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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases involving the word "to" in various contexts

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

    infinitive verb phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.76
     Roskov
    -0.66
    ftagPool
    -0.63
    +#+#
    -0.62
     ExecuteAsync
    -0.60
    sizeCache
    -0.59
    httphttps
    -0.59
    Hochspringen
    -0.57
     تضيفلها
    -0.56
    UserScript
    -0.55
    POSITIVE LOGITS
    <strong>
    0.47
    <eos>
    0.45
     Lutz
    0.44
     Hecht
    0.42
    ↵↵↵
    0.42
    <h3>
    0.42
     Gug
    0.41
     Connell
    0.41
     Persson
    0.40
     Apakah
    0.40
    Act Density 0.080%

    No Known Activations