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

    Neuronpedia

    INDEX
    Explanations

    instances of special tokens or markers indicating the beginning or end of a segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.06
    Personendaten
    -0.99
     nakalista
    -0.89
     AssemblyCulture
    -0.88
    Autoritní
    -0.86
    IsMutable
    -0.86
    yntaxException
    -0.85
     Савезне
    -0.83
    aarrggbb
    -0.83
     defaultstate
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.55
    <eos>
    0.49
    ↵↵↵
    0.48
     affatto
    0.48
    ’
    0.46
    0.45
    ور
    0.43
    <blockquote>
    0.42
     jeb
    0.42
    ‍
    0.42
    Act Density 0.160%
    No Known Activations