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

    Neuronpedia

    INDEX
    Explanations

    references to digital technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.05
    2:0.09
    3:0.04
    4:0.03
    5:0.03
    6:0.21
    7:0.03
    8:0.03
    9:0.25
    10:0.03
    11:0.03
    Negative Logits
    tel
    -3.84
     thor
    -3.73
     Kemp
    -3.62
     Thur
    -3.54
     Howe
    -3.50
    rongh
    -3.50
    ara
    -3.50
     tow
    -3.50
     decl
    -3.49
     Wyr
    -3.40
    POSITIVE LOGITS
    mix
    8.73
     Mix
    8.71
    Mix
    8.57
     mixes
    7.71
     mixer
    7.28
     mixing
    7.17
     mix
    7.13
     Blend
    5.65
     Mixed
    5.52
     mixed
    5.40
    Act Density 0.005%

    No Known Activations