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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.10
    3:0.06
    4:0.04
    5:0.05
    6:0.06
    7:0.10
    8:0.07
    9:0.17
    10:0.13
    11:0.07
    Negative Logits
    �
    -1.10
    oyal
    -1.05
     ancest
    -1.03
     domains
    -0.99
    jong
    -0.99
    edy
    -0.96
    iosis
    -0.95
    ones
    -0.93
    omever
    -0.93
    Alert
    -0.91
    POSITIVE LOGITS
     gestation
    1.38
     onwards
    1.36
    released
    1.23
    imester
    1.22
    ��
    1.19
    bernatorial
    1.16
    enhagen
    1.10
     Maiden
    1.09
     release
    1.08
     clearance
    1.05
    Act Density 0.022%

    No Known Activations