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

    Neuronpedia

    INDEX
    Explanations

    isolated or standalone punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -1.00
     autorytatywna
    -0.90
    TagMode
    -0.83
    :✨
    -0.81
    IndentedString
    -0.79
    richTextPanel
    -0.76
     Roskov
    -0.74
    AxisAlignment
    -0.73
    Personendaten
    -0.73
    migrationBuilder
    -0.73
    POSITIVE LOGITS
    </em>
    0.55
    —
    0.54
    …
    0.51
     ‘
    0.51
     ’
    0.47
     su
    0.47
     مج
    0.47
    ,
    0.47
     sich
    0.45
    </i>
    0.45
    Act Density 0.017%

    No Known Activations