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

    Neuronpedia

    INDEX
    Explanations

    references to marginalized or vulnerable social groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTYPE
    -0.15
    βά
    -0.15
    clas
    -0.15
     Inflate
    -0.14
    uzzi
    -0.14
    ¼åIJĪ
    -0.14
    &type
    -0.14
    éĻ£
    -0.14
     Dunn
    -0.14
    axe
    -0.14
    POSITIVE LOGITS
    477
    0.17
    /tiny
    0.15
     sector
    0.15
     population
    0.15
     visibility
    0.15
    :numel
    0.15
    772
    0.15
     special
    0.14
     exist
    0.14
     group
    0.14
    Act Density 0.008%

    No Known Activations