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

    Neuronpedia

    INDEX
    Explanations

    references to literary and cultural figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.16
     سÙĨت
    -0.16
    isin
    -0.15
    388
    -0.15
    izzo
    -0.15
     motel
    -0.14
    uzzi
    -0.14
    UTE
    -0.14
    esign
    -0.14
    345
    -0.14
    POSITIVE LOGITS
     Hogwarts
    0.25
     Dumbledore
    0.22
     Voldemort
    0.21
     Harry
    0.21
    Harry
    0.19
     Rowling
    0.19
     Potter
    0.19
     Snape
    0.18
     HP
    0.17
    foy
    0.17
    Act Density 0.022%

    No Known Activations