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

    Neuronpedia

    INDEX
    Explanations

    generally accepted narratives in crime-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.11
    3:0.07
    4:0.32
    5:0.02
    6:0.10
    7:0.15
    8:0.02
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    Interstitial
    -1.90
    isSpecialOrderable
    -1.87
    inventoryQuantity
    -1.66
    dayName
    -1.63
    ach
    -1.53
    _-
    -1.53
    lins
    -1.50
    eches
    -1.47
    ande
    -1.43
    aches
    -1.43
    POSITIVE LOGITS
     practition
    1.56
     fray
    1.52
    ILD
    1.50
     UA
    1.42
    iyah
    1.34
    RM
    1.33
     programme
    1.32
     earthqu
    1.31
     infertility
    1.29
     custody
    1.26
    Act Density 0.005%

    No Known Activations