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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h2>
    -0.57
    /***/
    -0.52
    </h3>
    -0.51
    InjectAttribute
    -0.51
     rien
    -0.50
     发表于
    -0.49
    </b>
    -0.49
    ,}
    -0.47
    [](
    -0.47
    ,
    -0.46
    POSITIVE LOGITS
    ∬
    0.77
     inſ
    0.73
    paisaje
    0.72
     raiſ
    0.72
     ſta
    0.71
    lijck
    0.71
    ftance
    0.70
    obald
    0.68
     Efq
    0.67
     Balth
    0.66
    Act Density 0.410%

    No Known Activations