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

    Neuronpedia

    INDEX
    Explanations

    locations and institutions related to government and public services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.18
    3:0.13
    4:0.21
    5:0.04
    6:0.05
    7:0.03
    8:0.05
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
    etheless
    -1.72
     unequivocally
    -1.67
     smarter
    -1.67
    cipled
    -1.61
    ItemTracker
    -1.60
    ourcing
    -1.56
     empath
    -1.54
     faire
    -1.53
     Canaver
    -1.50
     inexpensive
    -1.50
    POSITIVE LOGITS
     CTR
    1.62
     Soldiers
    1.59
     Statue
    1.58
     Hospital
    1.57
     Recre
    1.55
     entrance
    1.54
    rium
    1.54
    tons
    1.51
     Athlet
    1.45
     Revelation
    1.44
    Act Density 0.155%

    No Known Activations