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

    Neuronpedia

    INDEX
    Explanations

    the presence of formatting and structural elements in text, particularly beginning and ending markers or specific symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ";
    -0.60
    ';
    -0.57
    ".
    -0.54
    ”;
    -0.54
    "
    -0.53
    ];
    -0.52
    ”.
    -0.51
    ’;
    -0.49
    ’.
    -0.47
    ."
    -0.47
    POSITIVE LOGITS
     дописавши
    1.00
    IsContent
    1.00
    BeginContext
    0.95
     ModelExpression
    0.89
     Infórmanos
    0.88
    Autoritní
    0.87
     насељу
    0.87
     Normdatei
    0.87
    ⓧ
    0.87
     resourceCulture
    0.84
    Act Density 0.097%

    No Known Activations