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

    Neuronpedia

    INDEX
    Explanations

    backslashes and mathematical symbols used in equations or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ❞
    -0.64
    </sub>
    -0.59
    ьте
    -0.58
    "]);
    -0.56
    ?”
    -0.56
    '");
    -0.55
     aard
    -0.55
    ?”.
    -0.53
    ''')
    -0.52
    `);
    -0.52
    POSITIVE LOGITS
     "..\..\..\
    0.92
     autorytatywna
    0.90
     ostavi
    0.86
     betweenstory
    0.85
     &___
    0.82
     "..\..\
    0.79
     صوتيه
    0.79
    riwal
    0.78
    ulemon
    0.78
    InjectAttribute
    0.77
    Act Density 1.284%

    No Known Activations