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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connecting phrases that indicate relationships between ideas or clauses

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

    connecting words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁣
    -0.88
    Personendaten
    -0.87
    Datuak
    -0.77
    ſſung
    -0.76
    ftagPool
    -0.75
    ésultats
    -0.73
     Paglinawan
    -0.73
    rungsseite
    -0.72
    <unused8>
    -0.71
    <unused16>
    -0.71
    POSITIVE LOGITS
    .
    0.49
    <strong>
    0.37
    <h4>
    0.36
    //
    0.36
    　
    0.36
     //
    0.36
    PE
    0.34
    pe
    0.34
    W
    0.33
    ."
    0.33
    Act Density 0.081%

    No Known Activations