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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that often conclude statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -1.06
    /***
    -0.96
    ///**
    -0.91
    /**
    -0.89
    <?
    -0.89
    
    -0.88
     springfox
    -0.82
    /*
    -0.79
     AssemblyCompany
    -0.67
    POSITIVE LOGITS
     seksi
    0.86
     soulign
    0.85
     épu
    0.83
     lele
    0.80
     Karakter
    0.78
     véhic
    0.76
     évalu
    0.76
     alté
    0.76
     déchir
    0.75
     marea
    0.74
    Act Density 1.208%

    No Known Activations