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

    Neuronpedia

    INDEX
    Explanations

    statements that emphasize importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.14
    3:0.08
    4:0.09
    5:0.03
    6:0.05
    7:0.26
    8:0.04
    9:0.04
    10:0.05
    11:0.12
    Negative Logits
    ahime
    -1.62
     proud
    -1.57
    grad
    -1.57
     maze
    -1.53
     halfway
    -1.50
     tricked
    -1.50
     reluct
    -1.49
     strateg
    -1.49
     stumbling
    -1.49
    agle
    -1.48
    POSITIVE LOGITS
    Premium
    1.69
     Allaah
    1.63
     SERVICES
    1.58
    CTV
    1.56
     Flavoring
    1.52
     Presence
    1.50
     ACTION
    1.49
     Transactions
    1.48
     Customer
    1.48
    Untitled
    1.47
    Act Density 0.001%

    No Known Activations