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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.06
    4:0.23
    5:0.03
    6:0.14
    7:0.14
    8:0.03
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     accessed
    -1.42
     Units
    -1.35
     Attacks
    -1.32
     Females
    -1.31
     Males
    -1.31
     assembled
    -1.29
     ALSO
    -1.28
    guards
    -1.27
     Cells
    -1.25
    rium
    -1.23
    POSITIVE LOGITS
     convinc
    1.65
    enough
    1.54
    henko
    1.54
    ensical
    1.52
    BuyableInstoreAndOnline
    1.51
    ibaba
    1.44
    successfully
    1.44
    agra
    1.40
    ingen
    1.39
     satisf
    1.38
    Act Density 0.011%

    No Known Activations