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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "built."

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

    built-in construction origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sereia
    -0.58
    WireFormatLite
    -0.58
    atoare
    -0.53
     Kramer
    -0.51
     Shaffer
    -0.51
     Rhapsody
    -0.50
    hapsody
    -0.50
    czaj
    -0.49
     Amiens
    -0.48
    aronder
    -0.48
    POSITIVE LOGITS
    Built
    1.94
     Built
    1.94
     built
    1.90
    built
    1.82
     BUILT
    1.68
    BUILT
    1.60
     construido
    1.13
    build
    1.08
     buil
    1.07
     build
    1.05
    Act Density 0.008%

    No Known Activations