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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auctor
    -0.64
     attravers
    -0.61
     muzzle
    -0.60
     suspens
    -0.59
     каждо
    -0.58
     innamor
    -0.58
     formales
    -0.57
    Geschiedenis
    -0.56
     büyü
    -0.56
     Utilisez
    -0.56
    POSITIVE LOGITS
     nakalista
    0.93
    +#+#
    0.92
    ViewFeatures
    0.90
    ății
    0.83
    abetes
    0.83
    μβρίου
    0.83
    tableFuture
    0.78
    vábbi
    0.78
    TagMode
    0.74
     NSCoder
    0.73
    Act Density 0.100%

    No Known Activations