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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "caught"

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

    being caught

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    räume
    -0.43
    SMO
    -0.43
    GeoNames
    -0.42
    ila
    -0.42
     mão
    -0.42
    y
    -0.41
    osi
    -0.41
    rendon
    -0.40
     نوف
    -0.40
    ML
    -0.40
    POSITIVE LOGITS
     caught
    2.06
    caught
    1.85
    Caught
    1.84
     Caught
    1.84
     catch
    1.65
     Catch
    1.58
    catch
    1.52
     catching
    1.46
     catches
    1.45
    Catch
    1.45
    Act Density 0.003%

    No Known Activations