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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to emotional reactions and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.65
    IVEREF
    -0.63
     Мексичка
    -0.59
    titleMargin
    -0.57
    тьяна
    -0.57
     Numerade
    -0.57
    AddTagHelper
    -0.56
     ivelany
    -0.56
     kasarigan
    -0.55
     Himalaya
    -0.55
    POSITIVE LOGITS
     puisque
    0.36
     récomp
    0.36
    !).
    0.33
     potentially
    0.31
    )!
    0.31
     puisqu
    0.31
     enfans
    0.31
     suficientemente
    0.31
     necessariamente
    0.30
    !),
    0.30
    Act Density 0.894%

    No Known Activations