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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating degrees or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ίος
    -0.61
     in
    -0.59
    (@"%@",
    -0.57
    ,
    -0.54
    GEBURTSDATUM
    -0.52
     oma
    -0.52
    unif
    -0.51
    Халык
    -0.51
    خرى
    -0.50
    .
    -0.50
    POSITIVE LOGITS
     amount
    0.96
    ^(@)
    0.92
     amounts
    0.90
     cantidad
    0.87
     quantidade
    0.83
    Aiheesta
    0.83
     ſeveral
    0.82
     ſever
    0.80
     leaſt
    0.80
    ousands
    0.79
    Act Density 0.493%

    No Known Activations