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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and their corresponding properties for formatting documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.07
     Shakspeare
    -1.01
     '\\;'
    -1.00
     ―――――
    -0.99
     itſelf
    -0.98
     Monfieur
    -0.97
    WriteTagHelper
    -0.92
     Theſe
    -0.90
     iſt
    -0.90
     myſelf
    -0.90
    POSITIVE LOGITS
     \
    0.92
    \
    0.76
     
    0.73
     $\
    0.67
    <eos>
    0.67
     T
    0.66
     {\
    0.61
    </tr>
    0.61
    ↵↵
    0.60
     S
    0.59
    Act Density 0.098%

    No Known Activations