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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and human connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.54
    ########.
    -0.50
     grandparents
    -0.47
     Catan
    -0.46
     mechanically
    -0.46
    ボン
    -0.45
     predecessors
    -0.45
     godfather
    -0.44
     scribe
    -0.44
     tío
    -0.44
    POSITIVE LOGITS
     سكانية
    0.81
    новниш
    0.75
    ViewFeatures
    0.74
     humaines
    0.71
    TagMode
    0.69
    tanleria
    0.69
     userSchema
    0.66
     humaine
    0.65
     Demographics
    0.65
    Население
    0.65
    Act Density 1.205%

    No Known Activations