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

    Neuronpedia

    INDEX
    Explanations

    references to time and specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.11
    4:0.17
    5:0.03
    6:0.12
    7:0.03
    8:0.04
    9:0.04
    10:0.10
    11:0.17
    Negative Logits
     Sept
    -1.48
     bookmark
    -1.47
    terday
    -1.46
    assian
    -1.38
    HOU
    -1.36
     Slovenia
    -1.35
    nexus
    -1.32
     clause
    -1.32
     OPEC
    -1.29
     1850
    -1.29
    POSITIVE LOGITS
    Reviewer
    1.93
    ividual
    1.88
    sbm
    1.66
    asive
    1.61
    atever
    1.56
     Plaintiff
    1.43
    urus
    1.42
     UFOs
    1.42
     proport
    1.41
    mberg
    1.40
    Act Density 0.001%

    No Known Activations