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

    Neuronpedia

    INDEX
    Explanations

    references to dancing and dance-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mögens
    -0.80
    waltung
    -0.73
     Malfoy
    -0.73
     shewn
    -0.72
    riwal
    -0.71
    sstelle
    -0.69
    RTLE
    -0.68
    iarkan
    -0.67
    FieldNumber
    -0.67
     lakhs
    -0.66
    POSITIVE LOGITS
     dance
    1.91
     Dance
    1.73
     dancing
    1.73
     danced
    1.72
     dances
    1.62
    Dance
    1.59
     DANCE
    1.58
     Dancing
    1.57
    dancing
    1.49
    dance
    1.48
    Act Density 0.085%

    No Known Activations