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

    Neuronpedia

    INDEX
    Explanations

    references to political movements and self-determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utral
    -0.16
    presso
    -0.15
    HF
    -0.15
    ãĥ©ãĥ¼
    -0.15
    istrovstvÃŃ
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    ucas
    -0.13
    Ĥæķ°
    -0.13
     desi
    -0.13
    znam
    -0.13
    POSITIVE LOGITS
     Catal
    0.35
     Catalan
    0.34
     Catalonia
    0.30
     Pu
    0.30
     separat
    0.28
     catal
    0.27
     independence
    0.27
     se
    0.25
     Pod
    0.24
     Jord
    0.23
    Act Density 0.007%

    No Known Activations