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

    Neuronpedia

    INDEX
    Explanations

    the word "keep" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.90
    Personensuche
    -0.87
    homonymie
    -0.86
    Portale
    -0.84
    \{\\
    -0.83
     zů
    -0.82
     rimanere
    -0.82
    ValueStyle
    -0.81
     Saxons
    -0.81
    Clik
    -0.81
    POSITIVE LOGITS
    ::{
    0.77
     kep
    0.71
    /***/
    0.69
     Kep
    0.67
    esp
    0.66
    ]]
    0.65
    </b>
    0.63
    ']]
    0.62
    ftagPool
    0.62
    >>;
    0.62
    Act Density 0.029%

    No Known Activations