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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or mild judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     singola
    -0.60
     nicio
    -0.54
     poitrine
    -0.53
     charité
    -0.52
     '\\
    -0.52
     pauvreté
    -0.52
     gloire
    -0.51
    Atoi
    -0.50
    Endless
    -0.49
     ouvriers
    -0.49
    POSITIVE LOGITS
    Somewhat
    0.94
     المعيارى
    0.88
    extAlignment
    0.83
    有点
    0.83
    Kinda
    0.82
     demografica
    0.81
    tagext
    0.80
     Somewhat
    0.79
     abit
    0.79
     bit
    0.78
    Act Density 0.103%

    No Known Activations