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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts

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

    "As" followed by "well", "it", or "a"

    np_acts-logits-general · gemini-2.0-flash

    as well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.60
    ConstraintMaker
    -0.57
    ⓧ
    -0.56
    CppCodeGen
    -0.51
     وتسجيلات
    -0.49
    SourceChecksum
    -0.46
    RTHOOK
    -0.45
     CreateTagHelper
    -0.44
    сылкі
    -0.43
    archiviato
    -0.43
    POSITIVE LOGITS
     >=",
    0.55
     part
    0.45
     accessory
    0.45
     collateral
    0.45
    openConnection
    0.44
    accessory
    0.44
    łosi
    0.42
     distraction
    0.42
    FO
    0.42
    cos
    0.42
    Act Density 0.248%

    No Known Activations