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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating immediacy or current relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.11
    3:0.03
    4:0.02
    5:0.04
    6:0.15
    7:0.23
    8:0.05
    9:0.08
    10:0.07
    11:0.14
    Negative Logits
     breakup
    -1.11
     mask
    -1.06
    hid
    -1.06
    formance
    -0.97
     acronym
    -0.96
    urat
    -0.95
     triangle
    -0.94
    ミ
    -0.93
    arb
    -0.93
    duty
    -0.91
    POSITIVE LOGITS
    seekers
    1.06
    zyk
    1.01
    OIL
    1.00
    wat
    0.96
    SPONSORED
    0.94
     sear
    0.90
     archaeologists
    0.90
    sql
    0.90
     Wik
    0.90
    emis
    0.89
    Act Density 0.017%

    No Known Activations