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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or correlation between multiple subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lindsey
    -0.15
    eric
    -0.15
    izes
    -0.14
    emo
    -0.14
     overall
    -0.14
    ize
    -0.14
     hab
    -0.13
     aged
    -0.13
     Ne
    -0.13
    ie
    -0.13
    POSITIVE LOGITS
    <typeof
    0.15
    Lazy
    0.15
     Levi
    0.14
    ointment
    0.14
    dac
    0.14
    kın
    0.14
    erdem
    0.14
    ollider
    0.14
     æ¥Ń
    0.14
     myself
    0.13
    Act Density 0.067%

    No Known Activations