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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and connections between two or more entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allemaal
    -1.06
    ſelf
    -0.88
    ſelves
    -0.87
     للاسماء
    -0.86
     Efq
    -0.85
     Theſe
    -0.85
     ſeveral
    -0.84
     Jefus
    -0.83
     itſelf
    -0.83
     purpoſe
    -0.81
    POSITIVE LOGITS
     two
    1.06
     Both
    0.99
     Two
    0.95
    Both
    0.94
     both
    0.93
     beiden
    0.92
    Two
    0.88
     Beide
    0.86
    two
    0.86
     duo
    0.85
    Act Density 1.187%

    No Known Activations