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

    Neuronpedia

    INDEX
    Explanations

    symbols, punctuation, and formatting cues within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ...
    -0.21
    &nbsp
    -0.18
     &#
    -0.18
     ↵↵
    -0.17
    &#
    -0.17
     ↵
    -0.17
     ...↵
    -0.16
    Âł
    -0.16
    ---
    -0.16
     "...
    -0.16
    POSITIVE LOGITS
     Usa
    0.17
    _Api
    0.16
     yourselves
    0.16
     iii
    0.16
     –
    0.15
     ii
    0.15
     vivastreet
    0.15
    _Generic
    0.14
     nevertheless
    0.14
    .–
    0.14
    Act Density 0.003%

    No Known Activations