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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.04
    4:0.12
    5:0.02
    6:0.04
    7:0.40
    8:0.04
    9:0.02
    10:0.04
    11:0.11
    Negative Logits
    hop
    -1.85
    bows
    -1.80
    ø
    -1.60
    stown
    -1.55
     Bought
    -1.53
    hell
    -1.50
    hest
    -1.50
    ł
    -1.49
    ouched
    -1.48
    arnaev
    -1.47
    POSITIVE LOGITS
     pse
    1.95
     behavi
    1.86
     orally
    1.75
     authoritative
    1.74
     narr
    1.72
     AUTH
    1.72
    覚醒
    1.68
     unbeliev
    1.65
     histories
    1.63
     millenn
    1.61
    Act Density 0.000%

    No Known Activations