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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and the creation of artistic or scholarly works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     должна
    -0.27
     titul
    -0.27
     ÑģÑĤала
    -0.26
     бÑĭла
    -0.26
     herself
    -0.25
     italiana
    -0.24
     envi
    -0.23
     españ
    -0.23
     utiliz
    -0.22
     могла
    -0.22
    POSITIVE LOGITS
    ido
    0.30
    ificado
    0.29
    gado
    0.29
    ulado
    0.28
    erto
    0.28
    edido
    0.28
    rito
    0.27
    izzato
    0.27
    ativo
    0.26
    izado
    0.26
    Act Density 0.120%

    No Known Activations