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

    Neuronpedia

    INDEX
    Explanations

    references to ancient civilizations and their artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.03
    2:0.05
    3:0.07
    4:0.10
    5:0.04
    6:0.03
    7:0.09
    8:0.02
    9:0.09
    10:0.02
    11:0.31
    Negative Logits
     Disability
    -2.38
     interns
    -2.35
     TF
    -2.33
     accountability
    -2.29
     Accountability
    -2.18
     metrics
    -2.18
     ABS
    -2.14
     RESP
    -2.12
    ticket
    -2.10
     ratings
    -2.10
    POSITIVE LOGITS
     Zoro
    3.75
     rituals
    3.54
     rites
    3.53
     civilizations
    3.44
     pagan
    3.42
     ancestors
    3.38
     traditions
    3.35
     deities
    3.31
     hier
    3.26
     temples
    3.25
    Act Density 0.399%

    No Known Activations