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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "reverse" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anskje
    -0.78
     bParam
    -0.75
     BrowserModule
    -0.71
    AccessorTable
    -0.70
     يتيمه
    -0.69
    ()?;
    -0.69
    примеча
    -0.68
     Skyl
    -0.68
     stør
    -0.66
     ")[
    -0.63
    POSITIVE LOGITS
     Reverse
    1.39
     reverse
    1.35
     reverses
    1.35
     revers
    1.28
    逆
    1.27
    Reverse
    1.26
     reversal
    1.24
     inver
    1.23
     reversed
    1.21
    Reversed
    1.20
    Act Density 0.161%

    No Known Activations