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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating comparisons and expressions of opinion or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']);
    -0.94
    '));
    -0.90
    "));
    -0.89
    '));
    -0.89
    ']);
    -0.88
    ()));
    -0.88
     "));
    -0.88
    "]);
    -0.87
    "));
    -0.80
    "]);
    -0.80
    POSITIVE LOGITS
    ,
    1.01
    Obrázky
    0.86
    VersionUID
    0.82
    первых
    0.80
    Kedua
    0.76
    Lähteet
    0.75
     싶
    0.74
     Asimismo
    0.73
    Bronnen
    0.72
     Portanto
    0.71
    Act Density 0.757%

    No Known Activations