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

    Neuronpedia

    INDEX
    Explanations

    punctuation and full stops in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achu
    -0.09
    .CheckedChanged
    -0.08
    “He
    -0.08
    ascus
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
    iyas
    -0.08
     âĨĴ↵↵
    -0.08
    "He
    -0.08
    isel
    -0.08
    леннÑĭй
    -0.08
    POSITIVE LOGITS
     "
    0.12
    “And
    0.09
    "And
    0.09
    “But
    0.09
    "But
    0.09
     "[
    0.08
    "
    0.07
     "(
    0.07
    “That
    0.07
    "That
    0.07
    Act Density 0.038%

    No Known Activations