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

    Neuronpedia

    INDEX
    Explanations

    specific statistics and sample sizes in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.08
    2:0.02
    3:0.10
    4:0.06
    5:0.20
    6:0.12
    7:0.03
    8:0.11
    9:0.10
    10:0.02
    11:0.02
    Negative Logits
    Beast
    -1.94
    inventoryQuantity
    -1.88
    Tokens
    -1.82
     ripping
    -1.79
    Thunder
    -1.75
     razor
    -1.72
     slamming
    -1.70
    Jew
    -1.61
    atron
    -1.58
    �
    -1.58
    POSITIVE LOGITS
     cohort
    2.39
     randomized
    2.33
     administered
    2.30
     enrolled
    2.24
     recruited
    2.22
     population
    2.22
     Population
    2.13
     occupational
    2.13
     demographic
    2.10
     populations
    2.09
    Act Density 0.105%

    No Known Activations