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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "originally" in various contexts

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

    original intent or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.54
    finally
    -0.54
     finalmente
    -0.54
    eventually
    -0.54
    ついに
    -0.52
     eventualmente
    -0.52
     eventually
    -0.51
     eventual
    -0.51
    SizeMode
    -0.49
     ormai
    -0.49
    POSITIVE LOGITS
     intended
    0.82
     conceived
    0.66
     envisioned
    0.63
     intending
    0.62
     envisaged
    0.60
     Intended
    0.59
     intend
    0.59
    intended
    0.58
     planned
    0.57
     intends
    0.54
    Act Density 0.015%

    No Known Activations