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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.10
    3:0.06
    4:0.05
    5:0.05
    6:0.11
    7:0.22
    8:0.04
    9:0.03
    10:0.16
    11:0.07
    Negative Logits
     suspense
    -2.15
    anos
    -2.10
    etheus
    -2.06
    azel
    -1.93
    leans
    -1.92
    uador
    -1.89
     peppers
    -1.87
    achus
    -1.85
     sidx
    -1.84
     uncover
    -1.84
    POSITIVE LOGITS
    Picture
    2.53
     Picture
    2.49
    Image
    2.42
    Example
    2.18
    viation
    2.17
     Firstly
    2.12
     CV
    2.08
     QC
    2.07
    ploma
    2.05
     Solution
    1.99
    Act Density 0.002%

    No Known Activations