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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.58
     esternos
    -0.53
     autorytatywna
    -0.51
    帖最后由
    -0.49
    Personendaten
    -0.49
    Kjelder
    -0.48
    Brainz
    -0.48
    ۣ
    -0.45
    WriteTagHelper
    -0.45
     actionMode
    -0.45
    POSITIVE LOGITS
    0
    0.61
    闪过
    0.40
     gustado
    0.39
    ambién
    0.36
    omości
    0.34
     hablado
    0.34
    exitRule
    0.33
    emploi
    0.33
     Aner
    0.33
    fficient
    0.32
    Act Density 1.020%

    No Known Activations