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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.81
     …
    -0.74
    …”
    -0.73
    ‘’
    -0.72
    …’
    -0.70
     ‘’
    -0.69
     ’
    -0.68
     
    -0.67
    �
    -0.67
     #
    -0.66
    POSITIVE LOGITS
     $\$
    1.55
     \&
    1.43
    \&
    1.28
     $=$
    1.26
    \_
    1.24
     $\
    1.20
    .\\
    1.20
     $\&$
    1.20
     $=\
    1.18
     \#
    1.18
    Act Density 0.673%

    No Known Activations