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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.08
    3:0.06
    4:0.07
    5:0.03
    6:0.04
    7:0.37
    8:0.04
    9:0.04
    10:0.13
    11:0.05
    Negative Logits
    deen
    -1.52
     Dah
    -1.45
    vation
    -1.45
    icone
    -1.42
     Gutenberg
    -1.39
    zers
    -1.38
     Hurricane
    -1.34
    warning
    -1.32
     Lent
    -1.31
    rays
    -1.29
    POSITIVE LOGITS
    pai
    1.69
     semantics
    1.67
     roy
    1.65
     splitting
    1.64
     turf
    1.62
     proposition
    1.62
     alliances
    1.60
     superiority
    1.60
    Hash
    1.60
     pse
    1.58
    Act Density 0.001%

    No Known Activations