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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting used in programming or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.00
     HasFactory
    -0.87
    tanleria
    -0.78
     Roskov
    -0.76
    Personendaten
    -0.76
     nakalista
    -0.75
    帖最后由
    -0.75
     للمعارف
    -0.74
     Савезне
    -0.73
     Majefty
    -0.70
    POSITIVE LOGITS
    </b>
    0.52
    )
    0.46
    ’
    0.43
    </i>
    0.42
    }
    0.42
    </h3>
    0.41
    0.41
    '
    0.38
    </sup>
    0.38
    ↵↵
    0.37
    Act Density 0.001%
    No Known Activations