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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and elements of optionality in instructions

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

    start of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.95
    principalColumn
    -0.79
    SharedCtor
    -0.72
    kháu
    -0.69
     EconPapers
    -0.68
    Rhestr
    -0.68
     queſta
    -0.68
    ngdoc
    -0.68
     surla
    -0.67
    StoryboardSegue
    -0.66
    POSITIVE LOGITS
     initial
    0.43
    первых
    0.40
    Initial
    0.40
     early
    0.39
     preliminary
    0.38
     pré
    0.38
     preamble
    0.38
     initially
    0.37
     erstmal
    0.37
     prologue
    0.36
    Act Density 0.109%

    No Known Activations