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

    Neuronpedia

    INDEX
    Explanations

    references to players and statistics related to sports or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.14
    3:0.07
    4:0.05
    5:0.12
    6:0.03
    7:0.02
    8:0.19
    9:0.09
    10:0.07
    11:0.03
    Negative Logits
    usters
    -1.32
    enson
    -1.24
    byter
    -1.21
    rers
    -1.18
    encia
    -1.18
    soever
    -1.17
    shire
    -1.14
    hers
    -1.13
    ansen
    -1.12
    aneers
    -1.11
    POSITIVE LOGITS
     angles
    1.42
     positives
    1.39
     possibilities
    1.38
     resemblance
    1.34
     similarity
    1.33
    TextColor
    1.33
    inventoryQuantity
    1.29
     similarities
    1.29
     resemb
    1.29
     angle
    1.26
    Act Density 0.055%

    No Known Activations