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

    Neuronpedia

    INDEX
    Explanations

    terms related to bankruptcy and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.16
    3:0.06
    4:0.20
    5:0.06
    6:0.03
    7:0.03
    8:0.08
    9:0.13
    10:0.07
    11:0.03
    Negative Logits
    ufact
    -1.35
     worn
    -1.27
    agher
    -1.24
     cents
    -1.22
    osher
    -1.21
    uph
    -1.18
     luggage
    -1.17
     jackets
    -1.17
     detectors
    -1.17
     crib
    -1.16
    POSITIVE LOGITS
     Emails
    1.51
    clerosis
    1.46
     Despair
    1.36
    Meg
    1.34
     Kafka
    1.34
     Demon
    1.31
    "},"
    1.29
     Exam
    1.28
    aneous
    1.27
    -->
    1.24
    Act Density 0.001%

    No Known Activations