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

    Neuronpedia

    INDEX
    Explanations

    references to various cultural or societal norms and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -1.07
     дописавши
    -0.94
    。】
    -0.87
     الرياضيه
    -0.85
    ！】
    -0.83
    ？】
    -0.77
    .)}
    -0.77
    ）』
    -0.75
     bezeichneter
    -0.74
     “
    -0.73
    POSITIVE LOGITS
    ”
    1.88
    "
    1.72
    」
    1.70
    ",
    1.57
    ”,
    1.50
    ''
    1.43
    ’’
    1.42
    ".
    1.31
    ”.
    1.30
    ',
    1.21
    Act Density 0.520%

    No Known Activations