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

    Neuronpedia

    INDEX
    Explanations

    mathematical equivalences or equalities in terms of relationships between expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    =?";
    -0.61
    };*/
    -0.59
    ismen
    -0.56
    zeczytaj
    -0.54
    __':
    -0.53
    ificantly
    -0.52
     caufe
    -0.52
    ;*/
    -0.50
    =*/
    -0.50
    )))));
    -0.49
    POSITIVE LOGITS
    principalTable
    0.60
     naudoti
    0.60
     محفوظة
    0.59
    بوابة
    0.58
     kasarigan
    0.57
    Rüyada
    0.56
     cdti
    0.55
    ждую
    0.54
     ouvertes
    0.54
    equiv
    0.53
    Act Density 0.001%

    No Known Activations