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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and operations involving variables and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utilisons
    -0.43
     WHEREAS
    -0.43
    ently
    -0.42
     hiszen
    -0.42
     block
    -0.41
     pekan
    -0.39
    Block
    -0.38
     tek
    -0.38
    isesta
    -0.38
     dénon
    -0.38
    POSITIVE LOGITS
    Diweddarwch
    0.80
     resultList
    0.77
     getResult
    0.75
     Anſ
    0.75
     MainAxisSize
    0.73
     anſ
    0.73
     BoxFit
    0.72
    WireFormatLite
    0.72
     output
    0.69
     purpoſe
    0.69
    Act Density 0.331%

    No Known Activations