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

    Neuronpedia

    INDEX
    Explanations

    technical terms and metrics associated with parameter settings and thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     precedenti
    -0.52
     verlä
    -0.41
    mensa
    -0.41
     Ful
    -0.41
    jooq
    -0.39
    sptr
    -0.38
     Bef
    -0.38
    ografija
    -0.38
    жества
    -0.37
    ("]");
    -0.37
    POSITIVE LOGITS
    WriteTagHelper
    0.77
    tagHelperRunner
    0.75
    djangoproject
    0.72
     JpaRepository
    0.69
     Monfieur
    0.67
     rechange
    0.65
     دیکھیے
    0.64
    ArrowToggle
    0.64
    rishnan
    0.64
     оригіналу
    0.63
    Act Density 0.858%

    No Known Activations