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

    Neuronpedia

    INDEX
    Explanations

    conclusions or logical transitions in the text

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

    conclusive transition words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.70
    BeginContext
    -0.60
    richTextPanel
    -0.59
     estekak
    -0.56
    findpost
    -0.56
    writeFieldEnd
    -0.54
    BibitemShut
    -0.53
    thâu
    -0.52
     nakalista
    -0.52
    CodedInputStream
    -0.51
    POSITIVE LOGITS
     Therefore
    0.65
     therefore
    0.60
    Therefore
    0.59
     Hence
    0.59
    So
    0.59
     So
    0.59
    Hence
    0.57
     Somit
    0.57
     pertanto
    0.54
     hence
    0.53
    Act Density 0.070%

    No Known Activations