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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals involved in various narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.09
    4:0.16
    5:0.04
    6:0.11
    7:0.22
    8:0.04
    9:0.06
    10:0.05
    11:0.06
    Negative Logits
    quickShipAvailable
    -1.70
    Dynamic
    -1.58
    Asia
    -1.50
    Compare
    -1.41
    soType
    -1.39
    INO
    -1.34
    ahime
    -1.32
    imaru
    -1.31
     Norn
    -1.30
    Girls
    -1.30
    POSITIVE LOGITS
     retire
    1.59
    rows
    1.53
     debacle
    1.51
     leaves
    1.47
     Leaves
    1.47
    hower
    1.46
     stint
    1.42
    het
    1.40
     successes
    1.40
     retired
    1.38
    Act Density 0.021%

    No Known Activations