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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and other punctuation associated with dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.20
    UserScript
    -1.03
    aarrggbb
    -1.02
    theless
    -1.00
    SpringBootTest
    -0.99
     Berna
    -0.98
     Karak
    -0.97
     Infórmanos
    -0.97
     Monfieur
    -0.97
    ContentAlignment
    -0.96
    POSITIVE LOGITS
     ‚
    0.90
    ‘
    0.87
    ‗
    0.86
     ‘
    0.81
     Pisa
    0.76
    </sub>
    0.76
    </td>
    0.75
    lichen
    0.74
    Hoo
    0.73
     Martens
    0.72
    Act Density 0.112%

    No Known Activations