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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the character '{', indicating the beginning of code blocks or structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    function definition start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rechange
    -0.40
     inoxidable
    -0.39
     esternos
    -0.38
    SerializedName
    -0.37
    ormais
    -0.35
     ſur
    -0.35
    sendLog
    -0.35
     violación
    -0.35
     temor
    -0.35
     eliminación
    -0.34
    POSITIVE LOGITS
    :^{
    0.71
    __":
    0.57
     {
    0.56
    ={({
    0.56
    ⎩
    0.56
     confetti
    0.52
     :{
    0.52
     prescri
    0.52
    :{
    0.51
    ?):
    0.51
    Act Density 0.003%

    No Known Activations