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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating references or specifications to groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Micah
    -0.78
     écou
    -0.75
     ['./
    -0.75
    ocarp
    -0.74
    Micah
    -0.71
    IsPostBack
    -0.71
    Jum
    -0.67
     Berthe
    -0.66
     caul
    -0.66
    AndEndTag
    -0.65
    POSITIVE LOGITS
     those
    2.01
    Those
    1.81
    those
    1.76
     Those
    1.71
     THOSE
    1.56
     aquellos
    1.27
    那些
    1.23
     aqueles
    1.17
     ceux
    1.15
     Ceux
    1.10
    Act Density 0.087%

    No Known Activations