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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and terminology related to societal structures and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.06
    3:0.04
    4:0.02
    5:0.05
    6:0.10
    7:0.34
    8:0.09
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
     sidx
    -1.46
    etheus
    -1.33
    untled
    -1.31
    hesda
    -1.25
    obos
    -1.22
     conclud
    -1.17
     livest
    -1.11
     externalToEVAOnly
    -1.10
     inflamm
    -1.10
     Qiao
    -1.09
    POSITIVE LOGITS
     yacht
    1.33
     clubhouse
    1.00
     Neander
    0.98
    ework
    0.98
    ヘ
    0.97
     Marine
    0.97
    eur
    0.93
     Slater
    0.93
     Monk
    0.92
     surf
    0.92
    Act Density 0.696%

    No Known Activations