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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sucesor
    -0.69
     vorticity
    -0.60
     insec
    -0.59
     poussière
    -0.59
     Israël
    -0.58
     antenn
    -0.57
     idiota
    -0.57
     iguana
    -0.56
     autorité
    -0.56
     indiqué
    -0.55
    POSITIVE LOGITS
     a
    1.17
     few
    1.09
     large
    1.03
     different
    1.02
     great
    1.01
     larger
    0.99
    {}",
    0.94
     new
    0.93
     huge
    0.93
     very
    0.91
    Act Density 1.204%

    No Known Activations