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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve comparisons or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortic
    -0.15
    lash
    -0.15
     Echo
    -0.15
    论
    -0.15
     Fang
    -0.14
    oeff
    -0.14
    رÙĬÙĤ
    -0.14
    oria
    -0.14
    eria
    -0.14
    .Encoding
    -0.14
    POSITIVE LOGITS
    icked
    0.14
    estre
    0.14
    onde
    0.14
    iš
    0.14
    اÛĮÙĩ
    0.14
    307
    0.14
    asser
    0.13
     Ñģоп
    0.13
     rival
    0.13
     ci
    0.13
    Act Density 0.169%

    No Known Activations