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

    Neuronpedia

    INDEX
    Explanations

    different types of quotation marks or apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __).
    -0.69
     descar
    -0.66
    IGraphics
    -0.66
     compro
    -0.63
    "
    -0.61
    LayoutConstraint
    -0.60
    **
    -0.57
    

    -0.56
    ════
    -0.56
     mantel
    -0.56
    POSITIVE LOGITS
     '
    1.19
     ‘
    1.13
     ’
    0.99
     ‚
    0.94
     (‘
    0.93
    -'
    0.89
    ‗
    0.85
     jLabel
    0.83
     `
    0.83
     ('
    0.83
    Act Density 0.123%

    No Known Activations