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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be", particularly "was" and "were", often in the context of describing past experiences or states.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus

    instances of the verb "to be" in various forms

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

    Following "was" or "were"

    np_acts-logits-general · gemini-2.0-flash

    past states and experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ┐
    -0.42
    Something
    -0.40
     peny
    -0.39
     réalis
    -0.39
     meines
    -0.39
    setupUi
    -0.38
    <bos>
    -0.38
     something
    -0.37
    something
    -0.37
     ángeles
    -0.37
    POSITIVE LOGITS
     transfieras
    0.83
     ujednoznacz
    0.78
     GenerationType
    0.77
     greeted
    0.73
    endphp
    0.71
    WebServlet
    0.70
    หวัด
    0.70
    +#+
    0.70
     mxArray
    0.70
     rewarded
    0.68
    Act Density 0.233%

    No Known Activations