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

    Neuronpedia

    INDEX
    Explanations

    references to numbers or numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.04
    2:0.01
    3:0.13
    4:0.07
    5:0.07
    6:0.04
    7:0.07
    8:0.07
    9:0.12
    10:0.03
    11:0.21
    Negative Logits
    -.
    -2.33
    abouts
    -2.32
    0200
    -2.15
    ueless
    -2.13
    pdf
    -2.11
    -'
    -2.09
    tml
    -2.04
    bid
    -2.01
    dq
    -2.01
    pex
    -2.00
    POSITIVE LOGITS
    ModLoader
    1.78
     reconstruction
    1.76
    ULT
    1.73
     beauty
    1.71
    UST
    1.66
     transform
    1.64
    作
    1.64
     transformation
    1.61
     lamp
    1.60
    オ
    1.58
    Act Density 0.000%

    No Known Activations