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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and connections, particularly through prepositions and conjunctions

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

    "of"

    np_acts-logits-general · gemini-2.0-flash

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſicht
    -0.82
    ésultats
    -0.78
    iſche
    -0.76
    iſchen
    -0.76
    ſehen
    -0.71
    <unused14>
    -0.71
    <unused43>
    -0.71
    <unused8>
    -0.71
    [@BOS@]
    -0.71
    <unused3>
    -0.71
    POSITIVE LOGITS
     of
    0.48
     this
    0.36
    setof
    0.32
    式の
    0.30
     on
    0.30
    nameof
    0.30
     your
    0.30
     that
    0.30
     eben
    0.30
    unistd
    0.28
    Act Density 1.407%

    No Known Activations