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

    Neuronpedia

    INDEX
    Explanations

    evaluative phrases related to quality and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     humeur
    -0.54
    AddWithValue
    -0.51
    rophore
    -0.50
    mjs
    -0.47
    AutoModerator
    -0.47
     Thebes
    -0.45
     Erne
    -0.45
    vestre
    -0.45
     levure
    -0.45
    INDA
    -0.44
    POSITIVE LOGITS
    PYX
    0.77
    这么多
    0.65
    这么
    0.62
    これだけ
    0.62
    BoxShadow
    0.62
    這麼
    0.60
     столь
    0.59
    如此
    0.58
    这般
    0.58
     tantos
    0.58
    Act Density 0.189%

    No Known Activations