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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the significance or value of different subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.63
     beginnetje
    -0.63
    TagMode
    -0.62
    JspWriter
    -0.58
    hynchus
    -0.56
     Италијани
    -0.55
    setVerticalGroup
    -0.54
    lccn
    -0.53
     ComVisible
    -0.53
    transQ
    -0.52
    POSITIVE LOGITS
     importance
    1.73
     value
    1.69
     relevance
    1.63
     significance
    1.61
    importance
    1.41
    value
    1.30
     Importance
    1.30
    relevance
    1.29
     Value
    1.26
     Significance
    1.24
    Act Density 0.613%

    No Known Activations