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

    Neuronpedia

    INDEX
    Explanations

    frequency of numerical values and quantifiable measurements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.20
    1:0.05
    2:0.02
    3:0.13
    4:0.08
    5:0.10
    6:0.05
    7:0.03
    8:0.14
    9:0.10
    10:0.03
    11:0.02
    Negative Logits
     actionGroup
    -2.40
    ���
    -1.85
    aler
    -1.82
    wcsstore
    -1.80
    ��
    -1.78
    agall
    -1.75
    lication
    -1.69
    isse
    -1.68
    irie
    -1.68
    ther
    -1.68
    POSITIVE LOGITS
     unbelievable
    2.23
     total
    2.06
     believable
    2.00
     worth
    1.97
     totals
    1.94
     nightmare
    1.92
     dissatisf
    1.91
     TOTAL
    1.91
     underestimate
    1.88
     wow
    1.87
    Act Density 0.001%

    No Known Activations