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

    Neuronpedia

    INDEX
    Explanations

    specialized formatting or syntactical elements in text, such as mathematical symbols or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    хьтан
    -0.82
     oprot
    -0.81
     виправивши
    -0.77
    Vidite
    -0.75
    prefixer
    -0.73
     Мексичка
    -0.72
     OnDestroy
    -0.72
    ticulture
    -0.71
     Wither
    -0.70
     Italijani
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.92
    ↵↵↵
    0.86
    </blockquote>
    0.81
    ↵↵↵↵↵
    0.79
    ↵
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
    </tr>
    0.75
    ↵↵↵↵↵↵↵
    0.74
    ↵↵↵↵↵↵
    0.74
    );
    0.72
    Act Density 0.094%

    No Known Activations