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

    Neuronpedia

    INDEX
    Explanations

    instances of introductory words and phrases that signal transitions or additions in text

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

    Following an initial word or number

    np_acts-logits-general · gemini-2.0-flash

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.18
     lenker
    -0.97
    jooq
    -0.97
    omock
    -0.97
    الدراسه
    -0.94
    GEBURTSDATUM
    -0.92
     betweenstory
    -0.88
    Cyfeiriadau
    -0.87
    новниш
    -0.86
     nakalista
    -0.86
    POSITIVE LOGITS
    さて
    0.58
    Finally
    0.57
    ................
    0.56
    Also
    0.55
    Another
    0.53
    <eos>
    0.52
    Lastly
    0.52
    Anyway
    0.51
    A
    0.50
    autre
    0.50
    Act Density 0.849%

    No Known Activations