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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" indicating time or location

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

    time indications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.43
     kaarangay
    -0.42
    ########.
    -0.42
    ]--;
    -0.41
    WriteLiteral
    -0.41
     disambiguazione
    -0.41
     ſp
    -0.41
    BIÉN
    -0.41
    campal
    -0.41
    paedia
    -0.40
    POSITIVE LOGITS
     at
    0.99
     At
    0.54
    indd
    0.52
    At
    0.52
     tại
    0.51
    LookAnd
    0.48
    adaptiveStyles
    0.48
    at
    0.47
    oneofs
    0.43
    RegressionTest
    0.42
    Act Density 0.049%

    No Known Activations