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

    Neuronpedia

    INDEX
    Explanations

    verbs associated with creation or improvement

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

    cause or create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سكانية
    -0.63
    Datuak
    -0.63
    vician
    -0.50
    RegressionTest
    -0.49
    Personensuche
    -0.47
    Хьажоргаш
    -0.46
    ThroughAttribute
    -0.45
    Chham
    -0.45
     ſche
    -0.44
    getStringExtra
    -0.44
    POSITIVE LOGITS
    make
    0.52
     make
    0.52
     made
    0.49
     Making
    0.48
     making
    0.47
     Make
    0.46
    씀
    0.46
    GenerationType
    0.45
     membuatnya
    0.44
    使其
    0.44
    Act Density 0.036%

    No Known Activations