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

    Neuronpedia

    INDEX
    Explanations

    references to growth or rising trends in various contexts

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

    increasing change or magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.52
     houſe
    -0.51
    houette
    -0.51
     perſon
    -0.50
     ſche
    -0.49
     FormsModule
    -0.49
    readValue
    -0.48
    AutoresizingMask
    -0.48
     ſub
    -0.47
    Bibliograf
    -0.47
    POSITIVE LOGITS
    increasing
    1.50
    Increasing
    1.48
     Increasing
    1.48
     increasing
    1.47
     decreasing
    1.06
    decreasing
    1.03
     increasingly
    0.95
     crescente
    0.88
     creciente
    0.85
     zuneh
    0.81
    Act Density 0.015%

    No Known Activations