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

    Neuronpedia

    INDEX
    Explanations

    phrases related to raising awareness about various social, health, and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ereotype
    -0.16
    otype
    -0.16
    Ĥ
    -0.15
    ìĸ´
    -0.15
    ÅĻ
    -0.14
    omo
    -0.14
    iska
    -0.14
    iliz
    -0.14
    oples
    -0.14
    endo
    -0.14
    POSITIVE LOGITS
    ness
    0.30
    es
    0.28
    -ra
    0.27
    s
    0.20
    fulness
    0.20
    /alert
    0.20
     rais
    0.19
    (es
    0.19
    nder
    0.18
    nes
    0.18
    Act Density 0.022%

    No Known Activations