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

    Neuronpedia

    INDEX
    Explanations

    words that express negative opinions or judgments about individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     JADX
    -0.54
     ExecuteAsync
    -0.52
    :✨
    -0.51
    UseVisualStyle
    -0.50
    SqlClient
    -0.47
    สึก
    -0.46
    čnih
    -0.45
    MVH
    -0.45
     dreaded
    -0.45
    ьаж
    -0.45
    POSITIVE LOGITS
     stupid
    1.80
     dumb
    1.78
     stupidity
    1.78
     ignorant
    1.74
     foolish
    1.73
     naive
    1.70
     ignorance
    1.68
     Stupid
    1.62
    stupid
    1.60
     blind
    1.58
    Act Density 0.471%

    No Known Activations