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

    Neuronpedia

    INDEX
    Explanations

    expressions and structures involving the number two

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.80
     Jefus
    -0.79
     Efq
    -0.76
     ſeveral
    -0.76
    ſelves
    -0.72
     houſe
    -0.72
     ―――――
    -0.72
     wireType
    -0.71
     purpoſe
    -0.70
     allemaal
    -0.70
    POSITIVE LOGITS
     Two
    1.01
     duo
    1.00
     two
    0.99
    Two
    0.92
    two
    0.92
     beiden
    0.92
    Zwei
    0.90
     Both
    0.87
     dua
    0.87
     dupla
    0.86
    Act Density 1.317%

    No Known Activations