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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.11
    4:0.10
    5:0.03
    6:0.35
    7:0.05
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    advertisement
    -1.59
    andise
    -1.44
    pection
    -1.40
    Mine
    -1.39
     chase
    -1.33
    Exit
    -1.32
    Commerce
    -1.31
     carriage
    -1.27
    olls
    -1.21
    olphin
    -1.21
    POSITIVE LOGITS
    rosso
    1.55
    oğ
    1.47
    inous
    1.45
    agu
    1.29
    ッ
    1.28
    auc
    1.28
     Bie
    1.20
    onomous
    1.19
    sy
    1.17
    ten
    1.16
    Act Density 0.028%

    No Known Activations