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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their patterns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()]);
    -0.71
     Bellow
    -0.70
     αὐ
    -0.69
     Dage
    -0.69
     Bens
    -0.68
     Krom
    -0.67
    >");
    -0.64
     Bue
    -0.64
    />
    -0.64
     Bute
    -0.64
    POSITIVE LOGITS
    ftagPool
    0.80
    //
    0.73
     AssemblyCulture
    0.73
    scalatest
    0.71
     crossorigin
    0.66
    aarrggbb
    0.66
    Manbalar
    0.65
     חיצוניים
    0.63
    имость
    0.63
     MacGregor
    0.63
    Act Density 0.175%

    No Known Activations