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

    Neuronpedia

    INDEX
    Explanations

    references to masks and mask mandates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anova
    -0.15
    illis
    -0.15
    PasswordEncoder
    -0.15
    ixer
    -0.15
    essed
    -0.14
    tvrt
    -0.14
    ision
    -0.14
     Gran
    -0.14
    oen
    -0.14
    egl
    -0.14
    POSITIVE LOGITS
    дÑı
    0.17
     worn
    0.15
    gebra
    0.15
    vation
    0.14
     whenever
    0.14
     dici
    0.14
     درÛĮ
    0.14
    peaker
    0.13
    ylon
    0.13
    -sur
    0.13
    Act Density 0.016%

    No Known Activations