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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and group initiatives related to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tier
    -0.15
    chner
    -0.15
    ÅĻÃŃz
    -0.14
    tout
    -0.14
    zug
    -0.14
    еж
    -0.14
     care
    -0.13
    اخت
    -0.13
    eras
    -0.13
    tod
    -0.13
    POSITIVE LOGITS
     small
    0.21
    small
    0.19
     fewer
    0.18
     nhá»ı
    0.17
    Äįin
    0.16
     smaller
    0.16
     Small
    0.15
     pequ
    0.15
    ÑĨин
    0.15
     niche
    0.15
    Act Density 0.165%

    No Known Activations