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

    Neuronpedia

    INDEX
    Explanations

    references to statistical coefficients in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gubernur
    -0.56
     createState
    -0.55
     évêque
    -0.55
    TableAdapter
    -0.55
     musuh
    -0.53
    hålla
    -0.52
     wijn
    -0.52
     isolado
    -0.51
    envolvimento
    -0.51
     chrétien
    -0.50
    POSITIVE LOGITS
     blank
    0.71
     Blank
    0.69
    Blank
    0.63
    blank
    0.61
     blanks
    0.58
     essay
    0.57
     BLANK
    0.52
     Essay
    0.52
     waters
    0.51
     Commissioner
    0.51
    Act Density 0.107%

    No Known Activations