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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to variables and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h6>
    -0.76
    ↵
    -0.75
    </h2>
    -0.72
     $$
    -0.71
    </em>
    -0.70
    </td>
    -0.70
    </th>
    -0.70
     &
    -0.68
     $
    -0.66
    </h5>
    -0.66
    POSITIVE LOGITS
     pleaſure
    1.03
     greateſt
    0.95
     Eſ
    0.94
     beſt
    0.91
     Jefus
    0.90
     poffible
    0.90
     cauſe
    0.89
    NUMX
    0.89
     ſche
    0.88
     juſt
    0.88
    Act Density 0.384%

    No Known Activations