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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases focused on the concept of "how."

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

    Comes after "how" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    degree or surprise expressed with "how"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.58
    nteral
    -0.53
     Référence
    -0.47
    XSSF
    -0.46
    ágos
    -0.45
     entière
    -0.43
     szolg
    -0.43
    μεν
    -0.42
    <bos>
    -0.42
     neutralization
    -0.42
    POSITIVE LOGITS
     much
    0.93
     incredibly
    0.84
     amazing
    0.82
     Administrativna
    0.78
     lucky
    0.78
     awesome
    0.78
     far
    0.77
     they
    0.74
     incredible
    0.74
     "..\..\..\
    0.73
    Act Density 0.062%

    No Known Activations