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

    Neuronpedia

    INDEX
    Explanations

    percentage figures related to survey responses or data outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.61
     @"/
    -0.57
     correspondance
    -0.55
     maternelle
    -0.54
    basicConfig
    -0.53
     représ
    -0.53
     Czechos
    -0.52
    </tfoot>
    -0.51
     Monfieur
    -0.50
     hygien
    -0.50
    POSITIVE LOGITS
    %)
    1.29
     \%)$
    1.18
    \%)
    1.12
     %)
    1.09
    %),
    0.98
    %]
    0.97
    %")
    0.88
    GraphicsUnit
    0.87
    %)$
    0.86
    %).
    0.83
    Act Density 0.110%

    No Known Activations