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

    Neuronpedia

    INDEX
    Explanations

    the usage of contraction forms of "do" in a conversational context

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

    word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     G
    -0.43
    G
    -0.41
    M
    -0.38
     
    -0.36
    keur
    -0.34
    ho
    -0.34
    h
    -0.34
     R
    -0.33
    ={},
    -0.33
    vi
    -0.33
    POSITIVE LOGITS
     kasarigan
    0.73
    httphttps
    0.70
    oredCriteria
    0.68
    évaluateur
    0.66
     ویکی‌پدی
    0.65
    Personendaten
    0.62
     насељу
    0.60
    WebElementEntity
    0.59
     препратки
    0.58
     beginnetje
    0.57
    Act Density 0.003%

    No Known Activations