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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hora
    -0.17
    íĤ¹
    -0.15
    /stream
    -0.15
    strap
    -0.15
    /lg
    -0.15
    gens
    -0.14
    rsa
    -0.14
    illac
    -0.14
    (IC
    -0.14
    mania
    -0.14
    POSITIVE LOGITS
    fully
    0.19
    572
    0.17
    enti
    0.15
    entious
    0.15
    ention
    0.15
    werp
    0.15
    386
    0.15
    bew
    0.14
     intended
    0.14
     Bert
    0.14
    Act Density 0.061%

    No Known Activations