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

    Neuronpedia

    INDEX
    Explanations

    the presence of the acronym "BS" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.90
    الإنجليزية
    -0.74
    TemporalType
    -0.71
    Ij
    -0.69
     Nederland
    -0.68
    Hozzáférés
    -0.68
    исленность
    -0.68
     león
    -0.67
    //"
    -0.66
     diabe
    -0.65
    POSITIVE LOGITS
     BS
    1.34
    BS
    1.09
     bs
    1.06
    ")));
    1.05
    bs
    1.03
     photolibrary
    1.00
     itſelf
    0.91
     Jefus
    0.89
    $.
    0.88
     myſelf
    0.88
    Act Density 0.011%

    No Known Activations