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

    Neuronpedia

    INDEX
    Explanations

    text discussing conditions or statements relating to probabilities and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.32
     tibur
    -0.31
     tournage
    -0.31
     متحده
    -0.30
     ambassade
    -0.28
     âmes
    -0.28
     mierda
    -0.28
     instead
    -0.27
     igjen
    -0.27
     Selección
    -0.27
    POSITIVE LOGITS
    цездатний
    0.96
    참고
    0.81
    complexContent
    0.77
    oredCriteria
    0.73
    ValueGenerated
    0.73
    NamedQueries
    0.71
     iconLine
    0.68
    modelBuilder
    0.66
     EconPapers
    0.65
    findpost
    0.65
    Act Density 1.858%

    No Known Activations