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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that express strong emotions or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .",
    -0.81
    \",
    -0.79
     ]
    -0.75
    "=>"
    -0.75
    ]").
    -0.74
    ,}
    -0.73
    "],
    -0.73
    ".
    -0.73
    */,
    -0.73
    "]/
    -0.73
    POSITIVE LOGITS
    ?!
    0.70
    ?!?!
    0.66
    ?!?
    0.63
    rrrrr
    0.62
    ??
    0.59
     environments
    0.58
    rrrrrr
    0.58
    !?
    0.58
    ↵↵↵↵↵↵
    0.58
     للاسماء
    0.58
    Act Density 0.108%

    No Known Activations