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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their actions or characteristics, especially in the context of conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.06
    4:0.25
    5:0.02
    6:0.05
    7:0.30
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    imester
    -1.94
    iland
    -1.83
    ommel
    -1.77
    lege
    -1.63
    yssey
    -1.62
    legates
    -1.59
    answered
    -1.54
    akis
    -1.49
     Janeiro
    -1.49
    writers
    -1.47
    POSITIVE LOGITS
     tom
    1.66
     indiscrim
    1.57
     mortar
    1.53
     plaster
    1.50
     retali
    1.45
     sarc
    1.44
     cannon
    1.43
     cannons
    1.43
     disproportionate
    1.43
    Interstitial
    1.41
    Act Density 0.003%

    No Known Activations