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

    Neuronpedia

    INDEX
    Explanations

    references to consistency and similarity across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     препратки
    -0.51
     AssemblyCulture
    -0.44
     fallu
    -0.42
    balleur
    -0.40
    chartInstance
    -0.37
    🇶
    -0.37
    warten
    -0.36
     الرياضيه
    -0.35
    RTEX
    -0.35
    fatalError
    -0.35
    POSITIVE LOGITS
     same
    0.91
    same
    0.84
    Same
    0.82
     Same
    0.79
     SAME
    0.71
    同じ
    0.68
    相同的
    0.67
    同一个
    0.67
     mismo
    0.67
    SAME
    0.66
    Act Density 0.642%

    No Known Activations