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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative sentiment towards authority or systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ureau
    -0.16
    Ø´ÙħاÙĦÛĮ
    -0.15
    ÙĪار
    -0.15
     ahead
    -0.15
     trừ
    -0.14
    icc
    -0.14
    icers
    -0.14
    ĮĢ
    -0.14
    205
    -0.13
    iola
    -0.13
    POSITIVE LOGITS
     mass
    0.24
     masses
    0.23
     Massive
    0.21
     reaching
    0.20
    mass
    0.20
     Reach
    0.20
    reach
    0.20
     Mass
    0.20
     reach
    0.19
     massive
    0.19
    Act Density 0.027%

    No Known Activations