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

    Neuronpedia

    INDEX
    Explanations

    special formatted tokens or escape sequences in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithMany
    -0.81
     CWE
    -0.74
    DeleteBehavior
    -0.71
    Népesség
    -0.68
    исленность
    -0.66
     otomatig
    -0.66
    RTEX
    -0.65
    isição
    -0.64
    aarrggbb
    -0.64
     هيا
    -0.60
    POSITIVE LOGITS
     ***!
    0.70
    \{\\
    0.69
    typeorm
    0.68
    </h5>
    0.67
    </h6>
    0.67
    </blockquote>
    0.63
     autorytatywna
    0.63
     חיצוניים
    0.63
    </caption>
    0.62
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.62
    Act Density 0.261%

    No Known Activations