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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -1.00
    ⓧ
    -0.91
    الحياه
    -0.88
    Portale
    -0.88
    GEBURTSDATUM
    -0.87
     Савезне
    -0.84
    Personensuche
    -0.82
     Мексичка
    -0.78
    ⓘ
    -0.77
     հղումներ
    -0.75
    POSITIVE LOGITS
    ↵↵
    1.11
    <eos>
    0.63
    ↵↵↵↵
    0.62
     wasn
    0.60
     czego
    0.54
    ↵↵↵
    0.54
    ↵
    0.54
     isn
    0.53
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.51
    __":
    0.50
    Act Density 0.005%

    No Known Activations