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

    Neuronpedia

    INDEX
    Explanations

    modifiers or adverbs related to uncertainty or possibility

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

    auxiliary verbs and question words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſicht
    -1.04
    [@BOS@]
    -1.02
    <unused14>
    -1.02
    <unused42>
    -1.02
    <unused74>
    -1.02
    <pad>
    -1.02
    <unused8>
    -1.02
    <unused41>
    -1.02
    ésultats
    -1.02
    <unused28>
    -1.02
    POSITIVE LOGITS
    ,
    0.52
     lendemain
    0.40
    Meanwhile
    0.40
     mientras
    0.39
    while
    0.37
     Meanwhile
    0.36
     Wednesday
    0.36
    ;
    0.36
     miércoles
    0.36
    ?,
    0.34
    Act Density 0.081%

    No Known Activations