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

    Neuronpedia

    INDEX
    Explanations

    references to legal or academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jména
    -0.46
     cerimonia
    -0.42
     hjelp
    -0.39
     politiet
    -0.39
     kvinder
    -0.38
     héroe
    -0.38
     ín
    -0.37
     duros
    -0.36
     fjor
    -0.36
     avancée
    -0.36
    POSITIVE LOGITS
    aga
    0.54
    asser
    0.54
    ager
    0.54
    lab
    0.53
    itt
    0.53
    yszcz
    0.53
    rub
    0.52
    itter
    0.52
    rab
    0.52
    ull
    0.52
    Act Density 0.427%

    No Known Activations