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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional formations and constraints in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAK
    -0.44
     glycine
    -0.44
     Patagonia
    -0.44
     buffered
    -0.43
    ője
    -0.43
     Thorpe
    -0.42
    ContextHolder
    -0.42
    puerto
    -0.41
    iterations
    -0.41
    desarrollo
    -0.41
    POSITIVE LOGITS
     BoxDecoration
    0.53
     المعيارى
    0.53
     uſe
    0.50
     Avez
    0.50
    >>();
    0.49
     صوتيه
    0.48
    wirkt
    0.47
    InjectAttribute
    0.47
     يتيمه
    0.46
    legt
    0.46
    Act Density 0.014%

    No Known Activations