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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation related to proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.01
     myſelf
    -0.99
     Theſe
    -0.95
    ItemBackground
    -0.94
     themſelves
    -0.91
     Monfieur
    -0.91
     pleaſure
    -0.90
     ―――――
    -0.86
     Efq
    -0.85
     purpoſe
    -0.85
    POSITIVE LOGITS
     $\
    1.59
     $
    0.71
     ${
    0.69
    $\
    0.69
     _
    0.62
     \
    0.61
    Â
    0.60
     
    0.60
     â
    0.59
     $(
    0.59
    Act Density 0.201%

    No Known Activations