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

    Neuronpedia

    INDEX
    Explanations

    connections and conjunctions in the text

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

    Follows conjunctions/transition words

    np_acts-logits-general · gemini-2.0-flash

    especially, according, essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fö
    -0.50
     cr
    -0.50
    ceğim
    -0.50
    albeit
    -0.48
     становника
    -0.48
    TextHelper
    -0.48
     Malo
    -0.48
     Josiah
    -0.48
    Eloquent
    -0.48
     Comprometido
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.70
     also
    0.64
     autorytatywna
    0.61
    WriteLiteral
    0.59
     مرئيه
    0.58
    zent
    0.57
    IContainer
    0.56
     finally
    0.55
     nadie
    0.54
    WithIOException
    0.54
    Act Density 0.033%

    No Known Activations