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

    Neuronpedia

    INDEX
    Explanations

    connections between different components and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.03
    3:0.15
    4:0.03
    5:0.08
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.44
    11:0.02
    Negative Logits
    nesty
    -2.29
     refused
    -2.00
    aunted
    -1.99
    iven
    -1.99
    inventoryQuantity
    -1.96
    pection
    -1.95
    erous
    -1.94
     overshadowed
    -1.85
    nor
    -1.85
    Nor
    -1.84
    POSITIVE LOGITS
     dots
    3.00
     toget
    2.50
     via
    2.48
     onto
    2.31
     together
    2.21
     to
    2.17
     directly
    2.07
     connects
    2.04
     Together
    2.02
     connecting
    2.02
    Act Density 0.059%

    No Known Activations