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

    Neuronpedia

    INDEX
    Explanations

    the presence and frequency of the word "are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zieży
    -0.74
     verksamhet
    -0.67
    σία
    -0.67
     stuff
    -0.64
     neuem
    -0.64
     weevil
    -0.62
     lèvres
    -0.61
    compos
    -0.61
    Stuff
    -0.60
    protos
    -0.59
    POSITIVE LOGITS
     few
    1.11
    úgó
    1.00
     many
    0.99
     MANY
    0.96
     fewer
    0.92
    MANY
    0.92
     Meksiku
    0.91
     Fewer
    0.89
    TagMode
    0.89
    few
    0.86
    Act Density 0.080%

    No Known Activations