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

    Neuronpedia

    INDEX
    Explanations

    references to examples or instances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Diſ
    -0.81
    "]];
    -0.80
    "];
    -0.75
    ]");
    -0.74
    "]);
    -0.74
     Anſ
    -0.73
    ...");
    -0.72
    "])
    -0.72
    '];
    -0.71
     Houſe
    -0.71
    POSITIVE LOGITS
     например
    0.91
     bijvoorbeeld
    0.89
     example
    0.88
     Например
    0.87
    Например
    0.84
     Misalnya
    0.83
     eksempel
    0.82
     například
    0.82
     exemple
    0.80
     beispielsweise
    0.80
    Act Density 0.212%

    No Known Activations