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

    Neuronpedia

    INDEX
    Explanations

    significant words and phrases related to achievement, progress, and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rape
    -0.15
    rael
    -0.15
    pen
    -0.14
    ØŃÙĬ
    -0.14
    ean
    -0.14
    jeta
    -0.14
     Thornton
    -0.14
    RelativeTo
    -0.14
    .il
    -0.13
     stead
    -0.13
    POSITIVE LOGITS
    ensem
    0.16
     verde
    0.15
    arak
    0.14
    inis
    0.14
     Garten
    0.14
    isk
    0.14
    oref
    0.14
     TaÅŁ
    0.13
     Enumerable
    0.13
    ugh
    0.13
    Act Density 1.263%

    No Known Activations