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

    Neuronpedia

    INDEX
    Explanations

    negative statements or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    věř
    -0.67
    ing
    -0.66
    PAGER
    -0.62
    reif
    -0.61
     wł
    -0.61
     igång
    -0.60
    duire
    -0.59
    Swift
    -0.58
     sexta
    -0.58
     merid
    -0.57
    POSITIVE LOGITS
    новништво
    0.98
    evos
    0.90
     سكانية
    0.89
     tartalomajánló
    0.88
     Dons
    0.87
     do
    0.87
     Moulton
    0.86
     Does
    0.85
    evsky
    0.85
    retum
    0.84
    Act Density 0.160%

    No Known Activations