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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lack
    -0.72
    Hrsg
    -0.60
    seur
    -0.57
     ri
    -0.56
     ti
    -0.56
     die
    -0.56
     contr
    -0.55
     ter
    -0.54
     er
    -0.54
     supply
    -0.54
    POSITIVE LOGITS
    MessageOf
    0.89
     Infórmanos
    0.79
     cammin
    0.73
    RegressionTest
    0.73
     heilig
    0.72
     enfans
    0.72
     >=",
    0.72
     Juifs
    0.72
    Gemeinden
    0.72
    HtmlAttribute
    0.72
    Act Density 0.068%

    No Known Activations