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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and its variations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.75
     '\\;'
    -0.66
     ++)
    -0.64
    numerusform
    -0.63
    ftagPool
    -0.61
     fièvre
    -0.56
    :][
    -0.56
     simak
    -0.56
     للاسماء
    -0.56
    +#+
    -0.55
    POSITIVE LOGITS
     section
    0.79
     paper
    0.72
     chapter
    0.70
     document
    0.65
     appendix
    0.60
    tableFuture
    0.59
    Neste
    0.57
     report
    0.57
     JpaRepository
    0.56
     paragraph
    0.55
    Act Density 0.431%

    No Known Activations