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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.05
    2:0.13
    3:0.09
    4:0.06
    5:0.06
    6:0.04
    7:0.03
    8:0.07
    9:0.11
    10:0.10
    11:0.10
    Negative Logits
    yip
    -1.44
    kef
    -1.43
    nown
    -1.38
    psey
    -1.32
    wig
    -1.31
    abal
    -1.31
     scrut
    -1.28
    undai
    -1.27
    ndum
    -1.24
    staking
    -1.23
    POSITIVE LOGITS
    RELATED
    1.18
    Buff
    1.16
    },
    1.14
     receivers
    1.13
     Balanced
    1.10
     Gain
    1.09
    OURCE
    1.08
    Years
    1.07
     fibers
    1.06
     Composite
    1.06
    Act Density 0.010%

    No Known Activations