
    9:0.24
    10:0.02
    11:0.02
    Negative Logits
    Catalog
    -3.89
    slave
    -3.82
    consumer
    -3.81
    adobe
    -3.72
    rawdownloadcloneembedreportprint
    -3.67
     dolphin
    -3.59
     Portug
    -3.54
     dolphins
    -3.51
     Voyager
    -3.49
    avi
    -3.45
    POSITIVE LOGITS
     Hill
    10.40
    Hill
    10.39
     hill
    7.73
    hill
    5.75
     Hills
    5.39
     hills
    5.26
     Ridge
    4.92
     Heights
    4.13
     Cliff
    4.10
     Grove
    4.09
    Act Density 0.016%

    No Known Activations