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

    Neuronpedia

    INDEX
    Explanations

    references to formal mathematical statements and components of theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Origem
    -0.57
     Dix
    -0.53
     الأصل
    -0.51
    OLOGIES
    -0.51
    freund
    -0.50
    fortawesome
    -0.50
     ModelExpression
    -0.50
     Weiter
    -0.50
     MAG
    -0.50
    rigin
    -0.49
    POSITIVE LOGITS
    Theorem
    1.63
     Theorem
    1.42
     theorem
    1.41
    THEOREM
    1.25
    Lemma
    1.19
     theorems
    1.18
    theorem
    1.14
     THEOREM
    1.06
     Theorems
    1.02
    Corollary
    1.00
    Act Density 0.319%

    No Known Activations