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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    şti
    -0.54
     RSSSF
    -0.52
    initComponents
    -0.51
     citoy
    -0.51
     dentaire
    -0.50
    bleau
    -0.50
     trasparente
    -0.50
     pério
    -0.49
     fevere
    -0.49
     Gobernador
    -0.49
    POSITIVE LOGITS
     either
    1.26
    either
    1.18
    owohl
    1.05
     entweder
    1.04
     Either
    1.04
    ITHER
    1.01
     both
    0.99
    Either
    0.98
     Both
    0.88
    weder
    0.85
    Act Density 0.526%

    No Known Activations