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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "same" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jegyzetek
    -0.70
     DiCaprio
    -0.67
    例句
    -0.66
    seamnă
    -0.64
    RegressionTest
    -0.63
     commerciales
    -0.63
     ибо
    -0.63
    >[]
    -0.62
     propOrder
    -0.62
    tipped
    -0.62
    POSITIVE LOGITS
    SAME
    1.58
     same
    1.51
     SAME
    1.49
    Same
    1.46
     Same
    1.41
    same
    1.39
     samme
    1.17
     exact
    1.16
    isSame
    1.09
     samma
    1.05
    Act Density 0.082%

    No Known Activations