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

    Neuronpedia

    INDEX
    Explanations

    the concept of "something" in various contexts and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.05
    2:0.25
    3:0.03
    4:0.03
    5:0.04
    6:0.11
    7:0.08
    8:0.04
    9:0.07
    10:0.12
    11:0.07
    Negative Logits
    lement
    -1.42
     IMAGES
    -1.08
    oppers
    -1.07
    berus
    -1.05
    heit
    -1.05
    ippers
    -1.02
    enegger
    -1.01
     Strait
    -0.99
    aths
    -0.98
    lings
    -0.98
    POSITIVE LOGITS
    マ
    1.21
     else
    1.00
    WithNo
    0.92
    Untitled
    0.90
     provisional
    0.90
    uine
    0.89
    anooga
    0.89
    dimension
    0.89
     somewhere
    0.88
    Balance
    0.86
    Act Density 0.043%

    No Known Activations