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

    Neuronpedia

    INDEX
    Explanations

    punctuation and demarcation in the text

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

    Text following commas and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.56
     Chwiliwch
    -0.53
     auffi
    -0.46
     propter
    -0.45
     createState
    -0.45
     stället
    -0.45
    HasForeignKey
    -0.44
    『
    -0.43
    WSGI
    -0.43
    äsentation
    -0.42
    POSITIVE LOGITS
     however
    1.26
     }}$,
    1.07
     which
    1.06
     including
    1.04
     though
    0.99
    ,-,
    0.96
     but
    0.96
     etc
    0.94
     albeit
    0.94
    ?,?,
    0.93
    Act Density 2.721%

    No Known Activations