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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relations in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.81
     مشين
    -0.81
     Diſ
    -0.76
    ...");
    -0.74
    <?
    -0.73
    ulongan
    -0.72
     itſelf
    -0.72
     raiſ
    -0.71
     Jefus
    -0.70
     Anſ
    -0.70
    POSITIVE LOGITS
     example
    1.31
     esempio
    1.17
     ejemplo
    1.14
     eksempel
    1.12
     Beispiel
    1.09
    Например
    1.08
     exempel
    1.07
     eg
    1.06
    например
    1.06
     exemple
    1.06
    Act Density 0.277%

    No Known Activations