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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating causation or reasoning

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

    Sentences beginning with "because", "as", or "since"

    np_acts-logits-general · gemini-2.0-flash

    expressing reasonscausal conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.57
    ArgumentParser
    -0.56
    WireFormatLite
    -0.55
    RectangleBorder
    -0.54
    ResponseWriter
    -0.52
    mybatisplus
    -0.51
    dflare
    -0.50
    MenuInflater
    -0.49
     springfox
    -0.48
    IContainer
    -0.47
    POSITIVE LOGITS
     because
    0.59
     çünkü
    0.57
     deoarece
    0.54
     fordi
    0.53
     porque
    0.53
     poiché
    0.53
     چون
    0.51
     زیرا
    0.50
     क्योंकि
    0.50
    because
    0.49
    Act Density 0.621%

    No Known Activations