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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.06
    4:0.05
    5:0.03
    6:0.17
    7:0.20
    8:0.05
    9:0.05
    10:0.10
    11:0.09
    Negative Logits
    ゴン
    -2.02
    ��
    -1.68
    orst
    -1.53
    �
    -1.53
    Fourth
    -1.48
    ��
    -1.47
    ��
    -1.43
    Way
    -1.42
    enment
    -1.40
    \\\\\\\\
    -1.39
    POSITIVE LOGITS
     dollars
    1.79
     excess
    1.76
     amounts
    1.72
     shampoo
    1.63
     calories
    1.62
     amount
    1.59
     gallons
    1.59
     ounces
    1.58
     allot
    1.55
     peanuts
    1.54
    Act Density 0.010%

    No Known Activations