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

    Neuronpedia

    INDEX
    Explanations

    terms related to division or separation among groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.06
    4:0.37
    5:0.03
    6:0.05
    7:0.17
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    cooked
    -1.70
    hid
    -1.55
    embed
    -1.45
    advert
    -1.39
     miracles
    -1.34
    motion
    -1.33
    rosso
    -1.30
     Enhancement
    -1.30
    opal
    -1.28
    offer
    -1.28
    POSITIVE LOGITS
     purse
    1.76
    emies
    1.69
     Cind
    1.52
    MpServer
    1.52
    cloth
    1.51
    ynes
    1.47
     aback
    1.40
     evenly
    1.38
     thous
    1.38
     ire
    1.37
    Act Density 0.006%

    No Known Activations