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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to mathematical formulations and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ...
    -0.64
     The
    -0.63
    .
    -0.63
     of
    -0.62
     the
    -0.56
     mene
    -0.55
     :
    -0.54
    ↵
    -0.54
    </blockquote>
    -0.53
     Par
    -0.53
    POSITIVE LOGITS
     itſelf
    1.10
     myſelf
    0.98
     Majefty
    0.92
    ^(@)
    0.91
     Jefus
    0.90
     Anſ
    0.90
     ftate
    0.87
    ſelves
    0.86
     ་་
    0.86
     ſtate
    0.83
    Act Density 0.247%

    No Known Activations