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

    Neuronpedia

    INDEX
    Explanations

    references to academic programs and courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï
    -0.19
    å
    -0.17
     Cheat
    -0.15
    ladu
    -0.15
     NÄĽkter
    -0.15
    malar
    -0.15
    ël
    -0.15
    olla
    -0.14
    ávat
    -0.14
    urus
    -0.14
    POSITIVE LOGITS
     Brno
    0.23
     âĢŀ
    0.21
     Czech
    0.20
     Boh
    0.19
     Slovak
    0.19
     Velvet
    0.19
     PlzeÅĪ
    0.19
     cca
    0.18
    .cz
    0.18
     Prague
    0.17
    Act Density 0.055%

    No Known Activations