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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.54
     you
    -0.53
     itself
    -0.53
     that
    -0.52
     AssemblyVersion
    -0.51
     anyone
    -0.50
    oop
    -0.46
     оригіналу
    -0.46
     AssemblyCompany
    -0.45
    setContentView
    -0.45
    POSITIVE LOGITS
     el
    1.65
     la
    1.59
     su
    1.17
     los
    1.14
     las
    1.14
     una
    0.95
     ese
    0.93
     esa
    0.90
     este
    0.90
     un
    0.87
    Act Density 0.070%

    No Known Activations