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

    Neuronpedia

    INDEX
    Explanations

    phrases related to normalcy in relationships and the lived experiences of marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
    ectoria
    -0.75
    
    -0.67
    rungsseite
    -0.66
     GenerationType
    -0.61
    UnknownFields
    -0.58
    Slf
    -0.58
    logr
    -0.52
    opsida
    -0.51
    IonicModule
    -0.51
    POSITIVE LOGITS
     normal
    1.06
    normal
    0.96
    Normal
    0.93
     normaux
    0.87
     Normal
    0.87
     ordinary
    0.87
     normaal
    0.87
     normale
    0.87
     conventional
    0.86
    普通の
    0.85
    Act Density 0.324%

    No Known Activations