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

    Neuronpedia

    INDEX
    Explanations

    references to sports teams and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.02
    2:0.13
    3:0.10
    4:0.21
    5:0.03
    6:0.04
    7:0.03
    8:0.10
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
    assetsadobe
    -1.59
    76561
    -1.50
     misled
    -1.49
     compounded
    -1.49
     anecd
    -1.49
     likened
    -1.46
     cov
    -1.42
    reditary
    -1.38
     pioneered
    -1.36
    ochond
    -1.31
    POSITIVE LOGITS
    SPONSORED
    1.44
    grass
    1.40
    ?]
    1.33
     1888
    1.32
    comings
    1.31
     Handling
    1.31
     Pants
    1.26
     502
    1.24
     TBA
    1.23
    ============
    1.22
    Act Density 0.001%

    No Known Activations