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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically closing parentheses

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

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.60
    蚪
    -0.54
     gesteld
    -0.52
    withIdentifier
    -0.51
    rmtree
    -0.46
    Filmografie
    -0.46
    Попис
    -0.46
    emplo
    -0.45
    almaz
    -0.45
    setting
    -0.45
    POSITIVE LOGITS
     phone
    0.52
     telephone
    0.47
     telef
    0.45
     phones
    0.45
     telephones
    0.43
     telefon
    0.41
     telepon
    0.41
     Phones
    0.41
     Telephone
    0.40
     Phone
    0.40
    Act Density 0.004%

    No Known Activations