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

    Neuronpedia

    INDEX
    Explanations

    content related to social issues, particularly racism and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.58
    ślę
    -0.55
    TagMode
    -0.51
    oa̍t
    -0.50
     StringTokenizer
    -0.49
     >=",
    -0.49
     kysy
    -0.47
     tensione
    -0.45
     segni
    -0.45
    MLLoader
    -0.45
    POSITIVE LOGITS
     hypocritical
    1.01
     laughable
    0.94
     idiotic
    0.93
     hypocrisy
    0.90
     phony
    0.90
     incompetent
    0.90
     propaganda
    0.89
     misguided
    0.89
     pathetic
    0.88
     delusional
    0.86
    Act Density 1.068%

    No Known Activations