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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity or diversity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ax
    -0.14
    linkplain
    -0.14
    ibri
    -0.14
     Rubin
    -0.13
    boxed
    -0.13
    fty
    -0.13
    ìķł
    -0.13
     Demir
    -0.13
    uty
    -0.13
    lsi
    -0.13
    POSITIVE LOGITS
     stripes
    0.18
    acles
    0.18
     ages
    0.17
     stripe
    0.16
    isha
    0.15
    ensch
    0.15
    isser
    0.15
     sorts
    0.14
     age
    0.14
    573
    0.14
    Act Density 0.022%

    No Known Activations