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

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to overwriting or updating data

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

    overwriting or replacing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestBed
    -0.43
    XmlType
    -0.39
    amazonaws
    -0.38
    憬
    -0.38
    PerformLayout
    -0.37
    OGND
    -0.37
    aunt
    -0.37
    -0.37
    jface
    -0.36
    akaan
    -0.35
    POSITIVE LOGITS
     overwrite
    0.49
     overwritten
    0.49
     obliterated
    0.47
     antaranya
    0.46
    webElementXpaths
    0.45
    DeleteMapping
    0.45
     obliter
    0.45
    overwrite
    0.44
     erased
    0.44
     deleting
    0.41
    Act Density 0.214%

    No Known Activations